Split (1)

train · 8.3M rows

Search is not available for this dataset

conversations listlengths 2 2
[ { "from": "human", "value": "In this task, you are given a conversation between a flight agent and the customer. You are given 4 options and you need to select the goal of the conversation. It is provided as part of customer's context, which has to be one of the following: `book`: Make a new reservation, `cancel`: Cancel an existing reservation, `no_flight`: No flight found for the customer's preference, `no_reservation`: No reservation / No change / No cancellation was made in the conversation, mostly enquiring details\n\nExample input: customer: Hi. \n agent: Hello. How can I help you? \n customer: I would like to change my existing reservation as my plan to go for a holiday trip got postponed. Can you please help me with this? \n agent: Sure, may I know your name please? \n customer: My name is Anthony Phillips. \n agent: Please wait a moment. \n customer: Sure. \n agent: Unfortunately there is no reservation found with your given name. \n customer: Not a problem, thank you for checking. \n agent: Thank you for choosing us.\nExample output: no_reservation\nExample explanation: Here the customer has not asked for any booking, he just wanted to update his already booked flight, so the status would be no_reservation\nQ: customer: Hello. \n agent: Hello. How can I aid you? \n customer: I am Jonathan Williams. Can you please cancel my reservation as meeting with my client got postponed? \n agent: Ok, please wait I will revert you. \n customer: Sure. \n agent: We found reservation on your name and it is cancelled. \n customer: Ok. Thank you. \n agent: Thank you for availing us.\nA:" }, { "from": "gpt", "value": "cancel" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given the beginning and the ending of a three-part story. Your job is to complete the short story by writing a middle sentence that seamlessly connects the first and last sentence. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the middle sentence, and use names (e.g. Jack, Barbara,...) instead of pronouns (e.g. he / she) wherever possible.\nQ: Beginning: Tim was competing with his brother. Ending: They both quit and decided it didn't matter who was stronger.\nA:" }, { "from": "gpt", "value": "They decided to see who could bench press more weight." } ]
[ { "from": "human", "value": "You are given two sentences(Sentence1 and Sentence2). Answer \"Yes\" if these sentences are a paraphrase of one another, otherwise answer \"No\".\n\nSentence1: Searches for survivors from several previous shipwrecks have often had to be abandoned for similar reasons , leaving the vessels and most of their passengers unaccounted for ., Sentence2: In several previous shipwrecks , the search for survivors had to be abandoned for similar reasons , leaving the vessels and most of their passengers unaccounted for ." }, { "from": "gpt", "value": "Yes" } ]
[ { "from": "human", "value": "TASK DEFINITION: You will be given a summary of a story. You need to create a question that can be answered from the story. You can create a question about characters, events, facts and beliefs, etc. Your question should be specific, try not to use pronouns instead of full names. As the stories are sometimes movie plots, they will contain actor names in parentheses. You should not use those names. Only use character names. Try to ask a question about all parts of the plot, not just the beginning.\nPROBLEM: Miguel \"Sugar\" Santos (Perez Soto) spends his weekends at home, passing from the landscaped gardens and manicured fields on one side of the guarded academy gate to the underdeveloped, more chaotic world beyond. In his small village outside San Pedro de Macor s, Miguel enjoys a kind of celebrity status. His neighbors gather to welcome him back for the weekend; the children ask him for extra baseballs or an old glove. To his family, who lost their father years before, Miguel is their hope and shining star. With the small bonus he earned when he signed with the academy some time ago, he has started to build his family a new house one that has a bigger kitchen for his mom and a separate room for his grandmother.\nAfter learning a devastating knuckle curve, Sugar is invited to spring training by the fictional Kansas City Knights. He is assigned to their Single A affiliate in Iowa, the Swing. He is housed by the Higgins family, who take in Swing players every year. Jorge (Rufino), a veteran player and the only other Dominican on the team, also tries to help Miguel learn the ropes. However, despite the Higgins' welcoming efforts and Jorge's guidance, the challenge of Miguel's acceptance into the community is exposed in small ways every day, from his struggle to communicate in English to an accident of casual bigotry at a local bar.\nMiguel's domination on the mound masks his underlying sense of isolation, until he injures himself during a routine play at first. While Miguel is on the disabled list, Jorge, his one familiar connection to home in this strange new place, is cut from the team, never fully regaining his ability following off-season knee surgery. The new vulnerability of Miguel's injury, coupled with the loneliness of losing his closest friend, force Miguel to begin examining the world around him and his place within it. Pressure mounts when Salvador, a young pitching phenom who used to play with Miguel, is brought up from the Dominican Republic to join the team. Miguel's play falters, and the increased isolation begins to take its toll on him. As his dream begins to fall apart, Miguel decides to leave baseball to follow another kind of American Dream. His odyssey finally brings him to New York City, where at first he struggles to find community and make a new home for himself, like so many before him. Miguel ends up playing baseball with rejected players from the minor leagues.\n\nSOLUTION: Who joins the team and brings discouragement to Miguel?\n\nPROBLEM: In 1944, with the help of Russian mystic Grigori Rasputin, the Nazis build a dimensional portal off the coast of Scotland and intend to free the Ogdru Jahad monstrous entities imprisoned in deep space to aid them in defeating the Allies. Rasputin opens the portal with the aid of his disciples, Ilsa von Haupstein and Obersturmbannf hrer Karl Ruprecht Kroenen, member of the Thule Society and Adolf Hitler's top assassin. An Allied team is sent to destroy the portal, guided by a young Trevor Broom, who is well-versed in the occult. The German team is killed and the portal is destroyed in the process absorbing Rasputin while Haupstein and Kroenen escape. The Allied team discovers that an infant demon with a right hand of stone came through the portal; they dub him \"Hellboy\" and Bruttenholm adopts him.\nSixty years later, FBI agent John Myers is transferred to the Bureau of Paranormal Research and Defense (BPRD) at the request of Broom and he meets the adult Hellboy and a psychic, amphibious humanoid named Abe Sapien. He learns that a third BPRD member, Liz Sherman, has recently checked into a mental hospital to protect others from her volatile pyrokinetic abilities. Despite regular visits and coaxing from Hellboy, she is determined not to return. Kroenen and Haupstein resurrect Rasputin in the mountains of Moldova and the three unleash a hellhound known as Sammael. Rasputin imbues Sammael with the power to reincarnate and split his essence, causing two of the creature's eggs to hatch and mature each time one dies. Rasputin visits Liz as she sleeps, activating her powers and almost destroying the hospital. Myers convinces her to return to the Bureau.\nSammael's ability to multiply becomes a problem, as Hellboy repeatedly kills it, dozens are born. Concluding the eggs are in the sewer, Hellboy, Abe and several FBI agents go down the sewer to destroy them. Abe is injured while looking for the eggs, Kroenen kills most of the agents. Kroenen, whose mutilated body is run by mechanical parts, shuts himself down, pretending to be defeated. Kroenen's body is brought to the bureau. FBI Director Tom Manning is angered by Hellboy's recklessness. Myers takes Liz out for coffee and to talk. Hellboy, jealous, covertly follows them, leaving the bureau unguarded. Kroenen reanimates himself and Rasputin appears at the bureau, confronting Professor Broom. Rasputin offers him a vision of the future, showing Hellboy is the agent that will destroy the world. Broom is stabbed in the neck by Kroenen and dies clutching a rosary.\nManning takes over the B.P.R.D. and locates Rasputin's mausoleum in an old cemetery outside Moscow, Russia. A team led by Manning and Hellboy enter the mausoleum, but swiftly become separated. Hellboy and Manning find their way to Kroenen's lair and defeat him. Hellboy reunites with Liz and Myers at Sammael's new nest, but the creatures overwhelm them. Liz uses her pyrokinetic powers to incinerate the Sammaels and their eggs. Hellboy, Liz and Myers lose consciousness and are captured by Rasputin and Haupstein. Rasputin sucks Liz's soul out of her body, then tells Hellboy to release the Ogdru Jahad in return for her soul. Hellboy awakens his true power as Anung un Rama, causing his horns to regrow, and begins to release the Ogdru Jahad. Myers breaks out of his restrain, subdues Haupstein, and reminds Hellboy that he can defy his destiny. Remembering his true self and what Bruttenholm brought him up to be, Hellboy breaks his horns, reseals the Ogdru Jahad and stabs Rasputin with one of his broken horns.\nRasputin has been possessed by a creature from the Ogdru Jahad. The tentacled Behemoth bursts out of his body and grows to immense size, killing him and Haupstein. Hellboy allows himself to be swallowed by the beast, then detonates a belt of hand grenades and destroys it from the inside. He whispered something in Liz's ear and she is revived. When she asks how her soul was returned, Hellboy replies that he threatened to come to \"the other side\" to claim it back. Liz and Hellboy share a kiss.\n\nSOLUTION: Who ultimately reseals the Ogdru Jahad?\n\nPROBLEM: Finn McMissile, a British spy, infiltrates the world's largest untapped oil reserves owned by a group of lemon cars. After being discovered, he flees and fakes his death.\nLightning McQueen, now a 4-time Piston Cup champion, returns home to Radiator Springs to enjoy some quiet time, but when Italian formula race car, Francesco Bernoulli, challenges McQueen to the newly created World Grand Prix, led by its creator Sir Miles Axlerod, he and his best friend Mater along with Luigi, Guido, Fillmore, and Sarge depart for Tokyo for the first race of the Grand Prix. Meanwhile, the lemons, who are led by weapons designer Professor Z ndapp and an unknown mastermind, secretly plot to secure their oil profits by using an Electromagnetic pulse emitter disguised as a camera (discovered by Finn on the oil platform) to trigger and destabilize the use of Allinol, a fuel that was created by Axlerod and required for racers to use in the Grand Prix. McMissile and his partner Holley Shiftwell attempt to meet with American spy car Rod \"Torque\" Redline at a World Grand Prix promotional event in Tokyo, to receive information about the mastermind. However, Redline is attacked by Z ndapp's henchmen, but not before passing his information to Mater before he is captured, who is then mistaken to be the American contact of Holley and Finn. Before killing Redline, Professor Z ndapp finds out that Mater was given the information.\nAt the first race, three cars are ignited by the camera, and McQueen falls second in the race after Bernoulli, due to Mater accidentally giving him bad racing advice shortly after evading Z ndapp's henchmen with help from Holley and Finn. Mater is soon abducted by Finn and boards his plane, where he helps to identify some of the information he was given. After traveling to Paris to get more information from Finn's old friend, they travel to Italy, where the next race is being held. While the race is being held, Mater infiltrates the criminals' meeting, just as the camera is used on a few more cars, causing a multi car pileup, while allowing McQueen to finish first. Due to the criminals plan causing Allinol to be perceived as troublesome, Sir Miles Axlerod removes it as a required fuel for the final race. However, when McQueen decides to continue using it, the criminals plot to kill McQueen in the next race in London, which spooks Mater, causing him to blow his cover and allow him, Finn and Holley, to be abducted.\nTaken to the inside of the clock tower of Big Ben clock in London and tied up in it, while the final race is being held, Mater discovers that the camera did not function on McQueen, but quickly learns the criminals are planning to plant a bomb on him in his pits, causing him to break free and escape. Finn and Holley escape later, but realize that the bomb is on Mater's air filter. Mater soon flees on the race course when McQueen (who arrived at the pits) chases after him, while Finn apprehends Professor Z ndapp. The other lemons soon arrive and outnumber Finn, Holley, Mater, and McQueen, but they are soon rescued by the arrival of the other Radiator Springs residents. Mater then uses evidence he had seen to reveal that Axlerod is the leader of this plot and placed the bomb on him, whom he soon confronts and forces to deactivate the bomb, before he and the other lemons are taken into custody, foiling the operation.\nIn the end, Mater receives a honorary knighthood from the queen, while Sarge reveals that he changed McQueen's fuel from Allinol to gasoline, hence why the camera did not work on him. Finn and Holley ask if Mater can join them on another mission, but he turns it down. The final scene ends with the World Grand Prix competitors racing each other at Radiator Springs.\n\nSOLUTION:" }, { "from": "gpt", "value": "Who is the 4-time Piston Cup champion's best friend?\n\n" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, positions of two consecutive words have been swapped. You need to output the position of the swaped words. e.g. in the sentence 'Seattle has nice a weather', the word 'a' and 'nice' have been swapped. These words are at 3rd and 4th position respectively. So, the output should be (3, 4). Note that the index of first word is 1.\n\nfront The of a crane is lifted off the ground\n" }, { "from": "gpt", "value": "(1, 2)" } ]
[ { "from": "human", "value": "In this task you will be given a list of integers. You should remove any integer that is not prime. A prime integer is an integer that is only divisible by '1' and itself. The output should be the list of prime numbers in the input list. If there are no primes in the input list an empty list (\"[]\") should be returned.\nOne example is below.\nQ: [47, 444, 859, 530, 197, 409]\nA: [47, 859, 197, 409]\nRationale: The integers '444' and '530' are not prime integers and they were removed from the list.\nQ: [107, 421, 262, 964, 199, 515, 374, 355, 452, 694]\nA:" }, { "from": "gpt", "value": "[107, 421, 199]" } ]
[ { "from": "human", "value": "You are given a question. You need to detect which category better describes the question. A question belongs to the description category if it asks about description and abstract concepts. Entity questions are about entities such as animals, colors, sports, etc. Abbreviation questions ask about abbreviations and expressions abbreviated. Questions regarding human beings, description of a person, and a group or organization of persons are categorized as Human. Quantity questions are asking about numeric values and Location questions ask about locations, cities, and countries. Answer with \"Description\", \"Entity\", \"Abbreviation\", \"Person\", \"Quantity\", and \"Location\".\n\nExample Input: What 's the shape of a camel 's spine ?\nExample Output: Entity\n\nExample Input: Who invented the fountain ?\nExample Output: Person\n\nExample Input: How many miles of veins are in the circulatory system ?\nExample Output:" }, { "from": "gpt", "value": "Quantity\n\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nWe would like you to classify each of the following sets of argument pairs (discussing Gay Marriage) into either SIMILAR or NOT SIMILAR. A pair of arguments is considered SIMILAR if the arguments are about the same FACET (making the same argument), and is considered NOT SIMILAR if they do not have the same FACET. A FACET is a low level issue that often reoccurs in many arguments in support of the author's stance or in attacking the other author's position.\n\nSent1: Many social conservatives argue that benefits are provided to married couples because, in turn, married couples benefit society. \n Sent2: We give married couples marriage benefits TO STRENGTHEN the marriage, because marriage STRENGTHENS society.\nSolution: Similar\nWhy? Both arguments argue that married couples can benefit the society.\n\nNew input: Sent1: Though I didn't vote, I do financially support ACLJ against gay marriage simply because a union between same sex couples can easily have their rights established through adoption, wills, or power of attorneys.\n Sent2: Gay rights advocates argued the state was violating their civil rights by limiting marriage to opposite-sex couples.\nSolution:" }, { "from": "gpt", "value": "Not similar" } ]
[ { "from": "human", "value": "In this task, you will be given a list. The list is several integers and letters separated with a comma, written within a []. You can create new lists by dropping one of the items in the input list. Your task is to write a list containing all the possible lists you can make by dropping one item from the input list. For example, if the input list contains two items, you can drop one of the items each time. So the output should be a list comprising two inner lists that you have created by decreasing the items.\n\n['U', '9', '1', 'g', 'q', 's']\n[['U', '9', '1', 'g', 'q'], ['U', '9', '1', 'g', 's'], ['U', '9', '1', 'q', 's'], ['U', '9', 'g', 'q', 's'], ['U', '1', 'g', 'q', 's'], ['9', '1', 'g', 'q', 's']]\n\n['B', 'F', 'K', '8', 'r', 'Z', 'h']\n[['B', 'F', 'K', '8', 'r', 'Z'], ['B', 'F', 'K', '8', 'r', 'h'], ['B', 'F', 'K', '8', 'Z', 'h'], ['B', 'F', 'K', 'r', 'Z', 'h'], ['B', 'F', '8', 'r', 'Z', 'h'], ['B', 'K', '8', 'r', 'Z', 'h'], ['F', 'K', '8', 'r', 'Z', 'h']]\n\n['h', '5', '5', 'y']\n" }, { "from": "gpt", "value": "[['h', '5', '5'], ['h', '5', 'y'], ['h', '5', 'y'], ['5', '5', 'y']]\n\n" } ]
[ { "from": "human", "value": "You are given two sentences(Sentence1 and Sentence2). Answer \"Yes\" if these sentences are a paraphrase of one another, otherwise answer \"No\".\nOne example is below.\nQ: Sentence1: While it was being called mandatory , Dupont said authorities were not forcing people from their homes ., Sentence2: It was called mandatory , but Dupont said authorities did not force people to leave .\nA: Yes\nRationale: These sentences have the meaning. So, the output should be \"Yes\".\nQ: Sentence1: Random testing of security procedures should also take place ., Sentence2: Security assessments of these facilities should take place every three years .\nA:" }, { "from": "gpt", "value": "Yes" } ]
[ { "from": "human", "value": "Teacher:In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the count of all the numerical elements in the given list. Return 0 if no numerical element in the list.\nTeacher: Now, understand the problem? Solve this instance: ['235', 'v', '895', 'K', '3461', 'j', '3517', '479', 'A', '5283', 'a', 'x', '7537', 'T', '8619', 's', 'O', 'H', 'Z', '1239', '2847', 'h', 'T', 'x', 't', '7277']\nStudent:" }, { "from": "gpt", "value": "11" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a question and an answer. Answer \"Yes\" if the given answer correctly answers the question, otherwise answer \"No\".\nProblem:what year did the last monkeys go into space, Answer: The Soviet Union and Russia launched monkeys between 1983 and 1996.\nSolution:" }, { "from": "gpt", "value": "Yes" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the alphabetical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no alphabetical element is in the list.\nQ: ['2039', '8895', '4917', '4273', '8797', 'B', '2917', 'D', 'K', '3391', '1333', 'G', '3997']\nA:" }, { "from": "gpt", "value": "6, 8, 9, 12" } ]
[ { "from": "human", "value": "Definition: Given a command in a limited form of natural language, provide the correct sequence of actions that executes the command to thus navigate an agent in its environment. A command can be broken down into many different actions. Actions are uppercase and are individual steps that serve as the building blocks for a command. For commands, 'left' and 'right' are used to denote the direction of an action. The word 'opposite' turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. Actions and commands do not have quotations in the input and output.\nInput: jump opposite right and look twice\nOutput:" }, { "from": "gpt", "value": "I_TURN_RIGHT I_TURN_RIGHT I_JUMP I_LOOK I_LOOK" } ]
[ { "from": "human", "value": "In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis. It makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis. It makes you much more likely to believe the hypothesis is true. Your task is to output 'strengthener' or 'weakener' if the update strengths or weakens the hypothesis, respectively.\n\n[Q]: Premise: PersonX almost fell\nHypothesis: PersonX then puts hands out\nUpdate: PersonX saw a wall to brace.\n[A]: strengthener\n\n\n[Q]: Premise: PersonX rolls on PersonY's back\nHypothesis: PersonX is seen as in control\nUpdate: PersonY taps out\n[A]: strengthener\n\n\n[Q]: Premise: PersonX hits PersonY hard\nHypothesis: Before, PersonX needed get angry\nUpdate: PersonX wasn't watching as they were skiing down the hill.\n[A]:" }, { "from": "gpt", "value": "weakener\n\n\n" } ]
[ { "from": "human", "value": "In this task you will be given a list of lists, of numbers. For every inner list, you should multiply every number in that list and put the results in your answer. The output should be a list of numbers with the same length as the number of the lists in the input list.\nExample: [[5, 1, 2, 7], [0, 4, 6, 6], [7, 8, 10, 3, 1], [1, 4]]\nExample solution: [70, 0, 1680, 4]\nExample explanation: The second list had zero so the second product is zero. Every product is calculated correctly: 5x1x2x7= 70, 7x8x10x3x1=1680, 1x4=4.\n\nProblem: [[39, 20, 46, 9, -38], [3, 32, 18], [-42, 14, -41], [33, 29, -30, 34], [5, -34, 43, -24], [10, -43], [41, -32, 45, 29, -1], [-24, -14, -43]]\n" }, { "from": "gpt", "value": "Solution: [-12270960, 1728, 24108, -976140, 175440, -430, 1712160, -14448]" } ]
[ { "from": "human", "value": "Instructions: In this task, you will be shown an extract from a movie plot and a question. You need to provide the correct answer for it. Short answers containing words that are present in the passage are preferred.\nInput: Steve Clark (James Marsden) is a high school senior whose family moves to Cradle Bay, a picturesque coastal town in Washington state's Puget Sound with his parents. It has been nearly one year since Steve's older brother, Allen (Ethan Embry), committed suicide which traumatized the family. Steve's parents tell him that they have relocated from Chicago to Cradle Bay as a fresh start to move on with their lives.During Steve's first day at his new high school, he meets and befriends three outcast students, Gavin Strick (Nick Stahl), U.V. (Chad E. Donella), and Rachel \"Rae\" Wagner (Katie Holmes). Gavin tries to tell Steve that he believes there is something evil about the \"Blue Ribbons\"a clique of students taking part in a \"special program\" led by the school psychologist, Dr. Caldicott (Bruce Greenwood). Steve is understandably skeptical.Steve witnesses a fight in class between a student, Dickey, and one of the Blue Ribbons. Later, Dickey is trying to buy car parts for his muscle car at an out-of the way marina, and is accosted by the Blue Ribbons. Soon after, Dickey reappears at school, now one of the Blue Ribbons, and having donated his once-prized car to a demolition fundraiser.Steve goes to a local yogurt shoppe where the Blue Ribbons congregate. Steve comments about seeing Dickey and his recent adversary sitting together, to which Dickey replies \"We made peace\". Gavin arrives to meet Steve, and takes him outside after a tense exchange with the group of Blue Ribbons. Gavin shows a photograph of himself and several Blue Ribbons, who were until recently rocker/parties types. The two eavesdrop on a parents meeting, where Gavin learns his parents have signed him up for Caldicott's program. Steve remains skeptical of Gavin's fears of the Blue Ribbons and the program, and wrestles a gun Gavin produces, which he plans to use against his expected abductors. Steve heads home.The following day at lunch, Gavin walks in looking like a Blue Ribbon. When Steve tries to confront Gavin, he gets punched in the stomach for his impertinence. Later, after being chased home, Steve finds Blue Ribbon member Lorna Longley in his living room, ostensibley waiting up after tutoting Steve's younger sister while Steve's parents are \"At a meeting\". Steve suggests she leave. She asks to use the bathroom first, then emerges, partial undressed, and forcefully kisses Steve. Her heightened arousal causes her eye to glow red, startling Steve. Lorna starts saying \"wrong, bad\" then smash her head into a mirror, attacks Steve with a mirror shard, them obliviously leaves the house. She is later seen undergoing treatment at a medical facility under Dr. Caldicott's direction.During this time, Steve also befriends Dorian (William Sadler), the school janitor, who appears to be mentally handicapped and hunts rats for the city for some extra cash. Dorian demonstrates a device called an E-Rat-icator which emits a soft, high pitched whine that is supposed to be innocuous but annoying to rats, which is an abysmal failure. Steve discovers that Dorian is actually highly intelligent, and carries classical literature pieces with him, and that he's hiding because he wishes to be left alone and does not trust society. Dorian also tells Steve that he suspects that the entire community of Cradle Bay is part of a massive conspiracy made up of nearly all of the parents, the local police chief, the school principal and entire school faculty, who hired Dr. Caldicott to \"re-program\" their own children to become the perfect people that they want them to be and not free-thinkers. Rachel finds a CD-R disc that Gavin hid in the school's boiler room, containing a video he made of himself before his \"transformation\", telling about the club and about the history that he learned about Dr. Caldicott. A Blue Ribbon known as \"Chug\" (A.J. Buckley) assaults Rachel in the basement, when Dorian's E-Rat-icator goes off, and immediately sends Chug into a agonized frenzy, during which Rachel slips away. Chug smashes the E-Rat-cator and walks out, apparently oblivious to what has just occurred.During their personal investigation, Steve and Rachel try to find out what exactly has been happening to the Blue Ribbon kids, which leads them to a mental hospital called Bishop Flats following a lead on the disc that Gavin left behind in the basement (which Rachel had retrieved before her encounter with Chug). At Bishop Flats, they find out that mind control is being used to make depressed, awkward and unruly teens become perfect so they can function properly in life, but the programming has some glitches that lead to momentary relapses and violent fits. Also at Bishop Flats, they find Caldicott's daughter, Betty (Julie Patzwald), a failed project who spends her time repeating the same phrase: \"Meet the musical little creatures that hide among the flowers\", along with other damaged test subjects who compulsively brush, floss and apply makeup.After escaping from the hospital, Steve and Rachel return to Cradle Bay to plan to rescue Lindsey before fleeing town. They have a run-in with the town's police chief Cox (Steve Railsback) who is also involved in the conspiracy. He tries to arrest them for being out after curfew. But Dorian shows up under the pretense that he is disposing of dead rats, then knock out the police chief and frees Steve and Rachel, telling them to leave town and go public with what they know about Dr. Caldicott's work.When Rachel and Steve return to Steve's home to get Lindsay (Katharine Isabelle), Steve's parents (Terry David Mulligan and Susan Hogan) reveal that they are also part of the conspiracy and that they moved to Cradle Bay for the purpose to sign him up for Caldicott's program, and Caldicott himself confronts them. Steve and Lindsay try to get out but they get ambushed by a group of Blue Ribbons waiting for them outside the house. They drag Steve and Rachel to the programming center. Steve grabs a scalpel before being strapped into a chair. He confronts Caldicott about the human cost of the reprogram, but Caldicott is dismissive, including in regard to his own daughter. Before the reprogramming can start, Steve uses the scalpel to cut his bonds and escape to rescues Rachel, killing the medical techs. On the way out, they fight and kill Chug, who has been left behind to guard them.Exiting what turns out to be the town's hospital basement, Steve and Rachel are met by Lindsay and U.V. in Rachel's truck. Rushing to catch the early ferry, they meet with a roadblock made of Blue Ribbons and Caldicott on the road. When hope seems lost, Dorian drives up, striking Caldicott, and activating multiple E-Rat-icators that scramble the mind control tech inside the Blue Ribbons' heads. They chase after Dorian and try to destroy the E-Rat-icators Dorian, having been fatally wounded by a gunshot from Caldicott, and believing the Blue Ribbons to be beyond help, drives his car off a cliff with most of the Blue Ribbons hanging onto it. An injured Caldicott reappears, reacting to Steve's declaration that \"It's over\" by saying he will start his experiments again elsewhere. This leads to a final battle between Steve and Caldicott, which Steve wins by kicking Caldicott off the cliff. Steve and Rachel then leave town on the ferry with Lindsay and U.V. to begin a new life elsewhere without their parents.The final scene shows a classroom in an urban high school with kids playing loud music, cursing, and acting up. They are informed that they have a new student teacher. The well-groomed teacher turns around after writing on the board, and it's Gavin, with the blue ribbon \"red twinkle\" still active in his eye., Question: What is the name given to the group of students Dr. Caldicott's special program?\nOutput:" }, { "from": "gpt", "value": "Answer: Blue Ribbons" } ]
[ { "from": "human", "value": "In this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\n\nExample Input: Sentence 1: Girl with arms crossed, a man with a gray beard holding a glass, and a baby sitting on a porch. Sentence 2: The three people are in a getaway car crossing the state line.\nExample Output: a girl with crossed arms, a man with a gray beard holding a glass, and a baby sit on a porch.\n\nExample Input: Sentence 1: A dog running through the water right toward the camera. Sentence 2: Dog sleeping on the lawn.\nExample Output: Dog running through water.\n\nExample Input: Sentence 1: A woman in brown boots sits with her legs crossed. Sentence 2: the woman is standing next to a wookie\nExample Output:" }, { "from": "gpt", "value": "the woman is sitting\n\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nGiven a sentence in Tagalog language, translate the sentence to English language keeping the meaning of the original sentence intact.\n\nTagalog sentence: Maaari tayong tumugon sa mga sumusunod na pamamaraan: 1) Nais mo bang panagutan ang kasalanan ng mga tao na nagkasala mahigit 900 taon na ang nakararaan? 2) Nais mo bang panagutan ang mga kasalanan ng lahat ng nagsasabi na sila ay Kristiyano nunit hindi totoong Kristiyano? Ang paninisi sa buong sangka -Kristiyanuhan para sa mga krusada ay katulad din ng paninisi sa lahat ng mga Muslim para sa mga gawain ng terorismo ng Islam. Bumalik sa Tagalog Home Page Ano ang mga krusadang Kristiyano? Maghanap para sa:\nOutput:" }, { "from": "gpt", "value": "We can respond in the following ways: 1) Do you want to be held accountable for the actions of people who lived 900+ years ago? 2) Do you want to be held accountable for the actions of everyone who claims to represent your faith? Trying to blame all of Christianity for the crusades is analogous to blaming all Muslims for Islamic terrorism." } ]
[ { "from": "human", "value": "In this task, you will be presented with a question in Dutch language, and you have to write the location names from the question if present. B denotes the first item of a phrase and an I any non-initial word. Identifier used for the location name - LOC. . There can be instances with no location name entity, then return 'None'.\n\nExample input: Jean Alavoine ( Fra )\nExample output: Fra: B-LOC\nExample explanation: In the given sentence, Fra is identified as the location, which is correct.\nQ: Ofwel heeft het graan of de installatie zelf de besmetting veroorzaakt .\nA:" }, { "from": "gpt", "value": "None" } ]
[ { "from": "human", "value": "Teacher: You are supposed to identify the category of a high-school level math question. There are five possible categories (1) algebra (2) arithmetic (3) measurement (4) numbers, and (5) probability. Use the following guidelines: (1) 'algebra' questions will typically contain letter variables and will ask you to find the value of a variable (2) 'arithmetic' questions will ask the sum, difference, multiplication, division, power, square root or value of expressions involving brackets (3) 'measurement' questions are questions that ask to convert a quantity from some unit to some other unit (4) 'numbers' questions will be about bases, remainders, divisors, GCD, LCM etc. (5) 'probability' questions will ask about the probability of the occurrence of something. A question must belong to only one category.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nSuppose -d - 13 = -n - 0, 0 = 2d + 2. Solve 2x = -10 + n for x.\nSolution: algebra\nReason: This is a system of three linear equations, clearly an 'algebra' question. Standard methods of solving linear equations can be used to obtain the solution.\n\nNow, solve this instance: Three letters picked without replacement from hhoohhhhohhhooooooh. What is prob of sequence ooh?\nStudent:" }, { "from": "gpt", "value": "probability" } ]
[ { "from": "human", "value": "Detailed Instructions: Your task is to generate the next utterance in a given dialogue. You will be given a few sentences describing the personality of the person who is making the dialogue, and a history of the dialogue after that. Each line in the history is said by one of the two participants in the conversation.\nProblem:Personality: I own 4 cats.\nMy favorite band is metallica.\nI work at the grocery store.\nI am a college student.\nChat history: -Good afternoon, how are you today?\n -I am great, just heading into class and then off to work at Walmart. Hbu?\n -Well, normally I would be out flying my kite but with the hurricane I am staying in.\n -Oh are you in Florida? I would be scared for my 4 cats.\n -My car died tuesday so I was worried but I was able to get it fixed Friday.\n -Oh that's good. Do you like music?\n -I do! I listen to it when I work out.\n -Nice! Whats your favorite band? Mine is metallica.\n -I like red hot chilli peppers.\n -They are really cool too.\n -Yes, I like turn of the century bands.\nSolution:" }, { "from": "gpt", "value": "Yeah they're definitely good too." } ]
[ { "from": "human", "value": "You are given an original reference as well as a system generated reference. Your task is to judge the naturaleness of the system generated reference. If the utterance could have been produced by a native speaker output 1, else output 0.\n\nEx Input:\nSystem Reference: may i ask near where?\nOriginal Reference: where are you looking?.\n\nEx Output:\n0\n\n\nEx Input:\nSystem Reference: sw hotel is near chinatown has internet.\nOriginal Reference: sw hotel in chinatown has internet.\n\nEx Output:\n0\n\n\nEx Input:\nSystem Reference: can i double check you want a hotel that has internet?\nOriginal Reference: would you like to know if it has internet?.\n\nEx Output:\n" }, { "from": "gpt", "value": "0\n\n\n" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task you will be given a string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.\n\nonesevenfouronetwozerosixfour\n" }, { "from": "gpt", "value": "17412064" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nYou are given a question. You need to detect which category better describes the question. A question belongs to the description category if it asks about description and abstract concepts. Entity questions are about entities such as animals, colors, sports, etc. Abbreviation questions ask about abbreviations and expressions abbreviated. Questions regarding human beings, description of a person, and a group or organization of persons are categorized as Human. Quantity questions are asking about numeric values and Location questions ask about locations, cities, and countries. Answer with \"Description\", \"Entity\", \"Abbreviation\", \"Person\", \"Quantity\", and \"Location\".\n\nWhat's the most common name in nursery rhymes ?\nSolution: Person\nWhy? This question is about people's names. So, the output should be \"Person\".\n\nNew input: What country surrounds San Marino , the world 's smallest Republic ?\nSolution:" }, { "from": "gpt", "value": "Location" } ]
[ { "from": "human", "value": "Detailed Instructions: Given the sentence, generate \"yes, and\" response. \"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). 1 In short, a \"Yes, and\" is a dialogue exchange in which a speaker responds by adding new information on top of the information/setting that was constructed by another speaker. Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange, although it could be the case if it agrees with the description above. There are many ways in which a response could implicitly/explicitly agree to the prompt without specifically saying 'yes, and...'. \nQ: Hello, are you from Melbourne?\nA:" }, { "from": "gpt", "value": "Yeah, I'm from Melbourne and Australia." } ]
[ { "from": "human", "value": "In this task, you are given a review of a movie and a boolean question whether this review has positive sentiment or negative sentiment. Your task is to generate answer \"yes\" when the tweet has that particular sentiment, otherwise generate answer \"no\".\n\n[EX Q]: Review: This is one of the funniest movies i've ever seen. I rented it as a joke, expecting to get a giggle out of the first few scenes, and let me just say I've never laughed so hard in my life. The first scene where ninjas randomly pop out of the air and start a huge and ridiculous fire fight is one of the most incredibly funny stupid action movie moments of my life. This is not a dinosaur movie, but more a movie that makes fun (and doesn't mean to at all) of the action genre. I didn't see the first two, but judging by the complexity of the plot, I don't think there's to much I missed. If you wanna see a movie that goes great with a six pack or any herbal remedy, than I insist you rent this movie and sit back and watch a 100 years of advancement in cinema get thrown in the trash and get shat on by carnosours Question: is it a positive review?\n[EX A]: no\n\n[EX Q]: Review: Filmatography: Excellent, nice camera angles (I don't remember seeing a movie of late, with good close-ups, until this one). Could have avoided gruesome scenes with a soft camera. NY is pictured good.I liked the upside down angles, in particular (a different touch).Music: Not impressive. Songs don't stick around in your mind even after watching the movie. May be, I expected same quality like \"Anniyan\". A disappointment. Actors: Kamal needs to slowly pull away from hard-core action sequences. His age and belly really show up. Also, he should avoid close romantic sequences going forward. It was a very awkward to see a mature/aged star still trying to play like a 20+ heroes scenes. Love can be expressed at any age; as we get older, you still can express love nicely from a distance (without touching a woman too much. For example, the love expressed by Rajinikanth in \"chandrmukhi\").Jyotika just appears for the namesake in the movie. Not sure why she accepted this. Well, that is not my problem, I guess.Others just have a small presence.Direction: I expected Gautham to excel (or measure-up) to his other movie \"Kakka Kakka\". He disappointmented me. It took a long time to release the movie due to various issues. He slips in few scenes. Even abvious things got slipped from a famous director.Overall: Just a okay movie. Too much graphics. DEFINITELY not for kids (and adults who expect some kind of \"Entertainment\").Thx Question: is it a negative review?\n[EX A]: yes\n\n[EX Q]: Review: This film was so predictable, that during the entire time you're hoping that the obvious suspect is innocent, and there's some other big twist still coming. However... it doesn't. He just continues to act creepy, and she continues to ignore it. Mary found very incriminating evidence at his place, and she still trusted him? And what was that \"baiting the trap\"? There was no trap. She confronted him, he said \"excuse me. I have to go kill someone\" He left, and that was the end of it. They make attempts to use other suspects, (like that one older carnival girl at the end) but they're completely underdeveloped. Actually, all the characters are underdeveloped. They have no depth, and the setting is just plain strange... who hangs out in a recycling factory?? Its choppy and nothing is well developed. For example: When she leaves his place after having the beer, and he finds the pics and she runs out and he catches her and they end up having sex in that car... what was that? Her reactions weren't portrayed. In the car she acted scared like it could have been practically rape- but then all we see is her showering the next morning. booooooooo It could have been so much better.. sooo much better. Question: is it a negative review?\n[EX A]:" }, { "from": "gpt", "value": "yes\n\n" } ]
[ { "from": "human", "value": "Q: In this task, you're given a context passage, a question, and three answer options. Your task is to return an incorrect answer option to the question from the choices given. For all questions, only one of the three answer options is correct. Pick one of the two incorrect answer options as the output.\nContext: Addison talked to Remy like he was no good at all. \n Question: What will Addison want to do next? \n Options: (A) ask Remy out on a date (B) sorry (C) ask Remy to marry them\nA:" }, { "from": "gpt", "value": "C" } ]
[ { "from": "human", "value": "In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to classify the command into one of these seven categories: (1) majority, (2) unique, (3) superlative, (4) count, (5) comparative, (6) aggregation, and (7) ordinal. \n Here are the defications of each category: \n 1. majority: Describing the majority values (most or all) over one column, with the scope of all table rows or a subset of rows \n 2. unique: Describing one unique row, regarding one column, with the scope of all table rows or a subset of rows \n 3. Superlative: Describing the maximum or minimum value in a column, with the scope of all table rows or a subset of rows \n 4. Ordinal: Describing the n-th maximum or minimum value in a column, with the scope of all table rows or a subset of rows \n 5. Comparative: Comparing two rows in the table, regarding their values in one column \n 6. Count: counting some rows in the table based on the values in one column, with the scope of all table rows or a subset of rows \n 7. Aggregation: Describing the sum or average value over a column, with the scope of all table rows or a subset of rows. \n Here are the definitions of logical operators for understanding of command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\nOne example: round_eq { sum { all_rows ; casinos } ; 217 }\nSolution is here: aggregation\nExplanation: In this example sum returns the sum of the values in all of the casinos rows. Hence, aggregation is right category.\n\nNow, solve this: eq { hop { nth_argmax { all_rows ; population ; 3 } ; ethnic group } ; saho }\nSolution:" }, { "from": "gpt", "value": "ordinal" } ]
[ { "from": "human", "value": "Q: In this task, you are given a statement spoken by a politician in natural language and the subject of the discussion for the given statement. Your task is to determine if the given subject of the discussion is correct for the given statement. The subject can be multiple words. Answer with \"True\" if it's the correct subject of discussion or return \"False\" if it's incorrect.\nStatement: Debt doubled under Bush and now its tripling under Barack Obamas watch. \n Subject: crime,criminal-justice,guns\nA:" }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nGiven a simple high-school level math question, you are required to solve it and provide the final answer. The final answer is always a single number. These questions can range from a variety of topics like simple arithmetic, solving equations, converting a quantity from one unit to another, finding remainders/GCD/LCM, finding probabilities etc. Each question has only one correct answer. This answer can be a positive or negative integer, a fraction or a decimal number. If the answer is a negative number use the hyphen (e.g. -42) symbol for the minus sign. For decimal numbers, do not add extra zeros after the decimal point. For fractional numbers, separate the numerator and denominator using a forward slash (e.g. 3/25).\n\nSuppose -2l - 48 = -6l. Let h = 17 - 30. Let g = 119 - h. What is the greatest common divisor of l and g?\nOutput:" }, { "from": "gpt", "value": "12" } ]
[ { "from": "human", "value": "In this task, you will be presented with a question in Dutch language, and you have to write the part-of-speech tag for each word and punctuation in the question. Here is the list of part-of-speech tags used in this task: Adj: Adjective, Adv: Adverb, Art: Article, Conj: Conjunction, Int: Interjection, N: Noun, V: Verb, Num: Number, Misc: Miscellaneous, Pron: Pronoun, Prep: Preposition, Punc: Punctuation.\n\nQ: Pas enkele weken geleden werd het water weggepompt , want in de winter liggen de werkzaamheden hier stil .\n\nA: Adv Pron N Adv V Art N V Punc Conj Prep Art N V Art N Adv Adj Punc\n**\nQ: ze kregen allemaal hun exemplaar .\n\nA: Pron V Pron Pron N Punc\n\nQ: ( FSt )\n\nA:" }, { "from": "gpt", "value": "Punc N Punc\n**\n" } ]
[ { "from": "human", "value": "In this task, you need to count the occurrences of the given word in the given sentence.\nQ: Sentence: 'a television that is on top of a dresser in a living room'. Count the occurrences of the word 'on' in the given sentence.\nA: " }, { "from": "gpt", "value": "1" } ]
[ { "from": "human", "value": "In this task, you will be presented with a passage and have to answer a question based on your understanding of the events inferred from the passage. Among the entities, try to find the best entity that is most likely to fill in \"_\" and classify the answers based on options.\n\nWashington (CNN) -- The United States is open to a \"more constructive relationship with the Venezuelan government\" following the death of Hugo Chavez on Tuesday and the expulsion of two military attaches. However, the action against the United States is \"not a sign of strength,\" according to a senior Obama administration official, describing the move as an internal political ploy to stir nationalistic fervor. The official said Venezuela's vice president, Nicolas Maduro, \"is not charismatic\" and is trying to sustain the Chavez legacy and win an election by advancing \"conspiracy theories.\" Chavez died of cancer, Maduro said. President Barack Obama said in a statement that the United States \"reaffirms its support for the Venezuelan people and its interest in developing a constructive relationship\" with Venezuela's government.White House interested in policies that promote democratic principlesSource says expulsion of two U.S. military aides \"not a sign of strength\"Obama administration wants elections to be \"free and fair and credible,\" source saysVenezuelan President Hugo Chavez died after a long fight with cancer \n Questions:The officials believe that Chavez adherents led by _ will want to maintain the same approach, but could be more pragmatic and less confrontational. (A) Washington (B) CNN (C) United States (D) Venezuelan (E) Hugo Chavez (F) Obama (G) Venezuela (H) Nicolas Maduro (I) Chavez (J) Barack Obama (K) White House (L) U.S." }, { "from": "gpt", "value": "(H)" } ]
[ { "from": "human", "value": "Instructions: The task is to write a full sentence or two using all of the information given. The sentence(s) will be a brief review of a restaurant. Use all of the information provided.\nInput: name[xname], eattype[coffee shop], cuisine[Indian], price[high], rating[average], location[city centre], familyFriendly[yes], near[xnear]\nOutput:" }, { "from": "gpt", "value": "xname is a coffee shop offering Indian food at a high price. It is in the city centre near xnear. It has an average customer rating and is children friendly." } ]
[ { "from": "human", "value": "Given a sentence, generate a new sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\nQ: You can inspect waxed dental paste to clean your teeth .\nA: " }, { "from": "gpt", "value": "You can grow waxed dental floss to finger your teeth ." } ]
[ { "from": "human", "value": "Given a text passage as input consisting of dialogues of negotiations between a seller and a buyer about the sale of an item, the task is to classify the text into one of the labels from the two possible outputs - 'accepted'/'rejected'. Select [accepted] if by the end of the conversation the buyer seems likely to buy the item from the seller. A sale is likely made when the buyer and seller agree upon a common price or when a deal is made between them. Select [rejected] if the buyer did not seem interested in buying the item from the seller at the end of the conversation. This happens when the buyer and seller do not agree on the price or other aspects of the item being sold by the seller.\nQ: Buyer: Hello, I seen your ad in regards to the Dining Room Table. \nSeller: Yes it is a very portable one. Are you interested and ready to pick it up?\nBuyer: I just have a couple questions. How many chairs does it comes with and what kind of wood is this table made out of? \nSeller: Its made of Mahogany wood. Very durable. The sale does not come with the chairs but you can get your own chairs. Three chairs can comfortably sit with it.\nBuyer: Oh I see, I just asked because your ad stated 'screw loose on one of the chairs' no problem. I really love the table itself and it's made of good wood. Perfect for my small apt. If I come pick it up now, will you take $45? \nSeller: Okay since you are coming to pick it up yourself and will still be fixing the loose screws yourself i shall give it to you for the $45.\nBuyer: Awesome. Please e-mail me your address and I will pick it up at your earliest convience! \nBuyer: \nSeller: \n\nA: " }, { "from": "gpt", "value": "accepted" } ]
[ { "from": "human", "value": "In this task, you need to reverse all words of a given length in the sentence. The number of letters in a word determine its length. For example, the length of the word \"apple\" is 5.\n\nQ: Sentence: 'a tennis player is holding a tennis racket with the crowd in the background'. Reverse all words of length '3' in the given sentence.\n\nA: a tennis player is holding a tennis racket with eht crowd in eht background\n**\nQ: Sentence: 'a toilet and a sink in small bathroom'. Reverse all words of length '2' in the given sentence.\n\nA: a toilet and a sink ni small bathroom\n\nQ: Sentence: 'a close up of a bus parked in a lot near another car'. Reverse all words of length '4' in the given sentence.\n\nA:" }, { "from": "gpt", "value": "a close up of a bus parked in a lot raen another car\n**\n" } ]
[ { "from": "human", "value": "We would like you to assess the QUALITY of each of the following argument (discussing Gun Control) and determine if the argument is Valid or Invalid. A valid argument is clearly interpretable and either expresses an argument, or a premise or a conclusion that can be used in an argument for the topic of gun control. An invalid argument is a phrase that cannot be interpreted as an argument or not on the topic of gun control.\n--------\nQuestion: Guns in the hands of law abiding citizens save lives, the statistics back this up from EVERY country EVER to introduce gun control.\n\nAnswer: Valid\n\n\nQuestion: The civil rights violators claim they want to keep guns out of the wrong hands, when the truth of the matter is you and I \"have the wrong hands\"\n\nAnswer: Valid\n\n\nQuestion: i think that SOCOM would love guns arms that cant be dected, it would alco be useful for undercover agents.\n\nAnswer:" }, { "from": "gpt", "value": "Valid\n\n\n" } ]
[ { "from": "human", "value": "You are given a science question (hard-level) and four answer options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer based on scientific facts, knowledge, and reasoning. Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D'. There is only one correct answer for each question.\n\nExample Input: Which is caused by the tilt of Earth on its axis? \n (A) day and night (B) stormy weather (C) high and low tide (D) season changes\nExample Output: D\n\nExample Input: If an atom has two protons and three electrons, then the atom is \n (A) positively charged. (B) negatively charged. (C) radioactive. (D) neutral.\nExample Output: B\n\nExample Input: How much time is required for a bicycle to travel a distance of 100 m at an average speed of 2 m/s? \n (A) 0.02 s (B) 50 s (C) 100 s (D) 200 s\nExample Output:" }, { "from": "gpt", "value": "B\n\n" } ]
[ { "from": "human", "value": "Definition: In this task you will be given a text passage from a trivia quiz. You should choose the category this question belongs to from these categories: History, Science, Social Science, Fine Arts, Literature. You can only choose one category, so if in doubt, please choose the closest match.\nInput: During his first meeting with Richard Wagner he refused to sit down out of respect for his musical hero. His first major musical work, Requiem in D minor, was written while teaching at St. Florian in Austria. In 1856, he moved to Linz, and while there he composed a version of Ave Maria and his Mass in D Major. He dedicated his Third Symphony to Wagner but its 1877 premier was a failure - only 25 people remained in the auditorium by the end. FTP, identify this composer of the more favorably received Fourth or \"Romantic\" Symphony, who is sometimes better known for his Zeroth Symphony.\nOutput:" }, { "from": "gpt", "value": "Fine Arts" } ]
[ { "from": "human", "value": "Definition: In this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\nInput: Sentence 1: A man is standing on his hands with lots of people around him. Sentence 2: The man is flying on a trapeze.\nOutput:" }, { "from": "gpt", "value": "A person does a handstand." } ]
[ { "from": "human", "value": "Instructions: In this task, you're given the middle and ending of a three-part story. Your job is to complete the short story by writing a probable beginning of the story. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the beginning, and use names (e.g. Jack, Barbara,...) instead of pronouns (e.g. he / she) wherever possible.\nInput: Middle: Ellen accidentally let go of the balloon. Ending: Ellen decided not to cry and enjoyed watching it till it disappeared.\nOutput:" }, { "from": "gpt", "value": "Ellen received a beautiful, helium-filled balloon for her birthday." } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given an article and an answer. Your task is to generate the question for the answer based on the given article.\nProblem:Article: Picture a wasteland of old computer monitors and TVs, stretching as far as the eye can see. Imagine towers of boxes, all of them filled with broken glass and discarded electronic devices. Technology graveyards like this can be found in communities across the country. Experts say that landfills and warehouses will overflow unless a plan for the disposal and reuse of electronics is put into place . \"We can't put electronics and glass aside and tell ourselves we'll deal with them later ,\" Lauren Roman , managing director of Transparent Planet said. Roman's group works to improve the disposal of electronic waste. She says about 660 million pounds of tech-trash is produced each year in the U.S. What's behind the tech trash pile-up ?About ten years ago ,major advances were made in computer and television technology . Manufacturers began producing devices like flat -paneled LCDs and plasma screen monitors. These new products provide a clearer image and take up less space than older models. It goes without saying that consumers choose them rather than heavy glass-based technologies. The new electronics are built with materials that are difficult to recycle. In addition, the new products have decreased the demand for recycled parts from the older monitors and screens. Older, heavier computer monitors and TVs used glass-based components called CRTs. CRTs have a high lead content and can be environmentally hazardous if not recycled properly . If crushed and put in landfills, the lead from CUTs could seep into groundwater and rivers, harming the water supply. For many years, plants and recycling programs safely processed CRTs. The recycled CRTs were reused in the construction of new monitors. Monitors being made today do not use glass tubes . \"People are returning old -style TVs with CRTs , but no new ones are being made ,\" said Linnell. This is creating an imbalance in the amount of glass being disposed of and recycled properly. Many recycling companies have shut down. Others no longer have the resources or space to process these materials. This results in stockpiling. However , experts say there are ways to safely and responsibly address the tech-trash problem. \n Answer: New technology causes trouble for recyclers.\nSolution:" }, { "from": "gpt", "value": "What is the main idea of the passage?" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a hateful post in English from online platforms. You are expected to classify the post into two classes: aggresive or non-aggresive. An aggresive post is one that expresses feelings and opinions in an abusive way and tries to dominate others. Note that the URLs in the text have been replaced with [Link].\nSee one example below:\nProblem: Post: This immigrant should be hung or shot! Period! Animal.\nSolution: Aggresive\nExplanation: This post is aggresive because it is abusive to immigrants.\n\nProblem: Post: @SenatorDurbin If you would like to report illegal aliens, please call Immigration and Customs Enforcement (ICE) at 1-866-DHS-2ICE (347-2423). They will need to know names, locations (either work place or residence) and any other specific information you \nSolution:" }, { "from": "gpt", "value": "Aggresive" } ]
[ { "from": "human", "value": "Teacher: You are given a science question (easy-level) and four answer options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer based on scientific facts, knowledge, and reasoning. Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D'. There is only one correct answer for each question.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nWhich part of a bicycle BEST moves in a circle? \n (A) Seat (B) Frame (C) Foot pedal (D) Kickstand\nSolution: C\nReason: Seat, frame and Kickstand are static parts of the bicycle, even when bicycle moves. Foot pedal moves in a circle as bicycle moves.\n\nNow, solve this instance: In the construction of a house, the words excavation, slab, and footing are associated with the \n (A) roof. (B) floor. (C) frame. (D) foundation.\nStudent:" }, { "from": "gpt", "value": "D" } ]
[ { "from": "human", "value": "In this task, you are presented with a term, a description of the term, and an expected answer ('yes' or 'no'). You should write a yes-no question about the given term such that the answer is the one provided to you (i.e., If the answer is \"No\", you should ask a question that its answer would be \"No\", and if the answer is \"Yes\", you should ask a question that its answer is \"Yes\". ). The question should have a definitive answer (as opposed to ambiguous or subjective questions, e.g., Is Batman a good movie?). Create a question such that its answer can not be found easily on a single web page (e.g., mentioned in a Wikipedia page). This can be accomplished if answering the question requires more than one fact (facts = statements that can be found on a Wikipedia page or Google). For example, answering the question 'did Aristotle use a laptop?', one needs the know about the invention of the laptop and the death of Aristotle. Avoid questions should not just compare the properties of objects (e.g., Is a door bigger than an elephant?) or those that refer to details in the given description.\nExample: Term: Cooking oil, Description: Oil consumed by humans, from vegetable or animal origin., Answer:No\nExample solution: Can all types of cooking oil be poured?\nExample explanation: This is a good question. For answering this question, you need to know different cooking oils and whether they can be poured.\n\nProblem: Term: Honey bee, Description: Eusocial flying insect of genus Apis, producing surplus honey, Answer:No\n" }, { "from": "gpt", "value": "Solution: Can a single honey bee sting multiple humans?" } ]
[ { "from": "human", "value": "Teacher:\"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). Given a prompt and two responses, identify which response is the type of \"yes, and\". Indicate your answer by 'Response 1' if the first response is correct, otherwise 'Response 2'. Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange.\nTeacher: Now, understand the problem? Solve this instance: Prompt: You see, he makes like he's in a box. Now he's walking against the wind. \n Response 1: That sounds good. Just make sure you get us a good player in return. \n Response 2: But you told me you were pickpockets. So you're also theater students?\nStudent:" }, { "from": "gpt", "value": "Response 2" } ]
[ { "from": "human", "value": "In this task, positions of two consecutive words have been swapped. You need to output the position of the swaped words. e.g. in the sentence 'Seattle has nice a weather', the word 'a' and 'nice' have been swapped. These words are at 3rd and 4th position respectively. So, the output should be (3, 4). Note that the index of first word is 1.\n\nInput: Consider Input: Assortment of fruits with pastry and displayed beverage on table\n\nOutput: (7, 8)\n\n\nInput: Consider Input: Two women ride on horses a cloudy beach\n\nOutput: (4, 5)\n\n\nInput: Consider Input: A of pile luggage sitting up against a wall of towels\n\n" }, { "from": "gpt", "value": "Output: (2, 3)\n\n\n" } ]
[ { "from": "human", "value": "In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: obscene and non-obscene. A comment is obscene if it is considered offensive to the public sense of decency, for example because it too obviously relates to sex or contains language regarded as taboo in polite usage.\n\nExample input: Comment: Damn! Another cloudy day, and it's all Obama's doing!\nExample output: Obscene\nExample explanation: This is obscenity because it hints on sexual content that is offensive to the public sense of decency.\nQ: Comment: Protectionism works well for China. There are few Western technology or media companies allowed into the mainland market, and those that do are required to hand over all IP. Poloz is a traitor to focus who gets his instructions on trade policy from his QQ.\nA:" }, { "from": "gpt", "value": "Non-obscene" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a country name and you need to return the Top Level Domain (TLD) of the given country. The TLD is the part that follows immediately after the \"dot\" symbol in a website's address. The output, TLD is represented by a \".\", followed by the domain.\nProblem:Nicaragua\nSolution:" }, { "from": "gpt", "value": ".ni" } ]
[ { "from": "human", "value": "Teacher:In this task you need to indicate the plausibility of reasoning for the pronoun coreference relations. Each of the provided inputs contains a sentence with a target pronoun and a sentence that justifies which noun phrase the pronoun refers to. Correct reasons do not need to use all the knowledge from the sentence. The resolution of the pronoun coreference relations typically involve one or multiple following knowledge types about commonsense: First: 'Property', the knowledge about property of objects (e.g., ice is cold). Second: 'Object', the knowledge about objects (e.g., cats have ears). Third: 'Eventuality', the knowledge about eventuality (e.g., 'wake up' happens before 'open eyes'). Forth: 'Spatial', the knowledge about spatial position (e.g., object at the back can be blocked). Fifth: 'Quantity', the knowledge about numbers (e.g., 2 is smaller than 10). Sixth: all other knowledge if above ones are not suitable. You should answer 'Correct' if the reasoning made sense, otherwise, you should answer 'Wrong'.\nTeacher: Now, understand the problem? Solve this instance: Sentence: I can't cut that tree down with that axe; it is too small.\n Reason: The 'it' refers to the axe because an axe being too small would prevent you from using it to cut down a tree. \n Question: Is the above reasoning correct or wrong? \nStudent:" }, { "from": "gpt", "value": "Correct" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given the title of a five-sentence story and the first four sentences. Your job is to write the last sentence of the story such that it seamlessly connects with the rest of the story.\nQ: Title: The Sofa. Sentence 1: Andrew beared the weight of the sofa. Sentence 2: His father carried the other end, and they walked into the house. Sentence 3: They were halfway up the stairs when Andrew could take no more. Sentence 4: He sat the sofa down for a brief rest.\nA:" }, { "from": "gpt", "value": "Holding all the weight now, Andrew's father fell down the stairs." } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: identity-attack and non-identity-attack. Identity attack refers to anything rude or disrespectful about someone's identity, including appearance, race, gender, and sexual orientation.\nSee one example below:\nProblem: Comment: It's bad enough we already have all these American sicko's living in this country shooting up theatre, schools, churches, malls, etc., we don't have room for crazy muslims.\nSolution: Identity-attack\nExplanation: This comment contains identity attacks on both American and Muslim.\n\nProblem: Comment: Clearly she's catering to ignoramuses such as yourself who use language like \"pot frenzies\" which has no basis in reality. You're on some kind of drug...it causes derangement and delusions. Get help.\nSolution:" }, { "from": "gpt", "value": "Non-identity-attack" } ]
[ { "from": "human", "value": "Instructions: You are given a set of queries separated by '\n', and your job is to find out the query which is not a well-formed or well-structured query in terms of grammar, punctuations, or spelling errors.\nInput: How do you become wholesaler of clothes ?\nWho gets the complaint on mail tampering ?\nWhich room has dances on meez ?\nWhat is connucticut known for ?\nOutput:" }, { "from": "gpt", "value": "Which room has dances on meez ?" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you need to count the number of nouns/verbs in the given sentence.\nExample: Sentence: 'A small toy kept on tray held by a man'. Count the number of nouns in this sentence.\nOutput: 3\nThe words 'toy', 'tray', and 'man' are nouns in this sentence. So, the answer is 3.\n\nNew input case for you: Sentence: 'A closeup of a pizza with whole tomato slices'. Count the number of nouns in this sentence.\nOutput:" }, { "from": "gpt", "value": "4" } ]
[ { "from": "human", "value": "In this task, you're given a review from Amazon and category of the product based on the review given by the user and your task is classify whether the given category match the review. Generate \"True\" if given review and its category match, otherwise generate \"False\".\nQ: Reviews: Seriously, this is ridiculous. All of the roses were either off of the steams or broken open. How am I supposed to give this to anyone and say that this is how much I care for them??! \n Category: jewelry\nA: " }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "Instructions: You will be given a piece of text either about an everyday event, or a general statement. If the event seems a plausible event to you, or the general statement makes sense matches your commonsense, output 'True', otherwise output 'False'.\nInput: To keep documents safer in case of flood, it's better to put them in a plastic box instead of a cardboard box.\nOutput:" }, { "from": "gpt", "value": "True" } ]
[ { "from": "human", "value": "Instructions: In this task, you're given a review from Amazon's food products. Your task is to generate a rating for the product on a scale of 1-5 based on the review. The rating means 1: extremely poor, 2: poor, 3: neutral or mixed, 4: good, 5: extremely good. \nInput: This was great - so soft, so tasty. Better than expected. Perfect loaf every time.\nOutput:" }, { "from": "gpt", "value": "5" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you are given an utterance, which is a part of a conversation between a user and an agent. Your job is to detect the speaker. The user usually commands the agent to schedule events, retrieve event information, and check the schedule. While the agent's response is an answer to the user's questions or follow-up questions on the user's command. Answer with \"User\" or \"Agent\".\n\nLet me know if there's anything else I can help you with.\nSolution: Agent\nWhy? In this example, the speaker wants to help, and it's part of the agent's job. So, the output should be \"Agent\".\n\nNew input: And where might I be?\nSolution:" }, { "from": "gpt", "value": "user" } ]
[ { "from": "human", "value": "In this task you need to indicate the plausibility of reasoning for the pronoun coreference relations. Each of the provided inputs contains a sentence with a target pronoun and a sentence that justifies which noun phrase the pronoun refers to. Correct reasons do not need to use all the knowledge from the sentence. The resolution of the pronoun coreference relations typically involve one or multiple following knowledge types about commonsense: First: 'Property', the knowledge about property of objects (e.g., ice is cold). Second: 'Object', the knowledge about objects (e.g., cats have ears). Third: 'Eventuality', the knowledge about eventuality (e.g., 'wake up' happens before 'open eyes'). Forth: 'Spatial', the knowledge about spatial position (e.g., object at the back can be blocked). Fifth: 'Quantity', the knowledge about numbers (e.g., 2 is smaller than 10). Sixth: all other knowledge if above ones are not suitable. You should answer 'Correct' if the reasoning made sense, otherwise, you should answer 'Wrong'.\n\nExample Input: Sentence: Emma's mother had died long ago, and her education had been managed by an excellent woman as governess.\n Reason: The 'her' refers to emma because because she is still alive. \n Question: Is the above reasoning correct or wrong? \nExample Output: Correct\n\nExample Input: Sentence: The painting in Mark's living room shows an oak tree. It is to the right of the bookcase.\n Reason: The 'It' refers to the painting because The previous sentence describes a picture, not a house or a room. \n Question: Is the above reasoning correct or wrong? \nExample Output: Wrong\n\nExample Input: Sentence: In the storm, the tree fell down and crashed through the roof of my house. Now, I have to get it removed.\n Reason: The 'it' refers to the tree because The sentence talks about the tree falling, and it's the main subject. You assume its easier to remove a tree. \n Question: Is the above reasoning correct or wrong? \nExample Output:" }, { "from": "gpt", "value": "Correct\n\n" } ]
[ { "from": "human", "value": "Teacher:In this task you will be given a list of integers. You should round each integer to the nearest tens place. That means you should round the number to the nearest multiple of 10.\nTeacher: Now, understand the problem? Solve this instance: [403, -480, 920, 261, 850, 28]\nStudent:" }, { "from": "gpt", "value": "[400, -480, 920, 260, 850, 30]" } ]
[ { "from": "human", "value": "In this task, you are given inputs i and A, where i is an integer and A is a list. You need to list all the elements of A preceding the last i elements. i will always have a value less than the length of A.\n\nLet me give you an example: 3, ['a', '34', 'f', '931', '7', '3432', '13245', '762']\nThe answer to this example can be: a, 34, f, 931, 7\nHere is why: Here, all the elements except the last 3 from the list are 'a', '34', 'f', '931', and '7'.\n\nOK. solve this:\n1, ['c', '6199', 'r']\nAnswer:" }, { "from": "gpt", "value": "c, 6199" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you're given the beginning and the ending of a three-part story. Your job is to complete the short story by writing a middle sentence that seamlessly connects the first and last sentence. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the middle sentence, and use names (e.g. Jack, Barbara,...) instead of pronouns (e.g. he / she) wherever possible.\n\nBeginning: Kate always recycles. Ending: She just recycles them whole now.\n" }, { "from": "gpt", "value": "Kate used to crush her cans but realized they get crushed at the recycling center." } ]
[ { "from": "human", "value": "In this task, you will be shown a short story with a beginning, two potential middles, and an ending. Your job is to choose the middle statement that makes the story coherent / plausible by writing \"1\" or \"2\" in the output. If both sentences are plausible, pick the one that makes most sense.\n\n[EX Q]: Beginning: Denise had a dream to become a dancer. Middle 1: Denise told her Mom she wanted to take swimming lessons. Middle 2: Denise told her Mom she wanted to take dancing lessons. Ending: Denise was amazing, she changed her Mom's mind with her dance.\n[EX A]: 2\n\n[EX Q]: Beginning: Charles' grandmother told him do not date a white girl. Middle 1: Charles knew times were the same. Middle 2: Charles knew times had changed. Ending: Charles said he was a poor student, but Christina really wanted him.\n[EX A]: 2\n\n[EX Q]: Beginning: I had a dog. Middle 1: Then I saw that my neighbor had friendly mouse as well. Middle 2: Then I saw that my neighbor had friendly dog as well. Ending: Then I invited the neighbor over to have a dog play-date.\n[EX A]:" }, { "from": "gpt", "value": "2\n\n" } ]
[ { "from": "human", "value": "TASK DEFINITION: Evaluate the similarity between them and classify them into classes from 0-5 as follows:\n0 : The two sentences are completely dissimilar.\n1 : The two sentences are not equivalent, but are on the same topic.\n2 : The two sentences are not equivalent, but share some details.\n3 : The two sentences are roughly equivalent, but some important information differs/missing.\n4 : The two sentences are mostly equivalent, but some unimportant details differ.\n5 : The two sentences are completely equivalent, as they mean the same thing.\nPROBLEM: Sentence 1: That exploit works on unpatched Windows 2000 machines with Service Pack 3 and 4. Sentence 2: Both Counterpane and iDefense contend that the exploit works effectively against Windows 2000 systems running Service Pack 3 and 4.\n\nSOLUTION: 3\n\nPROBLEM: Sentence 1: Holly Holy We are all vessels filled with many wonders. Sentence 2: Say What You Will We are all vessels filled with many wonders.\n\nSOLUTION: 4\n\nPROBLEM: Sentence 1: A young boy plays in a red ball pit. Sentence 2: A laughing boy lies on a pit of blue balls.\n\nSOLUTION:" }, { "from": "gpt", "value": "3\n\n" } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task, you're given a short story of five sentences written in natural language. However, the order of the given story is not correct. Your job is to return the correct order for the given five sentences to create a coherent short story with the new order that has the correct flow. Generate your answer using the number of sentences in the correct order, such as '23415'.\nPROBLEM: Sentence1: He whined to his parents that it just wasn't Christmas without it. Sentence2: Kip was disappointed there wasn't any snow. Sentence3: They told him to go to bed. Sentence4: Kip dreamed of snowflakes. Sentence5: Kip stomped his way to his room and eventually fell asleep.\n\nSOLUTION: 21354\n\nPROBLEM: Sentence1: Nelly the cashier was having a bad day at the store. Sentence2: The fresh air was exactly what Nelly needed to clear her head. Sentence3: As soon as it was time for her break she dashed outside. Sentence4: She kept making small mistakes and people were getting mad. Sentence5: Even her last customer was mad and it wasn't even her fault.\n\nSOLUTION: 15423\n\nPROBLEM: Sentence1: One day he decided to go on a hike. Sentence2: Dave backed away slowly. Sentence3: To his right on the ground was a rattle snake! Sentence4: As he walking on the trail, he heard a hissing sound. Sentence5: Dave loved the outdoors.\n\nSOLUTION:" }, { "from": "gpt", "value": "25431\n\n" } ]
[ { "from": "human", "value": "In this task, you are given inputs i and A, where i is an integer and A is a list. You need to output the first i elements of A, starting with the 1st element in A. i will always have a value less than the length of A\n\n5, ['8499', 'z', 'B', '5059', 'J', '405', 't', 'O', 'x', 'l', 'A', '2233', 'k', 'u']\n8499, z, B, 5059, J\n\n1, ['C', 'l', '7891', '6015']\nC\n\n3, ['4183', 'Z', '3001', 'q', '8791', '6203', 'W', '7761', '8909', '1483', 'E', '6699', 'K']\n" }, { "from": "gpt", "value": "4183, Z, 3001\n\n" } ]
[ { "from": "human", "value": "Given two entities as input, classify as \"yes\" if second entity is the part of the first entity. Otherwise classify them as \"no\". These are entities of meronym In linguistics, meronymy is a semantic relation between a meronym denoting a part and a holonym denoting a whole. In simpler terms, a meronym (i.e., second entity) is in a part-of relationship with its holonym (i.e., first entity).\nQ: Entity 1: stiletto \n Entity 2: tannin\nA: " }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "Q: Given a factoid/trivia type question, generate the topic of the question. The topic is the entity the question talks about.\nFor which film in 1950, starring Bette Davis and Anne Baxter, did British actor George Sanders win the Oscar as Best Supporting Actor?\nA:" }, { "from": "gpt", "value": "george sanders" } ]
[ { "from": "human", "value": "In this task, you are given an abstract of article. Your task is to generate title for this article. Preferred titles are under thirty words.\n\nExample input: Alterations of the architecture of cerebral white matter in the developing human brain can affect cortical development and result in functional disabilities. A line scan diffusion-weighted magnetic resonance imaging (MRI) sequence with diffusion tensor analysis was applied to measure the apparent diffusion coefficient, to calculate relative anisotropy, and to delineate three-dimensional fiber architecture in cerebral white matter in preterm (n = 17) and full-term infants (n = 7). To assess effects of prematurity on cerebral white matter development, early gestation preterm infants (n = 10) were studied a second time at term. In the central white matter the mean apparent diffusion coefficient at 28 wk was high, 1.8 microm2/ms, and decreased toward term to 1.2 microm2/ms. In the posterior limb of the internal capsule, the mean apparent diffusion coefficients at both times were similar (1.2 versus 1.1 microm2/ms). Relative anisotropy was higher the closer birth was to term with greater absolute values in the internal capsule than in the central white matter. Preterm infants at term showed higher mean diffusion coefficients in the central white matter (1.4 +/- 0.24 versus 1.15 +/- 0.09 microm2/ms, p = 0.016) and lower relative anisotropy in both areas compared with full-term infants (white matter, 10.9 +/- 0.6 versus 22.9 +/- 3.0%, p = 0.001; internal capsule, 24.0 +/- 4.44 versus 33.1 +/- 0.6% p = 0.006). Nonmyelinated fibers in the corpus callosum were visible by diffusion tensor MRI as early as 28 wk; full-term and preterm infants at term showed marked differences in white matter fiber organization. The data indicate that quantitative assessment of water diffusion by diffusion tensor MRI provides insight into microstructural development in cerebral white matter in living infants.\nExample output: Microstructural development of human newborn cerebral white matter assessed in vivo by diffusion tensor magnetic resonance imaging.\nExample explanation: This title is appropriate for the given abstract because the focus of this abstract is cerebral white matter assesment.\nQ: Biological agents are widely used in rheumatology, dermatology and inflammatory bowel disease. Evidence about their efficacy and safety has been strengthened for all those therapeutic indications over the last decade. Biosimilar agents are monoclonal antibodies similar to previously approved biologics. In the European Union, they have been approved for all the indications in the management of immune-mediated inflammatory diseases (IMIDs), although data only in rheumatoid arthritis and ankylosing spondylitis are currently available. Direct evidence on efficacy, safety, and immunogenicity of biosimilars is mandatory in psoriasis, psoriatic arthritis, and inflammatory bowel disease, as well as in children. Based on the current evidence in the literature, we present the joint official position of the Italian Societies of Rheumatology, Dermatology and Inflammatory Bowel Disease on the use of biosimilars in IMIDs.\nA:" }, { "from": "gpt", "value": "The use of biosimilars in immune-mediated disease: A joint Italian Society of Rheumatology (SIR), Italian Society of Dermatology (SIDeMaST), and Italian Group of Inflammatory Bowel Disease (IG-IBD) position paper." } ]
[ { "from": "human", "value": "In this task, you are given a short story consisting of exactly 5 sentences where the second sentence is missing. You are given a candidate for the second sentence and you need to identify if the given sentence connects the first sentence with the rest of the story. Indicate your answer by \"Yes\" if it connects, otherwise \"No\". Do not generate anything else apart from \"Yes\" or \"No\". The given sentence is incorrect if it changes the subsequent storyline, so that at least one of the three subsequent sentences form a consistent story.\n\nExample input: Sentence 1: The cashier was counting the dollar bills at her desk. \n Sentence 3: Everyone panicked and started to scream. \n Sentence 4: The men threatened the people to remain quiet. \n Sentence 5: The cashier handed them the cash so they would go away. \n Given Sentence 2: Two men rushed into the store and held their guns up.\nExample output: Yes\nExample explanation: People panic when somebody holds their guns up. Sentence 2 correctly connects Sentence 1 with rest of the story. So, the answer is 'Yes'.\nQ: Sentence 1: Denise wanted to learn how to apply her own makeup. \n Sentence 3: After locating a tutorial, Denise tried to use her new found skills \n Sentence 4: However, Denise realized she would need more makeup lessons \n Sentence 5: Denise decided to subscribe to the channel so she could learn more \n Given Sentence 2: He decides to start jumping rope.\nA:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "In this task, you are given two strings A,B. Find the longer of the two lists, convert it to lowercase, and return all the unique alphabets used in it. The two input strings are never equal.\n\nLet me give you an example: JkbloNUq, nYblowj\nThe answer to this example can be: b, j, k, l, n, o, q, u\nHere is why: Here, 'JkbloNUq' is the longer string among the two input strings. Lowercasing it and finding all unique alphabets gives 'b, j, k, l, n, o, q, u'.\n\nOK. solve this:\nmpofIebYBjkRVwUWWIiZXjtTxVYgcf, EYptERVwUWWIiZXjtTvVqDdZ\nAnswer:" }, { "from": "gpt", "value": "b, c, e, f, g, i, j, k, m, o, p, r, t, u, v, w, x, y, z" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given an abstract of article. Your task is to generate title for this article. Preferred titles are under thirty words.\nQ: Multiple health priorities, limited human resources and logistical capacities, as well as expensive vaccines with limited funds available increase the need for evidence-based decision making in immunization programs. The aim of the Supporting Independent Immunization and Vaccine Advisory Committees (SIVAC) Initiative is to support countries in the establishment or strengthening of National Immunization Technical Advisory Groups (NITAGs) that provide recommendations on immunization policies and programs (e.g., vaccination schedules, improvements of routine immunization coverage, new vaccine introduction, etc.). SIVAC, a program funded by the Bill & Melinda Gates Foundation, is based on a country-driven, step-by-step process that ensures its support is tailored to country needs and emphasizes NITAG sustainability. SIVAC supports countries by reinforcing the capacities of the NITAG scientific and technical secretariat and by providing specific support activities established in consultation with the country and other international partners. Additionally, SIVAC and partners have built an electronic platform, the NITAG Resource Center, that provides information, tools, and briefings to NITAGs and the immunization community.\nA:" }, { "from": "gpt", "value": "The Supporting Independent Immunization and Vaccine Advisory Committees (SIVAC) initiative: a country-driven, multi-partner program to support evidence-based decision making." } ]
[ { "from": "human", "value": "Teacher: The task is reading a paragraph containing numbers as digits. The digits can be used to represent Quantity, Dates and Time, Addresses or Positions. Convert the digits into their text equivalents. If a number has a prefix, postfix or punctuation preserve it in the text equivalent. 100000 is translated as hundred thousand, Roman numerals are also translated. If multiple numbers are present convert all instances.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nThe boy placed 13th in class.\nSolution: The boy placed thirteenth in class.\nReason: Here the number represents the position of the person, and hence we use the 'th' form of the number.\n\nNow, solve this instance: \"A. Hidell, P.O. Box 2915, Dallas, Texas,\" on March 20, 1963.\nStudent:" }, { "from": "gpt", "value": "\"A. Hidell, P.O. Box two nine one five, Dallas, Texas,\" on March twenty, nineteen sixty three." } ]
[ { "from": "human", "value": "You are given a background paragraph that describes one or more causal or qualitative relationships such as a relationship in economics or a scientific law and a story that makes use of the concepts or the relationship described in the provided paragraph. You need to come up with a question about the story that requires an understanding of the relationship described in the background paragraph. The generated question should not be answerable without both the background and story. Write a question about the story that requires a relationship in the background paragraph to answer. Check whether your question requires both the background paragraph and the story to answer. If your question can be answered by only one of these, try to rewrite your question so that it requires both. Note that \"flipping\" a word in the question can give rise to a new question where the answer will be different from the original question. Often, \"flipping\" a word gives rise to flipping the direction of the relationship, for example, from \"increase\" to \"decrease.\"\n\nBackground Paragraph: One result of air pollution is acid rain. Acid rain is precipitation with a low (acidic) pH. This rain can be very destructive to wildlife. When acid rain falls in forests, freshwater habitats, or soils, it can kill insects and aquatic life. It causes this damage because of its very low pH. Sulfur oxides and nitrogen oxides in the air both cause acid rain to form ( Figure below ). Sulfur oxides are chemicals that are released from coal-fired power plants. Nitrogen oxides are released from motor vehicle exhaust. \nStory: Hydrologists studied two samples of rain water. Jim studied an acid rain sample from a nearby city, and Dan studied a sample of water from another town." }, { "from": "gpt", "value": "Which hydrologist didn't learn that acid rain falls in forests?" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n\| Attribute \| triggerword \| contrastive triggerword \| \n\| age \| old \| new \| \n\| altitude \| low \| high \|\n\| area \| small \| vast \| \n\| brightness \| dark \| light \| \n\| clarity \| obscure \| clear \| \n\| cleanness \| dirty \| clean \| \n\| complexity \| simple \| complex \| \n\| cost \| cheap \| expensive \|\n\| density \| sparse \| dense \|\n\| depth \| shallow \| deep \|\n\| distance \| near \| far \| \n\| electric conductivity \| low \| high \|\n\| flexibility \| rigid \| flexible \|\n\| granularity \| fine \| coarse \| \n\| hardness \| soft \| hard \| \n\| length \| short \| long \| \n\| magnitude \| small \| large \| \n\| mass \| small \| large \| \n\| odor \| weak \| strong \| \n\| pressure \| low \| high \| \n\| resistance \| low \| high \| \n\| shape \| round \| sharp \|\n\| shape \| flat \| spiky \|\n\| size \| small \| large \| \n\| sound \| quiet \| loud \| \n\| sound pitch \| low \| high \| \n\| speed \| slow \| fast \| \n\| stability \| unstable \| stable \| \n\| strength \| weak \| strong \| \n\| temperature \| low \| high \| \n\| texture \| smooth \| rough \| \n\| thermal conductivity \| low \| high \|\n\| thickness \| thin \| thick \| \n\| volume \| small \| large \|\n\| weight \| light \| heavy \| \n\| width \| narrow \| wide \| \n\| location \| in \| out \|\n\| location \| up \| down \|\n\| location \| above \| below \|\n\| location \| on \| off \|\n\| location \| to \| from \|\n\nProblem:Context Word: island. \nQuestion: On the island the weather was frequently unpredictable. It was supposed to rain this weekend and the _ would get very wet. \nAnswer: island.\nSolution:" }, { "from": "gpt", "value": "On the island the weather was frequently unpredictable. It was supposed to rain this weekend and the _ would be very heavy." } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given two facts, and a multiple-choice question. Based on the given facts, answer the question with index of the correct option (e.g, \"A\").\nProblem:Fact1: Fingernails prevent injury by forming protective plates over the ends of the fingers., Fact2: Fingernails are also made of keratin., Question: What forming over the ends of fingers prevents injury? (A) tissue (B) keratin (C) hairs (D) needles (E) shells (F) bone (G) Cartilage (H) tiny hairs\nSolution:" }, { "from": "gpt", "value": "B" } ]
[ { "from": "human", "value": "In this task, you are given a Reddit post as a text. Your task is to generate a title for this text. The title should start with \"TIFU by\", followed by a situation that caused humor. The title should contain 7-12 words, ideally.\n\nEx Input:\nText: this shit happened saturday night at roughly 9:30 pm. \n\nmy friends and i go to the ihop to indulge in the pancakes and breakfast. everyone is talking about life and merriment as we eagerly waited for our food to arrive. everyone got pancakes. i got chicken and waffles. \n\n\"would you like honey mustard?\", said the waitress to me.\n\n\"uhhh, sure.\", i said.\n\nbig mistake. the next thirty minutes were a mixture a foodgasmic taste experiences as well as grave regret. the syrup, soda and honey mustard were starting to get to me. everyone was done eating and already paying at the front counter.\n\n\"hold on guys, i gotta go to the bathroom.\", i said while clenching my stomach and sphincter in pain.\n\n\"k. try not shit all over the floor like you did at summer camp.\", said friend 4.\n\n\"that wasn\"t even me!\"\n\ni proceeded to the bathroom which to my surprise, had no one inside. what was an alleged code brown, was soon to be a code green. or more like code yellowish-brown. coughing and gagging my brains out and yet nothing came out. feeling like i had beaten the ihop, i left the stall and went to pay my bill.\n\nwe get into my car (we all carpooled there) but something was wrong. horribly, horribly wrong.\n\nit was coming.\n\nrising stomach gurgle\n\n\"oh fuck\"\n\ni get out of the drivers seat and run to a light post\n\nvomits on said light post\"\n\n\"aww, what the fuck, man!?\", said friend 1.\n\n\"i'm sorry, it was probably too much honey mustard.\", i replied.\n\n\"do you want me to drive?\", said friend 2 (the non-asshole with substantial medical knowledge).\n\n\"yeah, i'm not gonna make it on this one...\", i moaned.\n\nwe get about maybe fiddy yards away from the ihop when i start to vomit again. hard. \n\nblllllleeeeeuuugggghhhhhhh\n\nthe car stopped next to us is a four remembered middle eastern looking family. all of them filled with the faces of disgust. fucking priceless.\n\ncollective duuuuudddesss from friends in my car\n\n\"do i need to pull over?\", said friend 2.\n\n\"no, no, i'm fine\", i said obviously not fine.\n\nthank god we were at a stoplight.\n\nthe light turns green and we start moving again.\n\n\"i'm going to try to drive slowly, okay?\", said friend 2.\n\n\"alright, i trust you.\", i reluctantly cried.\n\nmaybe not even twenty seconds after the stoplight, i start vomiting again. hard.\n\nblllllleeeeeuuugggghhhhhhh\n\nnone of it hits the ground. just the side of my car.\n\nfast forward to a few more stoplights of this happening\n\nwe stop at yet another stoplight with me still feeling gurgley. this time, the car next to us is filled with african american individuals that may have been juniors in high school or freshman in college. i am very bad at guessing ages.\n\nloud as fuck gurgle\n\n\"oh god.\"\n\nstick head out of window and projectile vomit all over the car next to us*\n\nyep.\n\nyou heard right folks.\n\nall over their 4-door who-gives-a-fuck standard.\n\neveryone in the vomited car, aren't disgusted, just surprised. the mix of facial expressions ranged from \"eeewwww\" to \"da fuuuuhhhh?\"\n\ni smiled and promptly apologized for the vomit to which the driver rolled down his window and replied \"ayo, you need to turn down, bruh!\".\n\ntfw i believe him.\n\nmore vomiting out of the window onto the side of my car later ensued after that stoplight and continued until we arrived at friend 3's house. \n\nwe got out of my car and saw the damage. \n\nit.\n\nwas.\n\neverywhere.\n\ndried up from wind resistance vomit caked in all across the right side if my car.\n\none of the poor bastards on that side came out that way and got a nice handful of chicken and waffles from the door handle.\n\nafter hardy laughter, we played basketball, watched some kind of gay (i mean actually gay) movie about singing and dreams with friend 3's sister, and left to go home.\n\nall of the ride home, i had wondered what had made me sick. then it hit me. the honey mustard. i basically drank the whole bowl that the waitress brought me. i eventually arrived home at around 1 am. the perfect time for masturbation.\n\ndon't fuck around with honey mustard, kids. it may taste good but it can and will, fuck you up if drunken without moderation.\n\n\n\n \n\n\nedit: for those who don\"t believe me http://imgur.com/b4jfb5g\n\nEx Output:\nTIFU by eating IHOP\n\n\nEx Input:\nText: https://www.youtube.com/watch?v=wvjagrubf4w this is a chladni plate.\n\nas with most tifu this happened a year ago while i was working in a retail car installation bay. the other technician and i were starting to get bored and begun watching youtube videos. he's going to school to be an engineer and heard about the chladni plate and showed me a video. we both were convinced we could build one of our own, so we obtained an old car speaker, fashioned a metal rod from the cone, and attached a square plate to the rod. we have our own external car audio system for personal use while we work and we re-wired the plate to that. we used sand that was lying around for when it ices over and tried playing a few songs through the plate to see if we got a response, it worked but didn't move the sand like the video. so i downloaded a tone app on my phone, plugged it in at a random frequency and what came through was the loudest, highest pitched sound i have ever heard. the whole world stood still as we were paralyzed by the sound, and we watched as the sand on the plate morphed into a tessellation of brilliant circles, and then quickly burst into flames, followed by a deep electronic thump and then.. darkness. did we die? no, the store's electricity went out and we had three managers knocking on the door to the bay wondering what the hell happened. we set off a chain of events that made the rest of the business day basically worthless as security systems had to be rebooted and all the registers needed to be activated again. \n\nneedless to say they felt the need to move one of us out of the install bay, and i found myself working customer service.\n\nEx Output:\nTIFU by creating a Chladni Plate\n\n\nEx Input:\nText: of course this fuck up happened not today, but three months ago. \n\nso i was over at my friends house, lets call him jacob. he, his roommates and i were all hanging having a few drinks. harmless fun for a while until we got drunk and started to get bored (famous last words).\n\nwell i should also say that at the time we were all active duty military, wont say what branch because it may give away his identity.\n\nanyway, what better way is there for a few troops to quench boredom other than proving that one guy was stronger than the other? so we begin punching each other.\n\nit wasn't fighting mind you, just hit-for-hit deliberate punches to determine whose was harder.\n\nso we're a few rounds in and a bit sore when its my turn again. \ni pull back my fist, ready to go full strength on his arm. i throw the punch and crack!\n\nit would seem that after about half a bottle of vodka, my aim may have been a bit impaired. instead of hitting his arm square-on, i sort of glanced off the side and my wrist bent with it. a loud crack and an explosion of pain told me that perhaps, i may have hurt myself. so i wrapped it with an ace bandage, applied ice and resolved to go to the base clinic the next day if it didnt feel better in the morning.\n\na few pretty x-rays later, i found out i broke my wrist. more particularly my scaphoid. a relatively seriously break since one of the blood supplies to my hand runs over it. the dr./capt. told me that it would require surgery. \n\nso now i have a new piece of hardware in my wrist and a rather unsightly scar. awesome. fapping is never going to be the same.\n\n\n\n \nplayed a punching game to prove who threw harder whilst i was drunk, ended up breaking my wrist and requiring surgery and a screw. i either won that game or lost...you be the judge.\n\nEx Output:\n" }, { "from": "gpt", "value": "TIFU by throwing drunkin punches\n\n\n" } ]
[ { "from": "human", "value": "You are given a paragraph (Passage), a question (Question) and two answer options (Option1 and Option2). Your task is to find the correct answer (and return the string of the correct option, not option1/2) for the given question from the given options and based on the given passage. Answer of the question can be found directly from the passage.\n\nPassage: The bell rang , But I was not especially excited to get out of school today . For tomorrow were exams . And I had to write an exam for the students to complete tomorrow . The exam was going to be on medical terminology . Not too bad I say . I went home , took a shower and changed clothes . Let 's start off with some easy ones . First let me write the directions . Please complete the prefix with the medical term that it signifies . Well , after about an hour . I finished early . I went to the store and bought a light meal and a bottle of merlot . Question: What did the person want to get? Option1: the directions Option2: light meal and bottle of Merlot" }, { "from": "gpt", "value": "light meal and bottle of Merlot" } ]
[ { "from": "human", "value": "The input is a sentence. The sentence includes an emotion. The goal of the task is to classify the emotion in the sentence to one of the classes: 'fear', 'joy', 'anger', 'sadness'. The emotion mainly depends on the adverb within the sentence.\n\nThis girl feels devastated.\nsadness\n\nJerome feels discouraged.\nfear\n\nEbony feels devastated.\n" }, { "from": "gpt", "value": "sadness\n\n" } ]
[ { "from": "human", "value": "Teacher: In this task you will be given a list of integers. You should only return an integer if the first digit is the same as the last digit in the number. If an integer has a single digit, then it should be returned. If there are no integers that start and end with the same digit then an empty list (\"[]\") should be returned.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\n[77, 999, 855, 10, 56, 121, 801]\nSolution: [77, 999, 121]\nReason: The integers 77, 999, and 121 are the only integers in the input list that start and end with the same digit.\n\nNow, solve this instance: [643, 236, -534, 56, 812, -933, 6, 873, -491, 831, 112, -487, 18, -176, -385, -507, -502, 702, -920, 511, 112, 760, -440, 479]\nStudent:" }, { "from": "gpt", "value": "[6]" } ]
[ { "from": "human", "value": "In this task, you are given a natural language interpretation of commands (consist of logical operations) to select relevant rows from the given table. Your job is to generate command (in terms of logical operations) from given natural language interpretation. Define body (contains a collection of statements that define what the this logical operator does) of each logical operator between '{}' parenthesis. Here are the definitions of logical operators that you can use while generating command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\nOne example: select the row whose attendance record of all rows is 3rd maximum. the competition record of this row is danish superliga 2005-06.\nSolution is here: eq { hop { nth_argmax { all_rows ; attendance ; 3 } ; competition } ; danish superliga 2005 - 06 }\nExplanation: Here, the generated command using logical operators correctly selects third maximum from given table rows which is mentioned in natural language interpretation.\n\nNow, solve this: select the row whose first elected record of all rows is 3rd minimum . the incumbent record of this row is william huston natcher .\nSolution:" }, { "from": "gpt", "value": "eq { hop { nth_argmin { all_rows ; first elected ; 3 } ; incumbent } ; william huston natcher }" } ]
[ { "from": "human", "value": "Q: In this task, you are given a summary for US Congressional and California state bill, your task is to generate a Title for this bill. The preferred titles are under forty words and mention the purpose of the bill.\nAgricultural Mediation Improvement Act of 1994 - Amends the Agricultural Credit Act of 1987 to expand the types of agricultural issues covered by State mediation programs. \nExtends the authorization of appropriations for such programs.\nA:" }, { "from": "gpt", "value": "Agricultural Mediation Improvement Act of 1994" } ]
[ { "from": "human", "value": "In this task you are given a sentence pair from wikipedia that have high lexical overlap. If the sentences have the same meaning and are just paraphrases of each other label them as \"Paraphrase\" , if not label them as \"Not paraphrase\". The two sentences are seperated by a new line.\n--------\nQuestion: The film music department had a rare combination , sitar maestro Shailendra , with lyricist Pandit Ravi Shankar .\nThe film music department had a rare combination , Sitar Maestro Pandit Ravi Shankar , with the lyrics Shailendra .\n\nAnswer: Not paraphrase\n\n\nQuestion: Having won the NRL Premiership in 2001 , the Knights traveled to England to play the World Club Challenge against the Super League Champions , the Bradford Bulls , in 2002 .\nHaving won the 2001 Super League , the Knights traveled to England to play the 2002 World Club Challenge against NRL Premiership champions , the Bradford Bulls .\n\nAnswer: Not paraphrase\n\n\nQuestion: It has been awarded to civilian medical staff , Qantas crews , military personnel and embassy personnel .\nIt has been awarded to civilian medical personnel , Qantas crews , military personnel , and Embassy staff .\n\nAnswer:" }, { "from": "gpt", "value": "Paraphrase\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a context, a question, and three options. Your task is to find the correct answer to the question using the given context and options. Also, you may need to use commonsense reasoning about social situations to answer the questions. Classify your answers into 'A', 'B', and 'C'.\nSee one example below:\nProblem: Context: Tracy didn't go home that evening and resisted Riley's attacks. \n Question: What does Tracy need to do before this? \n Options: (A) make a new plan (B) Go home and see Riley (C) Find somewhere to go\nSolution: C\nExplanation: Tracy found somewhere to go and didn't come home because she wanted to resist Riley's attacks. So, C is the correct answer.\n\nProblem: Context: Kendall wanted to help Casey get hired for her new job. \n Question: Why did Kendall do this? \n Options: (A) make Casey get hired (B) hurt Casey's prospects (C) stop Casey from getting hired\nSolution:" }, { "from": "gpt", "value": "A" } ]
[ { "from": "human", "value": "Teacher:In this task, you are given two strings A,B. You must perform the following operations to generate the required output list: (i) Find the longest common substring in the strings A and B, (ii) Convert this substring to all lowercase and sort it alphabetically, (iii) Replace the substring at its respective positions in the two lists with the updated substring.\nTeacher: Now, understand the problem? Solve this instance: fxEabrugtulTWeouTMdaAaVzzaKTDaSPEfsiV, pArDdUPyPqJkmCeouTMdaAaVzzaKTWadFSXdBSQQ\nStudent:" }, { "from": "gpt", "value": "fxEabrugtulTWaaaadekmottuvzzDaSPEfsiV, pArDdUPyPqJkmCaaaadekmottuvzzWadFSXdBSQQ" } ]
[ { "from": "human", "value": "In this task you are given a sentence. You must judge whether subject of the main clause is singular or plural. Label the instances as \"Singular\" or \"Plural\" based on your judgment.\n\nLet me give you an example: Coming from a xenophobic race that possesses the unique ability to pass among other species and chooses not to, the bounty hunter is a walking contradiction.\nThe answer to this example can be: Singular\nHere is why: \"the bounty hunter\" is the subject of the sentence which is singular.\n\nOK. solve this:\nThe archer released his arrow.\nAnswer:" }, { "from": "gpt", "value": "Singular" } ]
[ { "from": "human", "value": "Instructions: Based on the given context, craft a common-sense question, especially those that are LONG, INTERESTING, and COMPLEX. The goal is to write questions that are easy for humans and hard for AI machines! To create such questions, here are some suggestions: A. What may (or may not) be the plausible reason for an event? B. What may (or may not) happen before (or after, or during) an event? C. What may (or may not) be a plausible fact about someone (or something)? D. What may (or may not) happen if an event happens (or did not happen)? You can also create other types of questions. DO NOT make your question answerable without looking at the context, or question of which the correct answer can be directly extracted from the context. DO NOT ask a question that requires very specialized knowledge that is not common sense. DO NOT ask too simple or too short questions. Your question must be related to the context and answerable with common sense. Try to add more variations and complexity to the questions.\nInput: Context: Clearing my inbox ( pretty much , only 30 or so left out of hundreds of email ) was surprising . I 'd forgotten that some people had ever emailed me , realised I 'd left far too many emails unanswered , and that horrible things such as ' social networking sites ' were clogging it up . This is the first time I ' ve ever almost - cleared my inbox ; so far I ' ve somehow managed not to . I also happened upon an email from someone whose emails I thought I 'd totally got rid of .\nOutput:" }, { "from": "gpt", "value": "What may happen after I clean up my inbox ?" } ]
[ { "from": "human", "value": "Teacher: You are provided with an \"Event\", \"Intent\" and \"XEmotion\" (PersonX's reactions for the given \"Event\"). Indicate PersonY's reaction (person feels) at the end of this event. Provide one reaction for PersonY. If there's nothing that can be implied, respond as None\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nEvent: PersonX not does PersonY any favours. Intent: 1) to inflict pain. XEmotion: 1) has no feelings\nSolution: horrible\nReason: Based on the given input PersonX is trying to inflict pain on PersonY as it has no feelings. PersonY being a third person might show an emotion of feeling horrible which is provided in the output\n\nNow, solve this instance: Event:PersonX gives PersonY the message. Intent: 1) to be forgiven. XEmotion: 1) forgiven\nStudent:" }, { "from": "gpt", "value": "really nothing at all" } ]
[ { "from": "human", "value": "In this task, you're given the beginning and the middle of a three-part story. Your job is to complete the short story by writing a probable ending. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the ending, and use names instead of pronouns (e.g. he / she) wherever possible.\n\nInput: Consider Input: Beginning: Ricard thought space was cool. Middle: Ricard saw a packaged spacesuit.\n\nOutput: On that morning he unwrapped one.\n\n\nInput: Consider Input: Beginning: Paul tried to look at my project. Middle: The teacher saw paul cheating off me.\n\nOutput: I ended up getting an F for my work.\n\n\nInput: Consider Input: Beginning: My body started to feel weak throughout the week. Middle: I decided to perform in the concert anyhow.\n\n" }, { "from": "gpt", "value": "Output: The audience cheered for me.\n\n\n" } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the letters E, C, and N respectively.\nPROBLEM: Sentence 1: A Mac laptop, open, on top of a blue chair in a room with a group of people sitting in a semicircle around it. Sentence 2: A group of hikers rest around a campfire.\n\nSOLUTION: C\n\nPROBLEM: Sentence 1: The market man prepares the meat for sale. Sentence 2: A man cleaning fish.\n\nSOLUTION: N\n\nPROBLEM: Sentence 1: On a natural stone bridge high over an evergreen valley, a man jumps into the air. Sentence 2: The cat is jumping.\n\nSOLUTION:" }, { "from": "gpt", "value": "C\n\n" } ]
[ { "from": "human", "value": "Q: Generate an appropriate title for the given text. The generated title must be short and include the main topic of the text. The preferred titles are under fifteen words.\nSince late April, soldiers have conducted about 100,000 Covid-19 tests in communities around Scotland The highest number of people tested at an army run Mobile Testing Unit (MTU) on one day was 773. Soldiers and ambulance service staff worked together last week in preparation for Monday's handover. The Army said the soldiers' work had been instrumental in maintaining the safety of communities across Scotland, as part of the integrated response to coronavirus. Scottish Secretary Alister Jack said the MTUs had helped reach some of the country's most remote and rural areas. He said: \"Since the outbreak of the pandemic the men and women of the UK's Armed Forces have worked tirelessly to support our response to tackle the virus.\" He added: \"I would like to thank all the troops who have worked so hard to run the units for the past few months. We are all very grateful for their work. \"The UK government is boosting Covid testing capacity in Scotland. This includes providing six drive through sites, the Lighthouse mega-lab in Glasgow and the opening of the walk-in testing site in St Andrews. This is on top of testing capacity provided by the Scottish government\". The Army said that at peak times, 18 MTUs were deployed. They were each crewed by 12 staff and all soldiers deployed to the MTUs were fully trained infantry, engineers or Royal Armoured Corps personnel. Some of the MTU staff have been Army reservists, mobilised at the start of the pandemic restrictions. They will now be going back to their civilian jobs and their regular Army colleagues will return to their units and their operational military roles.\nA:" }, { "from": "gpt", "value": "Coronavirus: Ambulance service takes over mobile testing" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given two strings A, B. Find the longest common substring in the strings A and B.\nProblem:wJFKlO, JRFKev\nSolution:" }, { "from": "gpt", "value": "FK" } ]
[ { "from": "human", "value": "You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. Your task is to label each of the continuous conversations done by one speaker with the emotion detected in that particular part. Your labels can be one among the following: 'No emotion', 'surprise', 'happiness', 'sadness', 'anger', 'disgust'.\nQ: Person1: Are you studying here ? \n Person2: Yes , I am studying in Eastern Asian language department . \n Person1: What are you major in ? \n Person2: I major in Japanese . \n Person1: What do you think of the literature course . \n Person2: Its very helpful . The course has let me into a world of literature . I read so many great literatures . \nA: " }, { "from": "gpt", "value": "No emotion,No emotion,No emotion,No emotion,No emotion,happiness" } ]
[ { "from": "human", "value": "You are given a review of Amazon's food products. Your task is to divide them into two classes: negative or positive, depending on the content of the review.\n\nLet me give you an example: I have bought several of the Vitality canned dog food products and have found them all to be of good quality. The product looks more like a stew than a processed meat and it smells better. My Labrador is finicky and she appreciates this product better than most.\nThe answer to this example can be: Positive\nHere is why: It's a positive review because the owner of the dog is satisfied with the product and mentioned that their dog appreciates the product.\n\nOK. solve this:\nThey refuse to ship this fine tea to Canada. I have to go to the Middle East to find it and bring it back.\nAnswer:" }, { "from": "gpt", "value": "Negative" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nYou will be given a sentence. Check whether the sentence is grammatically correct and is meaningful. If the sentence is grammatically correct, then answer with '1', otherwise answer with '0'.\n\nKelly buttered the bread with butter.\nOutput:" }, { "from": "gpt", "value": "0" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. You are given a science question (easy-level) and four answer options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer based on scientific facts, knowledge, and reasoning. Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D'. There is only one correct answer for each question.\n\nWhich of the following is a first-level consumer? \n (A) wolf (B) hawk (C) carrot (D) rabbit\n" }, { "from": "gpt", "value": "D" } ]
[ { "from": "human", "value": "In this task, you are given a review of a movie and a boolean question whether this review has positive sentiment or negative sentiment. Your task is to generate answer \"yes\" when the tweet has that particular sentiment, otherwise generate answer \"no\".\n\nQ: Review: What's with all the negative comments? After having seen this film for the first time tonight, I can only say that this is a good holiday comedy that is sure to brighten up any lonely person's day. When I saw that Drew (Ben Affleck) might end up spending the holidays alone, I wanted to cry. You'll have to see the movie if you want to know why. Also, even though I liked Tom (James Gandolfini) and Alicia (Christina Applegate) after awhile, if you ask me, they were real snobs. However, this film did make me smile and feel good inside. Before I wrap this up, I'd like to say that Mike Mitchell has scored a pure holiday hit. Now, in conclusion, I highly recommend this good holiday comedy that is sure to brighten up any lonely person's day to any Ben Affleck or Christina Applegate fan who hasn't seen it. Question: is it a positive review?\n\nA: yes\n**\nQ: Review: Master director Ching Siu Tung's perhaps most popular achievement is this series, A Chinese Ghost Story 1-3. Chinese Ghost Story stars Leslie Cheung in some distant past in China as a tax collector who is forced to spend a night during his \"collecting trip\" in a mysterious castle in which some strange old warriors fight and meet him. Beautiful actress Joey Wang/Wong is the ghost who lives in that castle and is under a domination of one powerful demon, a wood devil who collects human souls for herself/itself with the help of her beautiful ghosts. Leslie and Joey fall in love, and even though ghosts are not allowed to live with humans, they decide to break that rule and live happily together for the rest of their lives. This is not what the wood devil thinks and our protagonists have to fight for their lives and their happiness.This film is no less full of magic than other films by Ching Siu Tung. His masterpieces include Duel to the Death (1983) and the Swordsman series, which all have incredible visuals and kinetic power in their action scenes. Ghost Story is full of brilliant lightning and dark atmosphere, which is lightened by the strong presence of the beautiful and good willing ghost. The effects are simply breath taking and would work at their greatest power in the big screen. The camera is moving and twisted all the time and it adds to the fairy tale atmosphere this film has. There's plenty of wire'fu stunts, too, and even though some think they are and look gratuitous or stupid when used in films, I cannot agree and think they give motion pictures the kind of magic, freedom and creativeness any other tool could not give. When people fly in these films, it means the films are not just about our world, and they usually depict things larger than life with the power of this larger than life art form.The story about the power of love is pretty touching and warm, but the problem is (again) that the characters are little too shallow and act unexplainably occasionally. Leslie and Joey should have been written with greater care and their characters should be even more warm, deep and genuine in order to give the story a greater power and thus make the film even more noteworthy and important achievement. Also, the message about love and power of it is underlined little too much at one point and it should have been left just to the viewer's mind to be interpreted and found. Another negative point about the dialogue is that it's too plenty and people talk in this film without a reason. That is very irritating and sadly shows the flaws many scriptwriters tend to do when they write their movies. People just talk and talk and it's all there just to make everything as easy to understand as possible and so the film is not too challenging or believable as it has this gratuitous element. Just think about the films of the Japanese film maker Takeshi Kitano; his films have very little dialogue and all there is is all the necessary as he tells his things by other tools of cinema and never talks, or makes other characters talk too much in his movies. This is just the talent the writers should have in order to write greater scripts.Otherwise, Chinese Ghost Story is very beautiful and visually breath taking piece of Eastern cinema, and also the song that is played in the film is very beautiful and hopefully earned some award in the Hong Kong film awards back then. I give Chinese Ghost Story 7/10 and without the flaws mentioned above, this would without a doubt be almost perfect masterpiece of the fantasy genre. Question: is it a negative review?\n\nA: no\n\nQ: Review: Ah, the best and funniest movie about female football fans, only slightly better than the 1982 saga of teenage delusion set in North London (qv). By the way, I just watched this on Film 4 [2008-12-21] and am ruing my inability to set the PVR).This is easily my second favourite football movie after \"Mike Bassett: England Manager\", but this time with the added twist of looking like a guerrilla piece of movie-making from a team who apparently keep making movies which are banned in the country in which they are made (just think about the bit where the girls are taken from the stadium just as the Sun is setting: fast reactions all round). It is rare for a movie to make me laugh out loud, but when the rural soldier escorted one of the girls into the lavvies while forcing her to wear an inpromptu mask made from a poster of Ali Daei, I couldn't stop waking the others in the house with my snorts, especially when the young soldier misunderstood the grandfather's calls for assistance... Speaking of the toilets, I just wish I could speak Farsi so that I could work out the writing on the toilet walls (yes, there were a few scribblings in Roman script, but they mostly referred to wanky American rock bands).Also, on the rural-and-Farsi theme, don't you reckon that Omid Djalili sounds like a yokel when he talks Farsi? Listen to the custody sergeant in this movie and then go \"Yup.\"I'm not going to bore on about the sexual politics of Iran, and I'm not going to bore on about the dubious acting; my love for this movie comes from the script and the editing: top notch stuff.Here's a list of my top favourite football movies: 1. Mike Bassett, England Manager 2. Offside 3. Those Glory Glory Days 4. A Shot at Glory 5. The Arsenal Stadium Mystery Question: is it a negative review?\n\nA:" }, { "from": "gpt", "value": "no\n**\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nYou are given a short poem which is written by a kid. Your task is to predict if the kid is in elementary school or high school. Anyone who is from grade 1st to 6th-grade will be considered as in elementary school, and 7th to 12th-grade kids will be considered as in high school. There are only two possible outputs, i.e., elementary and high. All inputs have at least one output and it cannot have both categories at a time.\n\nthis life be the sparkle ocean i be aware of my vulnerablity destiny be my lead yet i choose each path though sometimes ocean may be calm gently ripple sometimes there be tsunami wash away the weak i 've hear i be glue to the wave move with them a the crash & amp settle i be not afraid of time hard to hold on i do not fear for i be a snake bend & amp blend with my destiny but i choose my reaction forever change my world i promise there shall be struggle i accept this gratefully i be the snake move with the water that may carry or crash it be journey one i will happily survive\nOutput:" }, { "from": "gpt", "value": "high" } ]

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.