Search is not available for this dataset
conversations
listlengths 2
2
|
|---|
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\nExample: 6, 14, ['9545', '5185', '1667', 'w', 's', '9559', 'T', 'u', 'U', '6843', 'L', 'l', '6365', '7103', 'A', '2381', '5037', 'X', '4487', 'd']\nOutput: 9559, T, u, U, 6843, L, l, 6365, 7103\nHere, all the elements between the 6th element and 14th element are '9559', 'T', 'u', 'U', '6843', 'L', 'l', '6365', and '7103'.\n\nNew input case for you: 3, 4, ['1207', 'A', 'h', '6765', 'Z', 'v']\nOutput:"
},
{
"from": "gpt",
"value": "h, 6765"
}
] |
[
{
"from": "human",
"value": "You are given a target race, and two sentences. Your task is to determine whether the second sentence is either a stereotype, anti-stereotype, or is unrelated with respect to the first sentence and the target. A stereotype is a widely held but oversimplified notion of a group of people. An anti-stereotype is an idea that goes against the widely held but oversimplified notion of a group of people. Sentences and targets are unrelated if there is no relevance between them.\n\n[EX Q]: Target: Hispanic \nHispanic people can be found all over the country. They love to dance.\n[EX A]: stereotype\n\n[EX Q]: Target: Britain \nbritain is where my ancestors are from. The telephone bill is too high this month.\n[EX A]: unrelated\n\n[EX Q]: Target: Eritrean \nThe Eritrean walked down the lane. He had dark skin and looked poor.\n[EX A]:"
},
{
"from": "gpt",
"value": "stereotype\n\n"
}
] |
[
{
"from": "human",
"value": "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. \nExample: 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.\nExample solution: 5\nExample explanation: The user really seem very satisfied with the product and gave good review worthy of 5 stars rating.\n\nProblem: This quinoa has to be rinsed! I would not have ordered it if I had known that. There are many other brands for the same price that DON\"T require this annoying and messy step.\n"
},
{
"from": "gpt",
"value": "Solution: 1"
}
] |
[
{
"from": "human",
"value": "Teacher: 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.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\n1968 : 1.\nSolution: Num Punc Num Punc\nReason: Based on the given question, All of the POS tags are correct.\n\nNow, solve this instance: ( FSt )\nStudent:"
},
{
"from": "gpt",
"value": "Punc N Punc"
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: In this task, you're given a statement and three sentences as choices. Your job is to determine which sentence can be inferred from the statement. Incorrect choices change the meaning in important ways or have details that are not mentioned in the statement. Indicate your answer as 1,2, or 3 corresponding to the choice number of the selected sentence.\nPROBLEM: Statement: Households' wealth-income ratio dropped from its 1999 peak. Choices: 1. Househould wealth-income increased since 1999. 2. Wealth-income ratio fell from what it was in 1999. 3. Income from the middle class have suffered greatly more than the other classes.\n\nSOLUTION: 2\n\nPROBLEM: Statement: 'I tire of this conversation,' White said. Choices: 1. I'll never get sick of this conversation, said White. 2. What was sick of the conversation. 3. White was tired of talking about the election. \n\nSOLUTION: 2\n\nPROBLEM: Statement: The central part of the Po valley is only a fraction of the Italian lands conquered by the Lombards when they crosed the Alps from eastern Europe in the early Middle Ages. Choices: 1. No part of the Po Valley was conquered by the Lombards. 2. The middle of the Po Valley is one area that was conquered by the Lombards. 3. The areas on the east and west sides of the Po Valley were not conquered.\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "2\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.\nQ: [[-34, -44, 12], [-48, -5, 9, 21, -14], [50, 8], [-14, 20, 40, -41, 26], [28, 24, 37, 2], [3, -33, 50, 14], [-26, 14, 14]]\nA: "
},
{
"from": "gpt",
"value": "[17952, -635040, 400, 11939200, 49728, -69300, -5096]"
}
] |
[
{
"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 need to count the number of words in a sentence that end with the given letter. Answer with numbers and not words.\n\nSentence: 'the street light is green in the city'. How many words end with the letter 't' in the sentence.\nSolution: 2\nWhy? The words 'street', and 'light' end with the letter 't'. So, the answer is 2.\n\nNew input: Sentence: 'several ingredients and tools for cooking sit on a counter'. How many words end with the letter 'r' in the sentence.\nSolution:"
},
{
"from": "gpt",
"value": "2"
}
] |
[
{
"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 incoherent / implausible by indicating 1 or 2 in the output. If both sentences are plausible, pick the one that makes less sense.\nOne example is below.\nQ: Beginning: Butch had a really old computer. Middle 1: Butch decided to order a new computer online. Middle 2: Butch noticed that a storm was approaching to his town. Ending: It arrived and Butch was much happier.\nA: 2\nRationale: People generally don't feel happy about natural disasters like storms. Therefore, we choose 2 in this case.\nQ: Beginning: Gina's crush sat behind her in class. Middle 1: When the tests scores came back she found out he had been studying very hard. Middle 2: When the tests scores came back she found out he had been lying about studying. Ending: Gina realized he wasn't her type after all.\nA:"
},
{
"from": "gpt",
"value": "1"
}
] |
[
{
"from": "human",
"value": "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.\nQ: Middle: He and his best friend signed up for a haunted tour of a building in a neighboring town that was known for being haunted. Ending: They were disappointed because nothing much happened.\nA: "
},
{
"from": "gpt",
"value": "Luis was interested in the supernatural."
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nGiven news headlines, an edited word and funniness labels. The original sentence has word with the given format {word}. Create new headlines by replacing {word} in the original sentence with edit word. Your task is to generate answer \"Yes\" if an edited sentence matches funniness label, otherwise generate answer \"No\". \n\nNews Headline: ' We have plenty of time ' : Congress may delay decision on fate of 700,000 {Dreamers} \n Edit: nightmares \n Label: Not Funny\nOutput:"
},
{
"from": "gpt",
"value": "No"
}
] |
[
{
"from": "human",
"value": "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.\n\nInput: Consider Input: turn right twice and walk around right thrice\n\nOutput: I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK\n\n\nInput: Consider Input: walk opposite left thrice after jump around right twice\n\nOutput: I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_LEFT I_TURN_LEFT I_WALK I_TURN_LEFT I_TURN_LEFT I_WALK I_TURN_LEFT I_TURN_LEFT I_WALK\n\n\nInput: Consider Input: turn opposite right twice after run around left thrice\n\n"
},
{
"from": "gpt",
"value": "Output: I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT\n\n\n"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, five ordered key facts are given. All the given facts are expressed in natural language. Your job is to generate a story 100 to 1000 words long, that includes all the facts given as input in their order of appearance while expanding upon them to produce a broader, yet coherent, narrative.\nInput: Fact1: Bombay after berates team for not listening to him game, Fact2: result is complete makeover both in look and in skill, Fact3: potential of Ducks player Charlie Conway catches Bombay 's eye, Fact4: Conway used when he played with Hawks hockey tactics, Fact5: star player for Hawks be playing for Ducks due to redistricting\nOutput:"
},
{
"from": "gpt",
"value": "Gordon Bombay Emilio Estevez is a successful Minneapolis defense attorney who never loses a case but whose courtroom antics have earned him no respect among his peers. After successfully defending a client resulting in his 30th win, Bombay is called into his bosss office to be congratulated but also chastised for embarrassing the judge. He responds by going out drinking and is subsequently arrested for drunken driving. Bombay is sentenced to community service by coaching the local District 5 PeeWee hockey team. Bombay has an unpleasant history with the sport; in 1973, Bombay was the star player on the Hawks, but, struggling to cope with the loss of his father, he missed a penalty shot during the championship game, disappointing his hypercompetitive coach, Jack Reilly Lane Smith. The Hawks would go on to lose in overtime. When Bombay meets the team, he realizes the children have no practice facility, equipment or ability. The teams first game with Bombay at the helm is against the Hawks. Reilly is still the head coach and remains bitter about Gordons miss years earlier. District 5 is routed as Reilly demands the Hawks run up the score; after the game, Bombay berates the team for not listening to him, and the players challenge his authority. For the next match, Bombay tries to teach his team how to dive and draw penalties, but this angers the team further. Meanwhile, Bombay discovers his old mentor and family friend Hans Joss Ackland, who owns a nearby sporting goods store, was in attendance. While visiting him, Bombay recalls that he quit playing hockey after losing his father four months before the championship game, and due to Reilly blaming Gordon for the loss. Hans encourages him to rekindle his childhood passion. Bombay approaches his boss, the firms cofounder Gerald Ducksworth Josef Sommer to sponsor the team. The result is a complete makeover for the team both in look, as they can now buy professional equipment, and in skill, as Bombay has more time to teach the kids hockey fundamentals. Currently playing as the Ducks named for Ducksworth. They fight to a tie in the next game. The Ducks recruit three new players: Figure skating siblings Tommy Danny Tamberelli and Tammy Duncan Jane Plank and slap shot specialist and enforcer Fulton Reed Elden Henson. The potential of Ducks player Charlie Conway Joshua Jackson catches Bombays eye; he takes him under his wing and teaches him some of the hockey tactics he used when he played with the Hawks. Bombay learns that, due to redistricting, the star player for the Hawks, Adam Banks Vincent Larusso, should be playing for the Ducks. He then threatens Reilly into transferring Banks to the Ducks. After hearing an outofcontext quote about them, the Ducks players lose faith in Bombay and revert to their old habits. Ducksworth makes a deal with Reilly about the Hawks keeping Banks; however, Bombay refuses it, since it would be against fair play, which Ducksworth berated him about when he started his community service. Left with either the choice of letting his team down or get fired from his job, Bombay takes the latter. Bombay manages to win back the trust of his players after they win a crucial match, and Banks, who decided hed rather play for the Ducks than not play hockey at all, proves to be an asset, and the Ducks reach the championship against the Hawks. Despite the Hawks massive attacks taking Banks out of the game, the Ducks manage to tie the game late, and Charlie is tripped by a Hawks player as time expires. In precisely the same situation Bombay faced at the beginning of the film, Charlie prepares for a penalty shot to win the championship. In stark contrast to Reilly who told Bombay that if he missed, he was letting everyone down Bombay tells Charlie that he will believe in him no matter what happens. Inspired, Charlie jukes out the goalie with a tripledeke taught to him by Bombay to defeat the Hawks for the state championship. The Ducks and family race out onto the ice in jubilation, where Bombay thanks Hans for his belief in him and Hans tells Bombay he is proud of him. Later, Bombay boards a bus headed to a minorleague tryout, secured for him by the NHLs Basil McRae of the Minnesota North Stars now the Dallas Stars. Although he seems daunted at the prospect of going up against younger players, he receives the same words of encouragement and advice from the Ducks Bombay had given them, promising he will return next season to defend their title."
}
] |
[
{
"from": "human",
"value": "Given a question and a context passage, generate the answer having the word or phrase from the context passage. Here, the answer should be a shortest continous span from the passage.\n\nContext: In this version, both Finduilas and Gil-galad were his children, while in the published Silmarillion, Gil-galad was the son of Orodreth's cousin Fingon. \n Question: Who is the offspring of Orodreth?"
},
{
"from": "gpt",
"value": "gil-galad"
}
] |
[
{
"from": "human",
"value": "In this task you will be given a list, of lists, of integers. For every inner list contained in the input list, you should multiply every odd number in that list. The output should be a list of integers with the same length as the number of lists in the input list. If there are no odd numbers in an inner list you should output 0 for that list.\nOne example: [[4, 4, 12, -6], [-9, 5, -6, -1], [8, 3, 9, -5, 1]]\nSolution is here: [0, 45, -135]\nExplanation: The first inner list has no odd integers, so the first number in the output is 0. The second list has -9, 5, -1 for odd integers so the second output is 45. The third list has 3, 9, -5, 1 as even numbers so the third output is -135. This is a good example.\n\nNow, solve this: [[-16, 22, -33], [24, -38], [17, 18, 1, -2], [-29, 16], [-50, 27], [-49, 17], [-21, 12, -18, -12], [-43, 43], [-15, 4, 0]]\nSolution:"
},
{
"from": "gpt",
"value": "[-33, 0, 17, -29, 27, -833, -21, -1849, -15]"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. The input is a conversation between an automated system and a user looking for suggestions for pubs, restaurants and coffee shops in Cambridge. In the dialogue, the user may provide some criteria for the type of place they want such as price range, cuisine, etc. Given such a dialogue, output the price range the user if looking for which can take one of four values: Cheap, Moderate, Expensive and Don't Care. Output cannot be any other value than the four values. Note that if the user asks for the prices of items provided at a pub, restaurant or coffee shop but doesn't mention the price range they are looking for then the correct classification will be Don't Care. If the user does not mention a particular price, the correct classification will be Don't Care.\n\nSystem: 'Thank you for calling the Cambridge Information system. Your call will be recorded for research purposes. You may ask for information about a place to eat, such as a restaurant, a pub, or a cafe. How may I help you?'\nUser: 'im looking for an expensive restaurant in the fenington area'\nSystem: 'What part of town do you have in mind? For example, something in the Barnwell, New Chesterton, or Trumpington area.'\nUser: 'fen ditton'\nSystem: 'What part of town do you have in mind? For example, something in the Addenbrooke's, central, or Romsey area.'\nUser: 'area'\nSystem: 'What part of town do you have in mind? For example, something in the Barnwell, New Chesterton, or Trumpington area.'\nUser: 'feninton'\nSystem: 'What part of town do you have in mind? For example, Barnwell.'\nUser: 'fen ditton'\nSystem: 'What part of town do you have in mind? For example, something in the Addenbrooke's, Barnwell, or Chesterton area.'\nUser: 'thank you good bye'\n\n"
},
{
"from": "gpt",
"value": "Expensive"
}
] |
[
{
"from": "human",
"value": "In this task the focus is on physical knowledge about the world. Given the provided goal task in the input, describe a process that would lead to the asked outcome. This process often involves physical motions with objects, such as moving them, arranging them in a certain way, mixing them, shaking them, etc. \nOne example is below.\nQ: How do you remove keys from a computer keyboard for cleaning?\nA: Place the tip of a knife under the corner of a key and gently twist to pop it off.\nRationale: The process of removing keys from a keyboard for cleaning is descriptive and logical.\nQ: how to charge riding mower battery\nA:"
},
{
"from": "gpt",
"value": "Make sure the charger is off. Hook-up the positive cable on the charger to the positive terminal on the battery. Hook up the negative cable on the charger to the negative terminal on the battery. Set the charger to the slowest charge rate."
}
] |
[
{
"from": "human",
"value": "You are given an open-domain question from an open movie database. Your task is to provide an answer to that question. Try to only include the answer. Do not put it in a sentence.\n\nEx Input:\nwhat is the main language in The Organization?\n\nEx Output:\nEnglish\n\n\nEx Input:\nwho is the creator of the film script for My Sister Eileen?\n\nEx Output:\nJoseph Fields, Jerome Chodorov, Ruth McKenney\n\n\nEx Input:\nwho is the director of Rosalie Goes Shopping?\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "Percy Adlon\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about \"doctors\", you can talk about \"health\" or \"diagnosis\", but don't mention \"aliens\". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example: \"She likes cakes.\" is changed to \"She doesn't like cakes.\"\n\nBeginning: Charles hated living in a sober living home. Middle: Charles and his friends decided to drink some alcohol. Ending: Then his roommate walked in wearing Charles' undergarments."
},
{
"from": "gpt",
"value": "Charles and his friends decided not to drink alcohol."
}
] |
[
{
"from": "human",
"value": "Instructions: You will be given one or more triples. The second part of each triple shows the relation between the first and the third element. Your task is to write a simple and short piece of text (sentence(s)) that describes the triples in natural language.\nInput: Dave_Challinor | club | A.F.C._Fylde\nOutput:"
},
{
"from": "gpt",
"value": "Dave Challinor is a player at the A.F.C. Fylde ."
}
] |
[
{
"from": "human",
"value": "In this task, you're given a context passage, an answer, and a question. Your task is to classify whether the question for this answer is correct or not, based on the given context with commonsense reasoning about social situations. If its correct ,return \"True\" else \"False\".\n\nContext: Jan left Riley's keys for them because she could not drive. \n Answer: very responsible \n Question: How would you describe Jan?"
},
{
"from": "gpt",
"value": "True"
}
] |
[
{
"from": "human",
"value": "Instructions: Given a statement about date and time, state whether the statement is true or false. The number of date/time operands in the statement ranges between 2 and 3. Let's say the values are denoted by t1, t2 and t3. The statements follow one of the following ten templates: 't1 occurs before t2, t1 doesn't occur before t2, t1 occurs after t2, t1 doesn't occur after t2, t1 occurs between t2 and t3, t1 doesn't occur between t2 and t3, t1 occured before t2 but after t3, t1 occured after t2 but before t3, t1 didn't occur before t2 but after t3, t1 didn't occur after t2 but before t3'. The output should be either 'True' or 'False'.\nInput: Dec 24, 2020 doesn't occur between September 15, 1992 and 23 June 2017\nOutput:"
},
{
"from": "gpt",
"value": "True"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element in the reverse order. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n\n7, 9, ['6895', '8971', '8121', 'Y', 'u', 'Z', '7095', 'c', 'w', 'c', '4007', '2839', 'm', '6499', 'k', 'D', 'k']\n"
},
{
"from": "gpt",
"value": "w, c, 7095"
}
] |
[
{
"from": "human",
"value": "In this task, you are given inputs i, j, and A, where i and j are integers and A is a list. You need to find all elements of A from the ith element to the jth element, reverse the order in which they occur, and then concatenate them to output the resultant string. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j. Perform the operations in order, i.e., do not concatenate the elements and then reverse the string.\n\nEx Input:\n1, 3, ['1827', 'A', '5773']\n\nEx Output:\n5773A1827\n\n\nEx Input:\n4, 6, ['3783', '2617', '9287', 'W', '2595', 'Y', '9381', '1233', 'H', '2117', 'F', '4805', 'e', '8563', '7089', 'p', '5517']\n\nEx Output:\nY2595W\n\n\nEx Input:\n4, 9, ['n', 'R', '2135', '1451', '4993', 'I', '4407', '941', 'L', 'b', '3605', '107', 'x', 'g', 'm', '3723', 'z', '9013', '3465', 'R', 'c', '603', 't', 'z', 'B', 'Q']\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "L9414407I49931451\n\n\n"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to concatenate all elements of A from the ith element to the jth element, and print the resultant string. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\nInput: 5, 6, ['E', 'W', 'M', '497', 'h', '7955', '1433', '43', '2193']\nOutput:"
},
{
"from": "gpt",
"value": "h7955"
}
] |
[
{
"from": "human",
"value": "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].\n\nPost: @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 "
},
{
"from": "gpt",
"value": "Aggresive"
}
] |
[
{
"from": "human",
"value": "In this task, you are given an answer, and your task is to generate a reasonable question for that answer.\n\nQ: I like classic science fiction.\n\nA: Are you a science fiction fan?\n****\nQ: Not for a long time\n\nA: Are you single?\n****\nQ: They are very well.\n\nA:"
},
{
"from": "gpt",
"value": "Are your parents still alive?\n****\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a news article. Your task is to classify the article to one out of the four topics 'World', 'Sports', 'Business', 'Sci/Tech' if the article's main topic is relevant to the world, sports, business, and science/technology, correspondingly. If you are not sure about the topic, choose the closest option. Note that URLs in the text have been replaced with [Link].\nQ: Washington Baseball at Risk, MLB May Seek Bids WASHINGTON (Reuters) - Washington, D.C., Mayor Anthony Williams on Wednesday said the deal to bring baseball back to the U.S. capital was close to dead after the city council changed the plan to require private financing, a move Major League Baseball called unacceptable.\nA: "
},
{
"from": "gpt",
"value": "Sports"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given inputs i, j, and A, where i and j are integers and A is a list. You need to find all elements of A from the ith element to the jth element, reverse the order in which they occur, and then concatenate them to output the resultant string. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j. Perform the operations in order, i.e., do not concatenate the elements and then reverse the string.\nExample: 1, 3, ['238', 'h', '92', 'U', '2799']\nOutput: 92h238\nHere, concatenating all the elements between the 1st element and 3rd element in reverse order gives '92h238'.\n\nNew input case for you: 4, 5, ['c', '321', '8959', 'b', 'P', '8657']\nOutput:"
},
{
"from": "gpt",
"value": "Pb"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In mathematics, the absolute value of a number is the non-negative value of that number, without regarding its sign. For example, the absolute value of -2 is 2, and the absolute value of 5 is 5. In this task you will be given a list of numbers and you need to return the element with highest absolute value. If a negative and positive element have the same absolute value you should return the positive element. The absolute value for negative numbers can be found by multiplying them by -1. After finding the element with the maximum absolute value you should return the value of that element before you applied the absolute value.\n\n[ 82.14 -94.783 97.018 -14.877 81.151]\n"
},
{
"from": "gpt",
"value": "97.018"
}
] |
[
{
"from": "human",
"value": "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'.\n\nLet me give you an example: 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\nThe answer to this example can be: C\nHere is why: 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\nOK. solve this:\nContext: Taylor raised up Cameron's arms because they were reenacting a scene from the Bible. \n Question: Why did Taylor do this? \n Options: (A) question taylor (B) tell a story (C) be wrong\nAnswer:"
},
{
"from": "gpt",
"value": "B"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you will be shown a conversation and a question. You need to answer the question and choose the correct option based on the conversation. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\nExample: M: I am considering dropping my dancing class. I am not making any progress. W: If I were you, I stick with it. It's definitely worth time and effort., Question: What does the man suggest the woman do? (A) Consult her dancing teacher. (B) Take a more interesting class. (C) Continue her dancing class.\nOutput: (C) Continue her dancing class.\nThis is a good example. Based on the conversation, we could understand that only option (C) is correct.\n\nNew input case for you: M: Shall we go to the park tomorrow? W: Good idea. What should I take? M: Your camera, please., Question: What does the man tell the woman to take? (A) Her umbrella. (B) Her camera. (C) Her hat.\nOutput:"
},
{
"from": "gpt",
"value": "(B) Her camera."
}
] |
[
{
"from": "human",
"value": "In this task, you will be presented with a question and you have to answer the question based on your knowledge. Your answers should be as short as possible.\n\nEx Input:\nHow many winners resulted from the club that is also known as `` The Sharks '' ?\n\nEx Output:\n1\n\n\nEx Input:\nThe area with the lowest recorded temperature has a peak ranked where on the list of mountains ?\n\nEx Output:\nfifth-highest\n\n\nEx Input:\nHow many MW is the power station formally listed on the stock exchanges of Pakistan in 2005 ?\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "1,600\n\n\n"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nGiven a negotiation between two participants, answer 'Yes' if both participants agree to the deal, otherwise answer 'No'.\n\nTHEM: all hats to you, book and balls to me YOU: ill give you just one ball and the book THEM: i can cede the book (plus hats) if i can have both balls YOU: what is cede THEM: give YOU: deal.\nOutput:"
},
{
"from": "gpt",
"value": "No"
}
] |
[
{
"from": "human",
"value": "You are asked to create a question containing a blank (_), based on the given context word. Your question must contain two related but different objects; for example \"trophy\" and \"suitcase\". The expected answer to your question must be one of the objects present in the sentence. The expected answer must not be associated with any specific word in the question; instead it should depend on the context present in the question. The expected answer should not be equally likely to fill the blank. For your question, there should be a agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use animals or proper nouns (e.g., New York, Macbook, Jeff Bezos, McDonald's, ...) as your objects. Avoid repeating the same style, pattern or phrases in each question, try to increase diversity by varying sentence structure, blank placement etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Object X and Y have the same number e.g. when ObjectX is singular, Object Y must be singular, too. The two objects (Object X & Object Y) should be used ONCE in your question. Here is a list of attributes and associated pair of contrastive words which may be used to create a valid question using the objects. You can use either of the contrastive words, but not both. You should think about more such attributes and associated words and use them in your question.\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\n\nContext Word: warts."
},
{
"from": "gpt",
"value": "The new cream didn't remove the warts like the last lotion, because the _ was not powerful enough."
}
] |
[
{
"from": "human",
"value": "Definition: You are given a dialog between 2 or more individuals. Within the dialog, there will be clues that indicate two individuals were or are dating. You will be prompted at the end to answer which Speaker (or named individual) is dating which other Speaker (or named individual).\nInput: Speaker 1: And why not?! \nSpeaker 2: Because I'm in love with Monica!! \nSpeaker 1: You're-you're what?! \nSpeaker 2: Love her! That's right, I...LOVE...HER!!! I love her!! I love you, Monica. \nSpeaker 3: I love you too Chandler. \nSpeaker 1: I just-I thought you guys were doing it, I didn't know you were in love! \nSpeaker 4: Dude! \nSpeaker 2: And hats off to Phoebe. Quite a competitor. And might I say your breasts are still showing. \nSpeaker 1: God! \nSpeaker 4: All right! So that's it! It's over! Everybody knows! \nSpeaker 3: Well actually, Ross doesn't. \nSpeaker 2: Yes, and we'd appreciate it if no one told him yet. Speaker 2 is or was dating which Speaker?\nOutput:"
},
{
"from": "gpt",
"value": "Speaker 3"
}
] |
[
{
"from": "human",
"value": "Definition: 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.\nInput: Context: Austin traced back his footsteps but did not find his wallet yet. \n Question: What will Austin want to do next? \n Options: (A) learn new steps next (B) look other places next (C) wanted to check where he dropped it\nOutput:"
},
{
"from": "gpt",
"value": "C"
}
] |
[
{
"from": "human",
"value": "In this task, you're given the title of a story consisting of five sentences, numbered 1 through 5. Your job is to determine which two sentences need to be swapped sentences in order to make a story that makes complete sense and is befittingly titled. Indicate your answer using the numbers of the two sentences in order, such as '34' or '25'. The first digit refers to the sentence which should come first in the story.\n\nQ: Title: Gabby. Sentence 1: Gabby now spends her afternoons playing with her doll house. Sentence 2: She saved all of her allowance money to buy one. Sentence 3: She went to a toy store with her parents. Sentence 4: Gabby found the perfect pink and purple doll house. Sentence 5: Gabby always wanted a doll house.\n\nA: 15\n****\nQ: Title: Invite. Sentence 1: Most of the teams did not have an important race so soon. Sentence 2: She told us not to run our hardest. Sentence 3: My coach said we wanted to be invited again. Sentence 4: We had an important race next week. Sentence 5: This was a cross country race.\n\nA: 13\n****\nQ: Title: Crusty Food. Sentence 1: Ursula took out several ingredients to prepare eggs. Sentence 2: She cracked two eggs open and placed them in a pan. Sentence 3: They started to sizzle. Sentence 4: However, she wasn't aware when they burned to a crisp. Sentence 5: Ursula left the eggs for several minutes.\n\nA:"
},
{
"from": "gpt",
"value": "54\n****\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, given a sentence in the English language, your task is to convert it into the Filipino language.\nQ: \"Out of concern for the interpreters and their families' security as well as the security of the Danish base in Iraq, the Defence Ministry has chosen to inform the public after the interpreters and others had left Iraq,\" the Danish Defence Ministry said in a statement.\nA:"
},
{
"from": "gpt",
"value": "\"Para sa kapakanan ng mga ng mga tagapagsalin at seguridad ng kanilang mga pamilya pati narin ang seguridad ng mga taga denmark na nakabase sa Iraq, Pinili ng Ministro ng Depensa na ipaalam sa publiko matapos makaalis sa Iraq ang mga tagapagsalin at iba pa,\" nasabi ng Danish Defence Ministry sa isang pahayag."
}
] |
[
{
"from": "human",
"value": "Q: Given a sentence in French, generate a new French 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.\nSi vous voulez visiter d'autres pays, alors vous devriez avoir un passeport.\nA:"
},
{
"from": "gpt",
"value": "Si vous voulez interdire d'autres spectacles, alors vous devriez avoir une maison."
}
] |
[
{
"from": "human",
"value": "In this task, you're given a question, a context passage, and four options which are terms from the passage. After reading a passage, you will get a brief understanding of the terms. Your job is to determine by searching and reading further information of which term you can answer the question. Indicate your choice as 'a', 'b', 'c', or 'd'. If you think more than one option is plausible, choose the more probable option to help you answer the question.\nQ: Question: What did the 390th Tactical Fighter Squadron do during the Vietnam War? Passage:Vandenberg graduated from the United States Military Academy in 1951 (where Buzz Aldrin was one of his classmates). In 1953, Vandenberg was assigned to the 86th Fighter-Bomber Wing. Later he would serve as a flight commander with the 413th Tactical Fighter Wing and the 31st Tactical Fighter Wing. He graduated from the Air Command and Staff College in 1961, after which he was assigned to the 4th Tactical Fighter Wing. In 1963, Vandenberg was appointed Operations Officer with the 23rd Tactical Fighter Squadron. During the Vietnam War, Vandenberg commanded the 390th Tactical Fighter Squadron. Upon returning stateside he was assigned to The Pentagon to work in the Office of the Director of Plans. He would graduate from the National War College in 1969 and return to The Pentagon to work with the Joint Chiefs of Staff. In 1971, Vandenberg became commander of the 12th Flying Training Wing. Vandenberg was named Vice Commandant of Cadets at the United States Air Force Academy in 1972. He would serve as Commandant from 1973 to 1975, during which time he assumed the rank of brigadier general. From 1976 to 1979, Vandenberg served at Headquarters U.S. Air Force, first as Deputy Director of Plans, later as Director of Operations and Readiness, and finally as Assistant Deputy Chief of Staff for Operations, Plans, and Readiness. Vandenberg was ultimately named Vice Commander in Chief of the Pacific Air Forces. His retirement was effective as of January 1, 1981.\n Links: a. Buzz Aldrin b. 390th Electronic Combat Squadron c. Joint Chiefs of Staff d. Vietnam War\nA: "
},
{
"from": "gpt",
"value": "b"
}
] |
[
{
"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.\n\nEx Input:\nselect the rows whose opponent record fuzzily matches to san francisco 49ers . the maximum attendance record of these rows is 65551 . the date record of the row with superlative attendance record is november 11 , 1979 .\n\nEx Output:\nand { eq { max { filter_eq { all_rows ; opponent ; san francisco 49ers } ; attendance } ; 65551 } ; eq { hop { argmax { filter_eq { all_rows ; opponent ; san francisco 49ers } ; attendance } ; date } ; november 11 , 1979 } }\n\n\nEx Input:\nselect the rows whose channel record fuzzily matches to atv world . take the launch date record of this row . select the rows whose channel record fuzzily matches to tvb pearl . take the launch date record of this row . the first record is less than the second record .\n\nEx Output:\nless { hop { filter_eq { all_rows ; channel ; atv world } ; launch date } ; hop { filter_eq { all_rows ; channel ; tvb pearl } ; launch date } }\n\n\nEx Input:\nfor the hand guards records of all rows , most of them fuzzily match to m4 .\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "most_eq { all_rows ; hand guards ; m4 }\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a context passage, followed by a question that needs to be answered. Based on the paragraph, you must write unambiguous answers to the questions and your answer must refer to a specific phrase from the paragraph. If multiple answers seem to exist, write the answer that is the most plausible.\n\nAustin interfered and got in Sydney's way when she tried to get to work. \nQuestion: What will Sydney want to do next?"
},
{
"from": "gpt",
"value": "tell Austin to leave her alone"
}
] |
[
{
"from": "human",
"value": "instruction:\nIn this task, you're given a review from Amazon. 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, 4: good, 5: extremely good.\nquestion:\nGreat, comfy, no padding but still great lift, keeps everything in place, easy on/off. Bought another one right away! I am a 34DD in bras so I bought this in 36DD for some give, and it was perfect. I am also very short so need a lot of tightness in the shoulders and they adjust far enough to stay put.\nanswer:\n5\n\n\nquestion:\nBest betta food on the market! Just make sure you soak the pellets for at least five minutes in tank water before feeding your fish. You would be surprised at how large they get.\nanswer:\n5\n\n\nquestion:\nOnly marking this down because I ordered 2 of the 3 packs and one of the packs was completely damaged. Emailed the company and never got a response or refund.\nanswer:\n"
},
{
"from": "gpt",
"value": "1\n\n\n"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you need to answer basic science questions. For each question, several terms are intentionally masked with ***. This masking can cover very few or many of the question words. Clearly, if masked terms are important, the modified question will be impossible to answer. Please indicate the correct answer with one of the following responses: \"A\", \"B\", \"C\", \"D\" or \"E\". While \"A\"-\"D\" correspond to the answer options provided in the input, \"E\" represents \"I don't know\" for questions that do not provide enough information. Respond via \"E\" if the question is not answerable. Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D', 'E'.\n\nQuestion: A student *** a *** of *** to a glass of *** water. The *** *** *** (A) increases (B) decrease (C) stay the same (D).\nOutput:"
},
{
"from": "gpt",
"value": "E."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given commands (in terms of logical operations) and natural interpretation of the given command to select relevant rows from the given table. Your job is to generate a label \"yes\" if the interpretation is appropriate for the command, otherwise generate label \"no\". \n Here are the definitions of logical operators: \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.\nProblem:Command: and { only { filter_eq { all_rows ; reason for change ; died } } ; eq { hop { filter_eq { all_rows ; reason for change ; died } ; vacator } ; thomas blount ( dr ) } }, interpretation: select the rows whose reason for change record fuzzily matches to died . there is only one such row in the table . the vacator record of this unqiue row is thomas blount ( dr ) .\nSolution:"
},
{
"from": "gpt",
"value": "yes"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task you are given a tweet. You must judge whether the author of the tweet is sad or not. Label the instances as \"Sad\" or \"Not sad\" based on your judgment. You can get help from hashtags and emojis, but you should not judge only based on them, and should pay attention to tweet's text as well.\nQ: Happiness is always there. You just have to choose to see it. There's no point dwelling in the dark and ignoring the light of the stars.\nA:"
},
{
"from": "gpt",
"value": "Not sad"
}
] |
[
{
"from": "human",
"value": "Definition: In this task, you are given a sentence containing a particular emotion. You must classify the sentence into one of the six emotions: 'joy', 'love', 'anger', 'fear', or 'surprise'.\nInput: i did restart my gallery but only because i was feeling very vain and gorgeous at the time\nOutput:"
},
{
"from": "gpt",
"value": "sadness"
}
] |
[
{
"from": "human",
"value": "Q: 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 are also given a question about the story that requires an understanding of the relationship described in the background paragraph and the story. You need to come up with an answer to the given question; the answer will be a span from either the question or the story. In order to correctly answer the given question, you need to understand the relationship mentioned in the background paragraph and should be able to use it to understand that in the story. Your answer can not consist of any word that is not mentioned in any of these: the background paragraph, the story, or the question. You can directly copy and paste a span from the story or the question while answering the given question.\nBackground Paragraph: During Amniocentesis a small amount of amniotic fluid, which contains fetal cells, is extracted from the amnion or amniotic sac surrounding a developing fetus, and the fetal DNA is examined for genetic abnormalities. Amniocentesis is not performed for every pregnancy, but is generally done when an increased risk of genetic defects in the fetus is indicated, by mother's age (over 35 years is common), family history of genetic defects, or other factors. \nStory: David is a doctor with the city hospital. Today, he is seeing four patients, patient A, patient B, patient C, and patient D. All four patients are expectant mothers. Moreover, patient A is over thirty five years old, but patient B is under thirty five years old. Patient C has family history of genetic disorder, but patient D does not have any family history of genetic disorder. David needs to prescribe appropriate treatment according to each patient's condition. \nQuestion: Would patient A be less or more at risk of genetic defects in the fetus than patient B?\nA:"
},
{
"from": "gpt",
"value": "more."
}
] |
[
{
"from": "human",
"value": "Q: Categorize the comment on the basis of toxicity. If the comment is toxic (harmful, malicious, derogatory, threat, insult, identity attck, etc.) output Yes, otherwise output No.\nThe decision to file a Petition to Revoke parole or probation--a PTR--is the parole/probation officer's call. The judge can agree to bail but the parole board has the final call: It can either hold the person in prison pending a parole hearing or agree to release them on bail. Either way, being held in jail shouldn't be a death sentence.\nA:"
},
{
"from": "gpt",
"value": "No"
}
] |
[
{
"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 two statements. The task is to output whether a given textual premise, i.e. Statement 2, entails or implies a given scientific fact, i.e. Statement 1. The output should be 'entails' if Statement 2 supports Statement 1 and should be 'neutral' otherwise.\n\nSentence 1: The sum of all chemical reactions that take place within an organism is known as metabolism. Sentence 2: Metabolism is the sum total of all chemical reactions performed by an organism.\nSolution: entails\nWhy? Sentence 2 gives out supporting information about the Metabolism hence it is correct\n\nNew input: Sentence 1: Urine is the term for liquid waste formed by kidneys. Sentence 2: The kidneys filter blood and form urine.\nSolution:"
},
{
"from": "gpt",
"value": "entails"
}
] |
[
{
"from": "human",
"value": "Instructions: The task is to generate text based of an event. For the given event, there will be a person who does the action in the event (usually PersonX). Your task is to write that persons emotional reaction to the event, i.e. how that person feels after doing the action.\nInput: PersonX gives PersonY utterance\nOutput:"
},
{
"from": "gpt",
"value": "clear"
}
] |
[
{
"from": "human",
"value": "You are given a sentence from a conversation between a human and a virtual assistant. Your task is to classify the sentence into one of the following five action categories - INFORM, INFORM_INTENT, OFFER, REQUEST, REQUEST_ALTS. If the sentence is about informing something, generate 'INFORM'. If it is about requesting something, generate 'REQUEST'. If the sentence mentions requesting an alternative option than the one provided, generate 'REQUEST_ALTS'. Similarly, generate 'OFFER' if the sentence is offering some information. If the sentence is about showing intent to do something, generate 'INFORM_INTENT'.\n\nInput: Consider Input: Great. So, what time does the concert start?\n\nOutput: REQUEST\n\n\nInput: Consider Input: Yes, that is what I want. What is the start time of the event and where can I find the venue?\n\nOutput: REQUEST\n\n\nInput: Consider Input: What else have you got?\n\n"
},
{
"from": "gpt",
"value": "Output: REQUEST_ALTS\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to return the sum of all the numerical elements in the list A between the positions i and j (including positions i and j). Return 0 if no numerical element is present in the list between the given ranges. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n\nEx Input:\n1, 12, ['m', 'f', 'y', '2363', '9555', 'E', 'm', 'J', '1977', 'z', '3733', '9745', 'm', 'u', '1033', 'x', '7351', 'O', 'W', '8311', '955', '8643', 'D', 'e', 'z', 'M', '5139', 'o', 'a']\n\nEx Output:\n27373\n\n\nEx Input:\n1, 2, ['E', 'z']\n\nEx Output:\n0\n\n\nEx Input:\n11, 17, ['a', 'S', 'M', '1827', 'F', '225', '7865', 'v', '5013', '3865', 'w', 'N', 'e', 't', '9559', 'W', '3973', '7521', '9489', '6237', '3989', 'q', 'K', 'W']\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "13532\n\n\n"
}
] |
[
{
"from": "human",
"value": "Q: In this task, You are given an amazon food product review and its summary. Your task is to Generate \"True\" if given review and its summary match, otherwise generate \"False\".\nI love this licorice and as someone with a lot of food allergies, I appreciate that it only has four ingredients. \n Summary: Taste like ...\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 story, answer the question about the story. The question is the last sentence in the input. The story has one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios. Note that there are distractor sentences in each story that are unrelated to the question and are designed to confuse the reader.\n\nOwen entered the sunroom. Alexander entered the sunroom. The tangerine is in the green_suitcase. Alexander exited the sunroom. Owen moved the tangerine to the blue_box. Where was the tangerine at the beginning?\nOutput:"
},
{
"from": "gpt",
"value": "green_suitcase"
}
] |
[
{
"from": "human",
"value": "In this task, you need to answer 'Yes' if the given word is the longest word (in terms of number of letters) in the given sentence, else answer 'No'. Note that there could be multiple longest words in a sentence as they can have the same length that is the largest across all words in that sentence.\n\nInput: Consider Input: Sentence: 'big piece of meat on a wood counter top in a kitchen'. Is 'counter' the longest word in the sentence?\n\nOutput: Yes\n\n\nInput: Consider Input: Sentence: 'a couple of dogs are laying on a bench'. Is 'couple' the longest word in the sentence?\n\nOutput: Yes\n\n\nInput: Consider Input: Sentence: 'a laptop and a tablet on a table'. Is 'tablet' the longest word in the sentence?\n\n"
},
{
"from": "gpt",
"value": "Output: Yes\n\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given a disfluent sentence, modify the sentence to it to its equivalent fluent form, preserving the meaning of the sentence.\nSee one example below:\nProblem: Who did the Han Chinese want to help the Khitan no I mean the Mongols fight?\nSolution: Who did the Han Chinese want to help the Mongols fight?\nExplanation: The input initially means Khitan and then changes to Mongols, hence this is correct.\n\nProblem: What is included along with gravitational acceleration proportional to what is included along with gravitational acceleration and mass of the EArth in a formula about rotation about the Earth?\nSolution:"
},
{
"from": "gpt",
"value": "What is included along with gravitational acceration, and mass of the Earth in a formula about rotation about the Earth?"
}
] |
[
{
"from": "human",
"value": "Given a premise, an initial context, an original ending, and a new ending, the task is to generate the counterfactual context that is aligned with the new ending. Each instance consists of a five-sentence story. The premise is the first sentence of a story, and the second sentence, which is the initial context, provides more information about the story's context. The original ending is the last three sentences of the story. Also, you are given a new ending that can provide the new story with the same premise. You should write a counterfactual context to explain the small differences between the original and new endings. More specifically, a story context contains the general plot of the story. And a counterfactual context is a slight modification to the initial context. To sum up, you should write the second sentence of a story based on the premise(first sentence) and the new ending(last three sentences) of the story.\n\nPremise: Marcus decides that he wants to play a sport this Spring. \n Initial Context: He has always been a great runner. \n Original Ending: He decides to try out for the track team. Marcus practices very hard until tryouts begin. Marcus succeeds in tryouts and makes the team! \n New ending: He decides to try out for the swim team. Marcus practices very hard until tryouts begin Marcus succeeds in tryouts and makes the team "
},
{
"from": "gpt",
"value": "He has always been a great swimmer."
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given inputs i, j, and A, where i and j are integers and A is a list. You need to find all elements of A from the ith element to the jth element, reverse the order in which they occur, and then concatenate them to output the resultant string. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j. Perform the operations in order, i.e., do not concatenate the elements and then reverse the string.\n\n1, 2, ['9789', 'w']\nOutput:"
},
{
"from": "gpt",
"value": "w9789"
}
] |
[
{
"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\nExample Input: Premise: PersonX performs PersonX's part\nHypothesis: PersonX then gains confidence\nUpdate: PersonX wins a large pot of money.\nExample Output: strengthener\n\nExample Input: Premise: PersonX gives the ultimate pleasure\nHypothesis: Because PersonX wanted to be the best\nUpdate: They practice all the time\nExample Output: strengthener\n\nExample Input: Premise: PersonX takes PersonX's exam\nHypothesis: Before, PersonX needed to be all the stationery required\nUpdate: PersonX was taking the SAT.\nExample Output:"
},
{
"from": "gpt",
"value": "weakener\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nThis task is about creating an unanswerable question based on a given passage. Construct a question that looks relevant to the given context but is unanswerable. Following are a few suggestions about how to create unanswerable questions:\n(i) create questions which require satisfying a constraint that is not mentioned in the passage\n(ii) create questions which require information beyond what is provided in the passage in order to answer\n(iii) replace an existing entity, number, date mentioned in the passage with other entity, number, date and use it in the question\n(iv) create a question which is answerable from the passage and then replace one or two words by their antonyms or insert/remove negation words to make it unanswerable.\nExample: Passage: In 1763, Spain traded Florida to the Kingdom of Great Britain for control of Havana, Cuba, which had been captured by the British during the Seven Years' War. It was part of a large expansion of British territory following the country's victory in the Seven Years' War. Almost the entire Spanish population left, taking along most of the remaining indigenous population to Cuba. The British soon constructed the King's Road connecting St. Augustine to Georgia. The road crossed the St. Johns River at a narrow point, which the Seminole called Wacca Pilatka and the British named \"Cow Ford\", both names ostensibly reflecting the fact that cattle were brought across the river there.\nOutput: Who owned Cuba after the Eight Years War?\nThis question appears to be relevant to the passage as both involves words such as 'Cuba' and 'War' which also exist in the passage. The passage mentions that \"after the war, almost the entire Spanish population left, taking along most of the remaining indigenous population to Cuba\". This information is not sufficient to conclude that which country owned cuba.\n\nNew input case for you: Passage: For much of Eton's history, junior boys had to act as \"fags\", or servants, to older boys. Their duties included cleaning, cooking, and running errands. A Library member was entitled to yell at any time and without notice, \"Boy, Up!\" or \"Boy, Queue!\", and all first-year boys had to come running. The last boy to arrive was given the task. These practices, known as fagging, were partially phased out of most houses in the 1970s. Captains of House and Games still sometimes give tasks to first-year boys, such as collecting the mail from School Office.[citation needed]\nOutput:"
},
{
"from": "gpt",
"value": "When was fagging mostly eliminated from all Houses?"
}
] |
[
{
"from": "human",
"value": "Q: Based on the information present in the given passage, you need to write a correct answer to the given question. A correct answer is one that correctly and completely answers the question. Do not write answers that address the question partially or incorrectly. The correct answer must be contained in the given paragraph.\nParagraph- Sent 1: (CNN) -- Shain Gandee, one of the stars of the MTV reality show \"Buckwild,\" has been found dead along with two other people in Kanawha County, West Virginia, authorities said Monday.\nSent 2: \"This is a very sad and tragic event,\" Kanawha County Commissioner Kent Carper said.\nSent 3: \"We live in a very small community.\nSent 4: Our thoughts and prayers are with the Gandee family.\"Sent 5: Gandee, 21, was found dead in a vehicle along with his uncle, David Dwight Gandee, 48, and Donald Robert Myers, 27, authorities said.\nSent 6: 'Buckwild' producer talks about the show \"Earlier this day after releasing information Shain Gandee was missing, the Kanawha County Sheriff's Office received word of a disabled vehicle in a wooded area near Thaxton Hollow, Sissonville, Kanawha County WV,\" said a statement from the Sheriff's Office.\nSent 7: \"Deputies and members of the Sissonville Volunteer Fire Department used all terrain vehicles to access that vehicle, a 1984 Ford Bronco belonging to the Gandee family.\nSent 8: The vehicle was in a muddy area along a worn path.\nSent 9: Inside were the bodies of three people.\"Sent 10: In a subsequent release, the Sheriff's Office said the vehicle was partially submerged in mud.\nSent 11: It was uneven but upright; its muffler was below the surface.\nSent 12: Mud covered the lower part of the Bronco's passenger side door, but the driver's side, where the younger Gandee sat, was free, the Sheriff's Office said.\nSent 13: Gandee was happy with life before death He was one of the nine cast members of \"Buckwild.\"Sent 14: The show follows a group of young adults trying to have fun in Sissonville, West Virginia, pulling stunts such as turning a dump truck into a swimming pool or just riding around the woods on their all-terrain vehicles.\nSent 15: Gandee was billed as a former high school prom king who had done \"every job from coal mining to being a garbage man.\". \nQuestion: Was the vehicle fund in the mud?.\nA:"
},
{
"from": "gpt",
"value": "Yes, the vehicle was partially submerged in mud."
}
] |
[
{
"from": "human",
"value": "Instructions: 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 are also given a question about the story that requires an understanding of the relationship described in the background paragraph and the story. You need to come up with an answer to the given question; the answer will be a span from either the question or the story. In order to correctly answer the given question, you need to understand the relationship mentioned in the background paragraph and should be able to use it to understand that in the story. Your answer can not consist of any word that is not mentioned in any of these: the background paragraph, the story, or the question. You can directly copy and paste a span from the story or the question while answering the given question.\nInput: Background Paragraph: Soil is well developed in the forest as suggested by the thick humus layers, rich diversity of large trees and animals that live there. In forests, precipitation exceeds evapotranspiration which results in an excess of water that percolates downward through the soil layers. Slow rates of decomposition leads to large amounts of fulvic acid, greatly enhancing chemical weathering. The downward percolation, in conjunction with chemical weathering leaches magnesium (Mg), iron (Fe), and aluminum (Al) from the soil and transports them downward, a process known as podzolization. This process leads to marked contrasts in the appearance and chemistry of the soil layers. \nStory: Two brothers owned two adjacent parcels of land. Tom's land was forested, while Bill's was covered with grasslands. \nQuestion: Which parcel of land didn't have an excess of water that percolates downward through the soil layers?\nOutput:"
},
{
"from": "gpt",
"value": "Bill's."
}
] |
[
{
"from": "human",
"value": "Q: 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.\n[790, -293, 921, 555, 675, 448, 604, -33, 78, 155, 318, 556, 903]\nA:"
},
{
"from": "gpt",
"value": "[790, -290, 920, 560, 680, 450, 600, -30, 80, 160, 320, 560, 900]"
}
] |
[
{
"from": "human",
"value": "\"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.\n--------\nQuestion: Prompt: Are you gonna use the disk drive of the computer? \n Response 1: He does look a ton like Rodenberg. But, I feel like, didn't you go to our firehouse and try to get a job there? I feel like I remember you from a long time ago. \n Response 2: I didn't even think of that. I rented this place that guaranteed that they had a DVD player.\n\nAnswer: Response 2\n\n\nQuestion: Prompt: I smelled the Tesla charging station from a great distance. The static electricity charge in the air is unmistakable. \n Response 1: I already told you. I want an elf costume for my baby. \n Response 2: The three Teslas are, of course, my Tesla, Gary's Tesla, and Pamela's. We just gave her hers for her sweet 16.\n\nAnswer: Response 2\n\n\nQuestion: Prompt: Now that we've got that all straightened out, what did you want to say, Daniel? Jacket-less. \n Response 1: You know what? I'll put on a jacket if it'll make you happy. \n Response 2: OK. I got those baked lays you wanted.\n\nAnswer:"
},
{
"from": "gpt",
"value": "Response 1\n\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)].\nQ: [\"we're\", 'back', 'with', 'our', 'groceries', 'table', 'but', \"we've\", 'expanded', 'on', 'it', 'a', 'bit', 'it', 'now', 'has', 'a', 'column', 'for', 'which', 'aisle', 'number', 'we', 'can', 'find', 'the', 'item', 'at', 'the', 'supermarket', 'plus', \"we've\", 'added', 'a', 'few', 'more', 'items', 'now', 'you', 'can', 'really', 'see', 'the', 'power', 'of', 'SQL', 'in', '', 'different', 'ways', 'that', 'you', 'can', 'retrieve', '', 'data', 'from', 'your', 'database', 'this', 'is', 'also', 'where', 'it', 'can', 'get', 'a', 'bit', 'tricky', 'to', 'start', 'off', 'simple', 'how', 'would', 'we', 'retrieve', 'all', 'the', 'rows', 'from', 'our', 'table', 'to', 'perform', 'any', 'query', 'right', 'select', 'and', 'then', 'which', 'columns', 'are', 'interested', 'in', 'like', 'the', 'name', 'and']\nA:"
},
{
"from": "gpt",
"value": "['NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF']"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given a passage, write a short incorrect summary based on the passage.\nProblem:result in a world cup group g match here on sunday .\nSolution:"
},
{
"from": "gpt",
"value": "us star lawyer ed fagan to sue poland for unpaid bonds"
}
] |
[
{
"from": "human",
"value": "In this task, you are given two strings A, B. Find the longest common substring in the strings A and B.\n\nQ: bmsrkXGb, GcarkXOZF\n\nA: rkX\n****\nQ: nhGinCtvLartcMPhJwGRbpZNrq, iQJlFKayEartcMPhJwDRROB\n\nA: artcMPhJw\n****\nQ: DRUNELNZbOOSvJah, qgzNZbOOSvJPNiTIVic\n\nA:"
},
{
"from": "gpt",
"value": "NZbOOSvJ\n****\n"
}
] |
[
{
"from": "human",
"value": "Q: In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element in the reverse order. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n16, 16, ['I', 'U', 's', '3845', 'n', '4815', 'p', '9805', 'A', 'r', '4263', '7765', '5967', '1573', 'x', 'P']\nA:"
},
{
"from": "gpt",
"value": "P"
}
] |
[
{
"from": "human",
"value": "Definition: You need to create a question containing a blank (_), based on the given context word. Your question must contain two persons --PersonX and PersonY. The expected answer to your question must be PersonX. PersonX and PersonY should not be equally likely to fill the blank. There should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people (e.g., Donald Trump, Putin, etc.) in your question. Avoid repeating the same style, pattern, or phrases in each question, try to increase diversity by varying sentence structure, blank placement, etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Person X and Person Y have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY.\nInput: Context Word: Pencil.\nOutput:"
},
{
"from": "gpt",
"value": "PersonX gave his pen to PersonY because _ didn't need a pen, as the test required pencil."
}
] |
[
{
"from": "human",
"value": "In this task, answer 'Yes' if the frequency of the given word in the two sentences is equal, else answer 'No'.\n\n[Q]: Sentence1: 'a station wagon being carried in the back of a truck', Sentence2: 'a stuffed animal cat on top of the steering wheel in a car'. Is the frequency of the word 'a' in two sentences equal?\n[A]: Yes\n\n\n[Q]: Sentence1: 'a child kneeling on the foot rest of a recliner playing with a laptop', Sentence2: 'a giraffe is standing near some type of advertising sign'. Is the frequency of the word 'sign' in two sentences equal?\n[A]: No\n\n\n[Q]: Sentence1: 'a woman sitting on a chair next to a man', Sentence2: 'a coach watches on as a pitcher pitches'. Is the frequency of the word 'a' in two sentences equal?\n[A]:"
},
{
"from": "gpt",
"value": "No\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a sentence or phrase in English. You must translate it to Xhosa in a way that is equivalent in terms of meaning and grammatically correct.\n\nFor the upper guide, a round turn is taken through the boom's end fitting and around the spinnaker pole."
},
{
"from": "gpt",
"value": "Ukukhokela okuphezulu, igephe elijikelezileye luthethwa ukudlula kwizifekelo ezisesiphelweni sentsika yokugcinci iseyile ivuliwe ukujikela kwipali yeseyile engunxantathu."
}
] |
[
{
"from": "human",
"value": "In this task, you're given the title of a story consisting of five sentences, numbered 1 through 5. Your job is to determine which two sentences need to be swapped sentences in order to make a story that makes complete sense and is befittingly titled. Indicate your answer using the numbers of the two sentences in order, such as '34' or '25'. The first digit refers to the sentence which should come first in the story.\n\nTitle: Jump Rope Competition. Sentence 1: Alicia loved jumping rope as a young girl. Sentence 2: Alicia was amazed by the moves the jumpers were doing. Sentence 3: Alicia decided to tune in to the jump rope competition. Sentence 4: Alicia was channel surfing, when she saw a jump rope competition. Sentence 5: Alicia was disappointed when the competition was over.\n24\n\nTitle: The Snake in the Leaves. Sentence 1: I was raking up the leaves in my yard into a pile for disposal. Sentence 2: I saw what I thought was a large stick of wood in the pile. Sentence 3: I bent down to pull the stick out, but suddenly it moved! Sentence 4: The snake slithered away and disappeared under the bushes. Sentence 5: The stick was really a garter snake resting in the warm leaves.\n45\n\nTitle: Nap Time. Sentence 1: My 2 year old daughter hates naps. Sentence 2: Today she hid under the bed. Sentence 3: Every day she tries to trick me into letting her stay awake. Sentence 4: I let her stay under there. Sentence 5: She ended up taking a nap under the bed instead!\n"
},
{
"from": "gpt",
"value": "32\n\n"
}
] |
[
{
"from": "human",
"value": "Q: In this task, you are given a question. You have to answer the question based on your information.\nReboot is the final studio album by the group Wonder Girls and was released through a South Korean entertainment company established by who?\nA:"
},
{
"from": "gpt",
"value": "Park Jin-young"
}
] |
[
{
"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\nExample input: If gun bans worked there would be no gun deaths in the countries that have banned guns.\nExample output: Valid\nExample explanation: It is an argument that claims that gun bans will not work.\nQ: [Exempting the Vice President, federal judicial and executive officers, congressmen and congressional officers, custom-house officers and clerks, post-officers and postal stage drivers, ferrymen on post roads, export inspectors, pilots, merchant mariners, and people exempted under the laws of their states\nA:"
},
{
"from": "gpt",
"value": "Invalid"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you are given an input list A. You need to find all the elements of the list that are numbers and calculate their sum.\nInput: ['3723', 'v', 'j', 'e', '2017', 'd', '4211', '2079']\nOutput:"
},
{
"from": "gpt",
"value": "12030"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a dialogue between a user and an assistant, where users and assistants converse about geographic topics like geopolitical entities and locations. The task here is to find if the dialogue is by the user or assistant. Classify your answers into user and assistant.\n\n[EX Q]: Interesting? Do you have any more information on their culture?\n[EX A]: user\n\n[EX Q]: I guess that makes sense huh? Haha. Any other etymology or demographics tidbits?\n[EX A]: user\n\n[EX Q]: You're welcome. Would you like to know more about Sussex tourism or history today?\n[EX A]:"
},
{
"from": "gpt",
"value": "assistant\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given a scientific question, generate an incorrect answer to the given question. The incorrect answer should be a plausible alternative to the correct answer. The answer should be some other item belonging to the same category as the correct answer but should be incorrect.\nQ: How do fungus-like protists such as slime molds reproduce?\nA:"
},
{
"from": "gpt",
"value": "photosynthesis"
}
] |
[
{
"from": "human",
"value": "Given a real-life anecdote of a complex ethical situation, generate a suitable title that describes the main event/root cause of the situation. Imagine that the given text is a social media post, and you have to write the title of the post, so the users can decide to read the main text or not.\nExample: My boyfriend (well just call him M) and I are creators on Instagram (he is also on TikTok). I'm a digital and traditional artist and in one of my classes we create t shirts and things (socks, lanyards, water bottles, stickers, you name it). I'm a big fan of putting my art on t shirts so I can sell them.\n\nM wanted to make some posts for TikTok and wanted to use the shirt I made today. My one personal rule is that if the shirt isn't being given to someone else, then I wear it first (this is because I know I wont get it back. Ive made one other shirt that I've worn, and he wore it for a week and hasn't given it back.) So I told him no, because I haven't worn the shirt yet. \n\nM proceeded to complain about not having content to post, and how his IG post today didn't get any engagement, saying \"of course you dont know, because you never look.\"\n\nAm I the asshole for wanting to wear the shirt I made just once?\nExample solution: wanting to wear a shirt\nExample explanation: The paragraph describes an argument of the author with her boyfriend regarding not wanting to give the shirt she just made before wearing herself. This desire to wear the shirt raises the ethical situation.\n\nProblem: So I know this is going to sound like a SHP, and I know many are going to call it that anyway, but this is really my life. From a young age I have always been freakishly tall. I was 6'0 at 14. I am now bordering on 7 feet at 22. My growth has slowed down considerably, which I am thankful for, but throughout my life I have been struggling.\n\nI know a lot of guys want to be taller. In reality, you feel very strange around your friends when you're growing up, and your family photos when you're a child make you look like a monster with a childs face and a mans body. I am also very shy despite what people think and I was verbally bullied at times based on my height and lankiness in highschool. I have to eat a lot of food to put on weight. I eat almost 4,000 calories a day to maintain my average build.\n\nNow I have started working out to increase my self esteem and I eat almost 5,000 a day. I weigh 320 pounds more or less. I can't go on many rides at theme parks and there are many activities I miss out on. Driving is terrible unless im in a larger pick up truck with cab space, which is very expensive. I don't have too many friends.\n\nWomen are also intimidated by me. I have a nice face on my profile but when we meet up they are very taken aback and quiet. They don't enjoy being around me. That all changed when I met my girlfriend who is 5'10, but has been amazing to me.\n\nWe have been dating for almost a year and have only been able to penetrate her a few times. My penis is too big for her she says. I measured it at fully erect and I am bordering on nine inches when hard, a little less. The thickness is also an issue since I can only get myself \"in\" maybe an inch or two before she starts complaining.\n\nWe have settled into her giving me oral sex, which I do enjoy somewhat and but that she REALLY enjoys. She is very enthusiastic to put it mildly, and she also expects me to be as enthusiastic when I give her oral sex which I also dont like that much but I do it to make her happy.\n\nHowever as a man I have a deep desire to penetrate a woman, its just a natural feeling. And whenever I sort of lead things that way she rejects me. She has allowed me to rub against her and other things but thats it. \n\nNow everything has gone to a head and she has flat out told me that she does not want me to fuck her, and I am very angry and hurt. I realize that I am not a \"normal\" man and I don't want to hurt her, but I don't know if I can keep living like this and be happy. I don't enjoy blowjobs nearly as much as she does. I don't enjoy handjobs at all, I don't like rubbing against her vagina as its not the same and sort of emasculating.\n\ni also know that she has been penetrated by her smaller boyfriends, but she wont allow me due to my size, which also hurts.\n\nI still think there are other options for us to maybe try penetration, but i am angry that she has shut the door entirely. I am almost thinking about breaking up and trying to find someone else but i do love her.\n\nAITA for being angry that my gf wont try penetrative sex?\n"
},
{
"from": "gpt",
"value": "Solution: being angry at my gf for not wanting to have penetrative sex with me"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nThe input is a conversation between an automated system and a user looking for suggestions for pubs, restaurants and coffee shops in Cambridge. In the dialogue, the user may provide some criteria for the type of place they want such as price range, cuisine, etc. Similarly, the user may ask details of the place suggested by the system such as phone number, address, etc. Given such a dialogue, output a summary of the dialogue stating the criteria provided and details seeked by the user in this dialogue. The summary should strictly be in second person point of view. The summary should not contain any information that was not present in the conversation.\n\nSystem: 'Thank you for calling the Cambridge Information system. Your call will be recorded for research purposes. You may ask for information about a place to eat, such as a restaurant, a pub, or a cafe. How may I help you?'\nUser: 'im looking for a pub with an internet connection'\nSystem: 'The Bakers, which has an internet connection, is a great pub.'\nUser: 'what is the address and price range'\nSystem: 'The Bakers is located on 176 East Road. The price for main courses ranges from 6 pounds to 8 pounds 49 and the price for a cheapest pint of beer is 2 pounds 25.'\nUser: 'thank you goodbye'\n\nOutput:"
},
{
"from": "gpt",
"value": "You are looking for a pub and it should have an internet connection. You don't care about whether children are allowed. You want to know the address and price range."
}
] |
[
{
"from": "human",
"value": "In this task, you are given a hypothesis and an update. The hypothesis sentence is a statement that speaks of a socially normative behavior. In other words, it is a generalizing statement about how we expect people to behave in society. The update provides additional contexts about the situation that might UNDERMINE or SUPPORT the generalization. An undermining context provides a situation that weakens the hypothesis. A supporting context provides a situation that strengthens the generalization. Your task is to output 'strengthener' or 'weakener' if the update supports or undermines the hypothesis, respectively\n\nHypothesis: It's bad to damage someone's personal property.\nUpdate: You can't afford to replace it."
},
{
"from": "gpt",
"value": "strengthener"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given two sentences. Your task is to classify the given sentences as \"Yes\" if they have same meaning; otherwise, classify them as \"No\". \n\nSentence-1: They fired me years ago.',Sentence-2: \"I am still working at Macy 's .\"\nOutput:"
},
{
"from": "gpt",
"value": "No"
}
] |
[
{
"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.\nA piece of text from one of these 5 languages - French, English, Dutch, Somali, Tagalog is given. Generate the language to which the text belongs.\n\nText: Cheval de soins pour les enfants de 3 ans!\nSolution: French\nWhy? The given text is in French language\n\nNew input: Text: Bewaring van het gereconstitueerde product Voor de bewaarcondities van het geneesmiddel na reconstitutie, zie rubriek 6.3.Berekening van een individuele dosis De totale dosis op basis van het lichaamsoppervlak kan als volgt worden berekend: Totale dosis (mg) = dosis (mg/m2) x lichaamsoppervlak (m2) De volgende tabel is uitsluitend bedoeld als voorbeeld van hoe individuele doses azacitidine kunnen worden berekend op basis van een gemiddeld lichaamsoppervlak van 1,8 m2.\nSolution:"
},
{
"from": "gpt",
"value": "Dutch"
}
] |
[
{
"from": "human",
"value": "In this task you will be given a list of integers. You should remove all of the integers that are divisible by 3 from the list. If every integer in the input list is divisible by 3 then an empty list should be returned. Zero is divisible by 3.\nOne example: [2, 5, 9, 6, 11]\nSolution is here: [2, 5, 11]\nExplanation: 6 and 9 are removed from the list because they are divisible by 3.\n\nNow, solve this: [16, -88, 25, -99, 7, 5, 56, -45, 62, -75, -78]\nSolution:"
},
{
"from": "gpt",
"value": "[16, -88, 25, 7, 5, 56, 62]"
}
] |
[
{
"from": "human",
"value": "You are given a math word problem and you are supposed to apply addition or subtraction mathematical operators on the numbers embedded in the text to answer the following question and then only report the final numerical answer.\n\nExample Input: Scarlett made a fruit salad with 0.25 pound of melon and 0.375 pound of berries . How many pounds of fruit did Scarlett use in all ?\nExample Output: 0.625\n\nExample Input: There are 2 bananas in a pile on the desk . Each banana comes in a package of 13 . 7 bananas are added to the pile . How many bananas are there in the pile ?\nExample Output: 9\n\nExample Input: Sam had 9 dimes in his bank . His dad gave him 7 more dimes . How many dimes does Sam have now ?\nExample Output:"
},
{
"from": "gpt",
"value": "16\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you need to count the number of words in a sentence that end with the given letter. Answer with numbers and not words.\nQ: Sentence: 'several ingredients and tools for cooking sit on a counter'. How many words end with the letter 'r' in the sentence.\nA:"
},
{
"from": "gpt",
"value": "2"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given a sentence from the research paper and the category to which it belongs. Your task is to classify whether the given category is correct or not by providing \"True\" and \"False\", respectively. Here are the definitions for the categories: Background (Why is this problem important? What relevant works have been created before? What is still missing in the previous works? What are the high-level research questions? How might this help other research or researchers?), Purpose (What specific things do the researchers want to do? What specific knowledge do the researchers want to gain? What specific hypothesis do the researchers want to test?), Method (How did the researchers do the work or find what they sought? What are the procedures and steps of the research?), or Finding (What did the researchers find out? Did the proposed methods work? Did the thing behave as the researchers expected?). \",\n\nSentence: outbreaks in schools and in general populations. \n Section: finding\nOutput:"
},
{
"from": "gpt",
"value": "True"
}
] |
[
{
"from": "human",
"value": "Q: In this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about \"doctors\", you can talk about \"health\" or \"diagnosis\", but don't mention \"aliens\". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example: \"She likes cakes.\" is changed to \"She doesn't like cakes.\"\nBeginning: Sandy is Louie's mother. Middle: Louie wanted to honor his mother by visiting a beach. Ending: Louie walked across the sandy beach, lonely.\nA:"
},
{
"from": "gpt",
"value": "Louie wanted to honor his beach by visiting a mother."
}
] |
[
{
"from": "human",
"value": "You will be asked how to do a certain task. You should describe a physical process that does not lead to the asked outcome, yet it is closely related to it (i.e., it should use the words that are provided in the input). The physical process can be moving something, arranging something in a certain way, mixing things, shaking them, etc. To make sure that the generated process does not lead to the asked outcome, you can introduce objects or events unrelated to the context of the question e.g. 'cleaning the keyboard by making an elephant sit on them'; or you can create contradictory statements e.g. 'drying wet keyboards with running water'. In your responses, avoid typos and misspellings.\nOne example is below.\nQ: How do you remove keys from a computer keyboard for cleaning?\nA: Place the tip of your finger under the corner of a key and gently twist to pop it off.\nRationale: The answer is related to the question, but certainly doesn't lead to the asked outcome( A sharp narrow object should be used instead of finger.), so this is a correct answer.\nQ: Organize toddler's dolls.\nA:"
},
{
"from": "gpt",
"value": "Mount picnic basket on wall."
}
] |
[
{
"from": "human",
"value": "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.\n\nInput: Consider Input: Context: Thursday morning when I went to put my walking shoes on by the front door , I noticed several ants crawling around on the floor . Where did those come from ? I never had ants in here before . Since then I have been finding ants on the living room floor , and now in the kitchen .\n\nOutput: What 's a possible reason there were ants crawling around on the floor ?\n\n\nInput: Consider Input: Context: Knowing when to use a comma and when to use a semicolon does n't make you a fiction writer , but any fiction writer who thinks the difference between a comma and a semicolon is irrelevant / silly / beneath them is n't likely to be any good . All a writer has is words , and every punctuation mark , every pause , makes a difference . True , there are copy editors and proofreaders out there who can correct your grammar and punctuation , and occasionally one does run across a gifted fiction writer who looks like they could n't pass freshman comp .\n\nOutput: Based on this post , what may be my profession ?\n\n\nInput: Consider Input: Context: Or well , I was n't physically , but the room around me was . Where was I ? My ears felt like they were stuffed with cotton that was slowly slipping out . A loud echoing sound was trying to penetrate the thick wall .\n\n"
},
{
"from": "gpt",
"value": "Output: What may be the reason they are experiencing these symptoms ?\n\n\n"
}
] |
[
{
"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.\n\nQ: select the row whose year left record of all rows is minimum . the school record of this row is south central ( union mills ) .\n\nA: eq { hop { argmin { all_rows ; year left } ; school } ; south central ( union mills ) }\n****\nQ: select the row whose goals scored ( gf ) record of all rows is maximum . the team ( equipo ) record of this row is arabe unido .\n\nA: eq { hop { argmax { all_rows ; goals scored ( gf ) } ; team ( equipo ) } ; arabe unido }\n****\nQ: select the row whose first elected record of all rows is 3rd minimum . the incumbent record of this row is william huston natcher .\n\nA:"
},
{
"from": "gpt",
"value": "eq { hop { nth_argmin { all_rows ; first elected ; 3 } ; incumbent } ; william huston natcher }\n****\n"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you will be presented with a question, a word, and a POS tag. You have to determine whether the part-of-speech tag of the given word in the question is equal to the given POS tag or not. Give your answer with True or False. Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: Possessive pronoun, RB: Adverb, RBR: Adverb, comparative, RBS: Adverb, superlative, RP: Particle, SYM: Symbol, TO: to, UH: Interjection, VB: Verb, base form, VBD: Verb, past tense, VBG: Verb, gerund or present participle, VBN: Verb, past participle, VBP: Verb, non-3rd person singular present, VBZ: Verb, 3rd person singular present, WDT: Wh-determiner, WP: Wh-pronoun, WP$: Possessive wh-pronoun, WRB: Wh-adverb\nInput: What is the 2017 population of the city that is now in transition to become the country 's 32nd federal entity ? \n, Word: What \n, POS tag: TO\nOutput:"
},
{
"from": "gpt",
"value": "False"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given a text, write a compressed version of it in a single sentence.\nProblem:I love the story you told about Doug Flutie's daughter Alexa looking at Michael Jordan and Mia Hamm in that \"Anything You Can Do, I Can Do Better\" commercial and saying, \"Who's the guy with Mia?\"\nSolution:"
},
{
"from": "gpt",
"value": "I love the story about Doug Flutie's daughter looking at Michael Jordan and Mia Hamm in that \"Anything You Can Do, I Can Do Better\" commercial.\""
}
] |
[
{
"from": "human",
"value": "You will be given a person's personality, and a history of a conversation this person has had. You will be given four candidate sentences to complete the conversation, based on the context. Choose one and answer with the text.\n\nEx Input:\nPersonality: I got married last year.\nI live on a boat.\nI'm a hair stylist.\nI've my own salon.\nChat history: -Hi, how is your day going?\n -I'm doing good, and you how are you doing?\n -Good, just opened my salon waiting for customers.\n -Today, I'm taking my car to the mechanic.\n -I hope its nothing major that needs fixed!\n -Its my brake, and need fixing quickly, but before I need to go my job.\n -Good, what do you do for a living?\n -Waitress, at a hooters in new York.\nCandidates 1) Good to hear. I just got done shopping! Love the shops here in Ny. 2) I'm great how are you today? 3) The only think you can consider love, it my online shopping. 4) Cool! I live in Seattle in a boat house.\n\nEx Output:\nCool! I live in Seattle in a boat house.\n\n\nEx Input:\nPersonality: I own a custom upholstery shop.\nI love my grandchildren.\nI am a wife.\nI am a mother.\nChat history: -Hi there, my husband died and I really need to socialize.\n -Oh my, I'm so sorry to hear that dear.\n -To top it off my 6 brothers and sisters never bothered coming to the funeral.\n -Goodness gracious, that's awful to hear.\n -I even broke my arm two times the past three months.\n -Oh dear, seems like a dark cloud has become over you.\n -It sure has now that my 70 year old parents just got divorced.\n -Oh now that hits too close to home. Now I really feel for your pain.\n -Guess its about the right time to adopt a cat and become the cat lady.\n -That's what my husband said his last wife became.\n -No thank you. I can smell the litter box now and I'm sick. Yuck.\n -Well, a hamster is an option. That is what my grand kids own.\n -They are so bad about eating their own though. Its so disturbing.\nCandidates 1) I'm completely deaf but I love playing tennis. 2) I agree, when they aren't properly fed. I've not had that problem yet. 3) I'm from Florida. My grandson loves game of thrones though. 4) That's adventurous. What do you do for work?\n\nEx Output:\nI agree, when they aren't properly fed. I've not had that problem yet.\n\n\nEx Input:\nPersonality: I drive a mercedes.\nI have a sweet tooth.\nI m the middle child of 3 siblings.\nI m a babysitter.\nI m getting married in six months.\nChat history: -Hello, how are you doing today?\n -I'm good. Just making my cat some warm milk. You?\nCandidates 1) I'm good! Does your cat like sweet stuff? 2) Oh wow that is impressive. Must be an extremely difficult job. 3) Good. I am glad to hear it. What kind of job are you looking for? 4) I am well just chatting with my friends trying to see where too this weekend.\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "I'm good! Does your cat like sweet stuff?\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a sentence with a missing word that can be an object, a person, and/or an action. Fill in the blank with a plausible word. Although each sentence has many correct answers, you only have to write one answer.\n\nPersonX gets ___ of one"
},
{
"from": "gpt",
"value": "pictures"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given a post that is a real-life anecdote of a complex ethical situation and a question asks if AUTHOR, NOBODY, EVERYBODY, or OTHER is wrong in the situation. Answer the question and classify your answers into yes or no.\nQ: Is NOBODY wrong in the post ? POST : I (39m) have two boys, ages 3 and 5. The older while was diagnosed with autism and is definitely on the spectrum while the younger had some developmental delays and because of older brother's diagnosis we were able to get him diagnosed too so we could qualify him for services. It's now apparent that the younger is catching up and although he has some issues, he's becoming pretty typical for his age. \n\nIt was brought to my attention by my wife that I totally favor the older child. I was doing so without realizing it and the more I thought about it it's true. I regard my eldest as my precious first born that I would do anything for. I dote on him and help him through any tantrums he may have over his inflexibilities. I play with him and smile and laugh and truly enjoy my time with him. \n\nAs for my younger child I love him as my child but oftentimes I treat him the way I would treat someone else's kid. He's around, he's ok, but whatever. I sometimes feel like playing with him is a chore and I definitely don't enjoy it as much as when I play with my older one. I don't feel as close to him and when he tantrums over something dumb that a typical 3 yr old tantrums over I just let him tantrum and cry it out. Sometimes I can't stand him and try to avoid him. \n\nI really feel like an asshole because I know I favor the eldest and I feel like I don't even want to try to like the younger one more. I feel like I'm a good dad to both but the younger one is definitely getting the short end of the stick. To top it off everyone says the younger one has my personality and is totally like me while the eldest that I favor is very much like my wife. \n\nAny parents out there have any advice or thoughts? How much of an asshole am I?\nA:"
},
{
"from": "gpt",
"value": "no"
}
] |
[
{
"from": "human",
"value": "Given a part of privacy policy text, identify the purpose for which the user information is collected/used. The purpose should be given inside the policy text, answer as 'Not Specified' otherwise\n\nA user with an account can make no specified choices about the use of generic personal information by a third party, which collects or receives it for an unspecified purpose."
},
{
"from": "gpt",
"value": "Unspecified"
}
] |
[
{
"from": "human",
"value": "You will be given two pieces of text with the same meaning. One of them is simpler and easier to understand for non-native English speakers. Complex texts may contain more difficult words, have unnecessary phrases or contain long sentences. Your task is to choose the simpler piece of text. You are expected to output 'Text one' if the first sentence is simpler. Otherwise output 'Text two'.\n\nText one: Awake is a 2007 suspense thriller written and directed by Joby Harold.\n Text two: Awake is a scary movie from 2007.\nText two\n\nText one: The San Antonio Spurs are an American professional basketball team based in San Antonio, Texas.\n Text two: The San Antonio Spurs are an American professional basketball team. They are in San Antonio, Texas.\nText two\n\nText one: Stefan Nemanja starts his rule over Serbia.\n Text two: Stefan Nemanja starts his rule over Serbia.\n"
},
{
"from": "gpt",
"value": "Text one\n\n"
}
] |
[
{
"from": "human",
"value": "Generate an appropriate single-sentence summary for the given text such that it includes the main topic of the text.\nExample: By Marianna SpringSpecialist disinformation reporter, BBC News The adverts show the Democratic Party challenger with an earpiece, and say that he refused to have his ears checked for devices prior to the debate. The Biden campaign rejected the claims. The Trump campaign adverts ask: \"Why won't Sleepy Joe commit to an ear test?\" and \"Who is in Joe's ear?\" Accusations that presidential candidates have received debate help via hidden hearing devices are familiar, albeit unproven. Such allegations have been levelled against both Republican and Democratic candidates in the past. Prior to Tuesday's debate, the rumour about Mr Biden's supposed earpiece was circulating on several social networks, and was being promoted by the Trump campaign. At least 15 versions The advertising campaign was launched after the debate, and also promotes two other baseless but widely shared rumours about Mr Biden. One suggested he asked for breaks during the debate, and another accused him of refusing a \"drug test\". The photo featured in the advert is not from Tuesday's debate. It was first shared online in September 2019. In a number of the adverts, it has been doctored to show Mr Biden wearing wireless Apple headphones. This was not the case in the original image. Some versions circle the ear featuring the headphone. By Wednesday evening, there were at least 15 different versions of the advert, and according to Facebook's Ad Library, they had reached at least 10 million users. Facebook has pledged to label posts containing voting misinformation and point users towards accurate information ahead of the election. However its policy does not involve fact-checking political speech, including in advertisements. The company declined to comment about the latest Trump ad campaign. Rumour origins Hours before the debate, the claims went viral on Facebook and YouTube. Identical memes were pushed by a number of popular Facebook pages with names such as US Conservative and Unhinged Left. They claimed \"Joe Biden should be inspected for a hidden earpiece as well as submit to a drug test before the debate\". These memes are subject to fact-checks - and some have had warning labels applied to them on Facebook. The claims were picked up by Fox News and other conservative news outlets. They were further amplified by supporters of QAnon, an unfounded a conspiracy theory that claims President Trump is fighting a secret war against elite Satan-worshipping paedophiles. Those who believe in QAnon are known for promoting political disinformation on social media which targets opponents of the president. They shared close-up pictures of Mr Biden's ears, alleging a listening device was visible. During the debate, some also shared photos of a fold in Mr Biden's shirt, claiming it was caused by a wire, and of a supposed device on his wrist, where he wears a rosary in memory of his late son Beau. Nothing new Conspiracy theories about secret listening devices have been recycled in presidential election campaigns for the past two decades. Democratic candidate Hillary Clinton faced similar unfounded claims ahead of the 2016 presidential election. In 2004, rumours circulated among left-wing sites and blogs that President George W Bush was being aided by a secret earpiece. None of those allegations were found to be true. Even if a candidate did wear an earpiece, any advantage would be questionable. As TV and radio presenters can attest, listening to someone while simultaneously talking during the back-and-forth of a live event is a difficult skill to master.\nExample solution: US President Donald Trump's re-election campaign is running hundreds of Facebook advertisements pushing an unfounded conspiracy theory that Joe Biden cheated during the first US presidential debate.\nExample explanation: This is a relevant summary for the given paragraph. It also contains explicit phrases from the given text\n\nProblem: By Barbara Plett UsherBBC News What's changed under Trump? The threat perception: The Americans believe that Pyongyang already has the technology to fire nuclear warheads at Japan and South Korea. And they calculate that it will likely be able to hit the United States within a few years. So North Korea is now seen as a threat to US national security, not only a menace to regional allies. Hence the sense of urgency and resolve. The rhetoric: Military options have always \"been on the table\", sometimes more actively than others. But rarely if ever has a US administration been as blunt or outspoken about it. That is largely a factor of President Trump's style but it's also due to growing concern about the imminence of the threat. The military posturing: Spring is usually a tense time in the Korean Peninsula, because North Korea celebrates a number of patriotic anniversaries that can serve as launch pads for weapons tests, and the US conducts military exercises with Seoul. But this year the Trump administration added to the firepower on display, including a submarine equipped with guided missiles, and an aircraft carrier group. The confusion over the deployment of the latter, however, may have detracted somewhat from its deterrent effect. North Korea: Pyongyang has long held that it needs nuclear weapons to guarantee its security, and has been ready to face down international censure and punishment. But Kim Jong Un has shown particular determination and, unlike his father and grandfather, a disregard for the views of his only major ally, China. \"Kim Jong Il for all of his sins at least cared what other people thought and particularly cared what the Chinese thought,\" the former US negotiator Chris Hill told the BBC. \"His son Kim Jung Un doesn't seem to care what anyone thinks.\" China: China is exasperated by its recalcitrant ally and worried about the growing sophistication of its weapons. It had already begun tightening its implementation of sanctions by following through with the UN's recent ban on coal imports. But it's probably even more worried that Trump's military posturing will escalate tensions, and uneasy about his insistence that Beijing is uniquely positioned to squeeze Pyongyang. In an apparent response to US pressure, Chinese newspapers have published tougher statements about North Korea. There's also been closer coordination between Beijing and Washington. The Secretary of State Rex Tillerson says Beijing has threatened Pyongyang with unilateral sanctions if it carries out a sixth nuclear test. What hasn't changed The options: There are still no good ones. Tillerson says denuclearisation would still be the goal, but he has not been precise about conditions for starting talks. The strategy: Actually, it has sort of changed and sort of hasn't. The administration says it has. But the components - pressing for tighter economic sanctions, urging China to lean on its neighbour, and waiting for North Korea to buckle - look a lot like Barack Obama's \"strategic patience\". The difference seems to be less patience, a more credible threat of military force, and more coercive diplomacy. Tillerson says the knob on the pressure campaign is at \"five or six\" right now, with the US \"testing\" Beijing's ability to influence North Korea, and threatening to sanction parties that violate the UN embargo. Alongside China, the Trump administration is also trying to convince South East Asian nations to isolate North Korea. China: China may be more willing to turn the screws on Pyongyang, but only so far. There is no sign that it has changed its calculation of North Korea as a buffer state. Beijing fears that if the regime collapses the American security umbrella will be extended across the peninsula right to its borders. And while North Korea is a dangerous headache, America is its biggest strategic rival. Tillerson's recent assurance that the US is not seeking regime change was aimed as much at Beijing as it was at Pyongyang. The wild card: Even with a nuclear rogue state, President Trump likes to be unpredictable. And his tactics are those of a deal maker. Nevertheless observers are struggling to interpret the contrast between his hardline rhetoric and his recent suggestion of a meeting with Kim Jong Un - under the \"right circumstances\" . Barack Obama also said during the 2008 election campaign he'd be willing to meet the North Korean leader. But he did not go on to praise his adversary as did Trump, calling him a \"smart cookie\" for holding onto power by wiping out his rivals. It's not clear if the president was deliberately dangling a carrot, making another overture among several to a strongman, or simply throwing an offhand comment into the mix.\n"
},
{
"from": "gpt",
"value": "Solution: After weeks of tough talk and escalating tensions between the US and North Korea, President Donald Trump has referred to the possibility of meeting his opposite number, Kim Jong Un. Let's take a step back and look at how we got here."
}
] |
[
{
"from": "human",
"value": "Teacher: In this task, you're given four sentences of a story written in natural language in which one part is missing. Your job is to predict the position and missing part of the story and return in the following format: position, missing part. The missing part is a sentence that completes the story, and the position is the number of the missing sentence in the new story.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nSentence1: Rick grew up in a troubled household. Sentence2: He never found good support in family, and turned to gangs. Sentence3: It wasn't long before Rick got shot in a robbery. Sentence4: He is happy now.\nSolution: 4, The incident caused him to turn a new leaf.\nReason: As mentioned in fourth sentence, he is happy now; so, the incident turned a new leaf to Rick's life.\n\nNow, solve this instance: Sentence1: Herman was very hungry but had no money. Sentence2: So he searched all over his house for spare change. Sentence3: He found a quarter under the couch and a dollar in his dresser. Sentence4: Herman managed to buy some food to make a small meal.\nStudent:"
},
{
"from": "gpt",
"value": "4, Herman came up with two dollars and walked to the store."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.