Split (1)

train · 8.3M rows

Search is not available for this dataset

conversations listlengths 2 2
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a question, along with a context passage. The passage will not have a direct answer to the question, but can include some information and a clue for the answer. Assuming you can only obtain information about one entity in the passage, your job is to determine whether information from the passage can be used to answer the question. Indicate your choice as `a` for Yes or `b` for No.\nQ: Question: Which TLC studio album made between 1999 and 2002 sold more copies? Passage:The Very Best of TLC: Crazy Sexy Hits material is taken from four of their studio albums: Ooooooohhh... On the TLC Tip (1992), CrazySexyCool (1994), FanMail (1999), and 3D (2002), and Now & Forever: The Hits (2003), which were all recorded from 1991 to 2003. Their 1993 cover of The Time's \"Get It Up\" for the soundtrack to Poetic Justice does not appear on any of their studio albums, but still appears on the compilation along with the trio's most successful singles in the United Kingdom. These include \"No Scrubs\", which placed at number three on the UK Singles Chart and was awarded a platinum certification from the British Phonographic Industry (BPI); \"Waterfalls\", which peaked at number four on the UK Singles Chart and also achieved platinum status; \"Unpretty\", a silver-certificated single which peaked at number six on the UK Singles Chart, and \"Creep\", which also peaked at number six on the UK Singles Chart after being reissued across the UK and Europe. It did not, however, include \"Dear Lie\", a moderately received UK single which was certified silver. Instead, the non-charting songs \"Come Get Some\", \"Damaged\" and \"Get It Up\" were included in the final track listing, with \"Whoop De Woo\" (a non-album track) and \"In Your Arms Tonight\" (from 3D) the only two non-single tracks that appeared the compilation.\n\nA:" }, { "from": "gpt", "value": "b" } ]
[ { "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 will be given a list of numbers and you need to find the mean (average) of that list. The mean of a list can be found by summing every number in the list then dividing the result by the size of that list. The output should be rounded to 3 decimal places.\n\n[1,3,5]\nSolution: 3.000\nWhy? The mean of the input list is (1+3+5)/3, which equals 3. This is a good example.\n\nNew input: [105.656, 162.482, 9.618, 180.797, 27.572, 157.868, 224.435]\nSolution:" }, { "from": "gpt", "value": "124.061" } ]
[ { "from": "human", "value": "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.\nExample: [-83, 53, -48, 8]\nExample solution: [-80, 50, -50, 10]\nExample explanation: The output correctly rounds each integer in the input list to the nearest ten. So this is a good example.\n\nProblem: [380, 272, -744, 640, -106, -922, 594, 837, 561, -488, -864, -973, -719, 401, -251]\n" }, { "from": "gpt", "value": "Solution: [380, 270, -740, 640, -110, -920, 590, 840, 560, -490, -860, -970, -720, 400, -250]" } ]
[ { "from": "human", "value": "Teacher:In this task you are expected to fix an SQL query based on feedback. You will be given an SQL statement and an English description with what is wrong about that SQL statement. You must correct the SQL statement based off of the feedback. An SQL query works by selecting data from a table where certain conditions apply. A table contains columns where every row in that table must have a value for each column. Every table has a primary key that uniquely identifies each row, usually an id. To choose which columns are returned you specify that after the \"SELECT\" statement. Next, you use a \"FROM\" statement to specify what tables you want to select the data from. When you specify a table you can rename it with the \"AS\" statement. You can reference that table by whatever name follows the \"AS\" statement. If you want to select data from multiple tables you need to use the \"JOIN\" statement. This will join the tables together by pairing a row in one table with every row in the other table (Cartesian Product). To limit the number of rows returned you should use the \"ON\" statement. This will only return rows where the condition specified after the statement is true, this is usually an equals operator with primary keys. You can also use the \"WHERE\" statement to specify that only rows with column values statisfying a certain condition, should be returned. The \"GROUP BY\" statement will group rows together that have equal column values for whatever columns follows the statement. The \"HAVING\" statement will return groups that statisfy whatever condition follows the statement. Any column(s) being returned from grouped rows must either be an aggregate function, (AVG, MAX, COUNT, SUM, ...) of a column, or the column(s) that the data was grouped by. To sort the returned data you can use the \"ORDER BY\" command which will order the data by whatever aggregate function or column follows the statement. The \"DESC\" statement will sort in descending order and the \"ASC\" statement will sort in ascending order. Finally, you can use the \"LIMIT\" statement to return a certain number of rows. When \"\" is used in an SQL statement every column is returned. For example, SELECT FROM table WHERE attribute = 1, will select every column from rows with the attribute column equal to 1. \nTeacher: Now, understand the problem? Solve this instance: SQL: SELECT T1.date_of_latest_logon , T3.test_result FROM Students AS T1 JOIN Student_Course_Enrolment AS T2 ON T1.student_id = T2.student_id JOIN Student_Tests_Taken AS T3 ON T2.registration_id = T3.registration_id\nFeedback: date of enrolment , date of completion should be used instead of date of latest logon , test result .\nStudent:" }, { "from": "gpt", "value": "SELECT date_of_enrolment , date_of_completion FROM Student_Course_Enrolment" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nGiven a category and a set of five words, find the word from the set that does not belong (i.e. is the least relevant) with the other words in the category. Words are separated by commas.\nExample: Category: construction \nWords: excavator, crane, pelican, hoist, upraise\nOutput: pelican\nA pelican is not related to construction because it is a type of bird.\n\nNew input case for you: Category: moral characteristic \nWords: just, alright, fair, honorable, sunny\nOutput:" }, { "from": "gpt", "value": "sunny" } ]
[ { "from": "human", "value": "In this task, you are given an answer, and your task is to generate a reasonable question for that answer.\n\nLet me give you an example: My stomach will be upset if i eat that.\nThe answer to this example can be: Do you like pineapple on your pizza?\nHere is why: The answer given was regarding something that the person ate and it caused his stomach upset. The question asked was if that person likes pineapple on pizza. Based on the given answer, the question was predicted correctly.\n\nOK. solve this:\nI've jumped around a bit.\nAnswer:" }, { "from": "gpt", "value": "Have you always worked in this field?" } ]
[ { "from": "human", "value": "You are given a password and you need to generate the number of steps required to convert the given password to a strong password. A password is considered strong if (a) it has at least 6 characters and at most 20 characters; (b) it contains at least one lowercase letter and one uppercase letter, and at least one digit; (c) it does not contain three repeating characters in a row. In one step you can: (1) Insert one character to password, (2) delete one character from password, or (3) replace one character of password with another character.\nOne example: password = a\nSolution is here: 5\nExplanation: Using 5 steps, it can become a strong password\n\nNow, solve this: password = r2Cy0urDGVsm8o7p\nSolution:" }, { "from": "gpt", "value": "0" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are presented with a term, a question, and a yes/no answer. For context, the term is associated with a short description. Write the simple facts one needs to know in order to answer the given question. The facts should be easily found on the web (e.g. mentioned in a Wikipedia page)\nProblem:Term: Goat, Description: domesticated mammal raised primarily for its milk, Question: Are people better climbers than goats?, Answer:No\nSolution:" }, { "from": "gpt", "value": "Fact1: Ibex are goats that can climb unassisted up walls that are nearly at 90 degree angles. Fact2: Hooves are extremely advantageous for climbing. " } ]
[ { "from": "human", "value": "Teacher:In this task, you're given a review from Amazon and category of the product based on the review given by the user and your task is classify whether the given category match the review. Generate \"True\" if given review and its category match, otherwise generate \"False\".\nTeacher: Now, understand the problem? Solve this instance: Reviews: Seller sent us a wet faucet in box. Item is scratched and obviously used, even came with rust on the side and damaged rubber gaskets. Thank you for shipping us someone elses returned item. Instruction pages were also soggy. What a wonderful wet mess of a surprise. Next time just ship us a box of black mold too. \n Category: automotive\nStudent:" }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task, you are given an input list A. If the count of numbers is more than that of alphabets in the list, answer 'Numbers Win'. If the count of alphabets is more than that of numbers in the list, answer 'Alphabets Win'. If the count of numbers is same as that of alphabets in the list, answer 'Numbers and Alphabets are Tied'.\nPROBLEM: ['1611', 'd', '3615', '9743', '1089', 'g', '7931', '4439']\n\nSOLUTION: Numbers Win\n\nPROBLEM: ['d', 'p', '3551', '863', '3757', '641', 'L', 'e', '4147', '849', '3731', '2587', 'i', 'B', 'U', '3881', '5129', '2409', '6795', '7943', '4623', '6251', 'c', '7739', 'i', 'W', '2189', 'x', 'm', 'z', 'v', 'k', '4553', 'r', '763', 'A', 'I', '3229', '5951', '3009', '2907', 't', 'm', 'n', '853', 'Y']\n\nSOLUTION: Numbers Win\n\nPROBLEM: ['h', 'w', 'u', '5195', '6715', '361', '497', 'L', 'O', '7135', '3623', 'U', 'f', 'W', '9087', 'V', 'i', '365', 'g', '1583', 'm', '9077', '6353', 'w', '5913', '3995', '969', 'R', 'L', 'R', '8533', 'A', 'n', 'P', 'W', 'X', 'X', '9671', '7159', 'k']\n\nSOLUTION:" }, { "from": "gpt", "value": "Alphabets Win\n\n" } ]
[ { "from": "human", "value": "Teacher:Given a category and a set of five words, find the word from the set that does not belong (i.e. is the least relevant) with the other words in the category. Words are separated by commas.\nTeacher: Now, understand the problem? Solve this instance: Category: type of sandwich \nWords: blt, bar, dagwood, hoagie, club\nStudent:" }, { "from": "gpt", "value": "bar" } ]
[ { "from": "human", "value": "Teacher:In this task you will be given a list of dictionaries. A dictionary is a set of key-value pairs, where each key is unique and has a value associated with that key. You should sort the list of dictionaries from smallest to largest by their 'first' key. If there is two dictionaries with the same 'first' value then sort them by their 'second' key. Negative numbers should come before positive numbers.\nTeacher: Now, understand the problem? Solve this instance: [{'first': -82, 'second': -23}, {'first': 67, 'second': 92}, {'first': -75, 'second': 0}, {'first': -35, 'second': 56}, {'first': 91, 'second': 28}]\nStudent:" }, { "from": "gpt", "value": "[{'first': -82, 'second': -23}, {'first': -75, 'second': 0}, {'first': -35, 'second': 56}, {'first': 67, 'second': 92}, {'first': 91, 'second': 28}]" } ]
[ { "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\nLet me give you an example: Hypothesis: You should help your family with funeral expenses.\nUpdate: They have asked you to chip in\nThe answer to this example can be: strengthener\nHere is why: If your family has asked you to chip in for the funeral expenses, you should help them.\n\nOK. solve this:\nHypothesis: It is reasonable for someone to want to go to their parent's funeral.\nUpdate: Their parent is being buried in an active war zone.\nAnswer:" }, { "from": "gpt", "value": "weakener" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given two natural language statements with similar wording. You must choose the statement that makes less sense based on common sense knowledge. A '\n' separates the statements. Use \"first\" or \"second\" to indicate which sentence makes less sense.\nQ: a traveler keep his clothes in a suitcase\na traveler keep his clothes in a bowl\nA:" }, { "from": "gpt", "value": "second" } ]
[ { "from": "human", "value": "In this task you will be given two dialogues. You need to determine if both dialogues have the same underlying emotion. The possible emotions are happy, sad, angry, or other. If they do output 'yes', if not output 'no'.\n\nDialogue 1: 'send your picpoutingfacepoutingface ill send one like it send your pic'. Dialogue 2: 'its just the name the villages are a beautiful place d its a township society'." }, { "from": "gpt", "value": "yes" } ]
[ { "from": "human", "value": "In this task, you're given a statement, the genre to which that statement belongs, and a label indicating if the statement should be agreed with (entailment), disagreed with (contradiction), or neither (neutral). Your job is to write a sentence that describes the genre that follows the tone with respect to the statement, as indicated by the label. If sentence X agrees with sentence Y, the can be concluded from one another. If sentence X disagrees with sentence Y, they can not be correct at the same time. The sentence must also belong to the genre specified.\nQ: Statement: The waterfront Riva degli Schiavoni (Quay of the Slavs) begins at the Ducal Palace, named after the Dalmatian merchants who unloaded their goods here.\nLabel: contradiction.\nGenre: travel.\nA: " }, { "from": "gpt", "value": "The palace was named after the royal family that lived there." } ]
[ { "from": "human", "value": "This task is to identify the language of a sentence correctly by classifying if it is English or Telugu\nQ: 5. Max panel width: 1010mm\nA: " }, { "from": "gpt", "value": "English" } ]
[ { "from": "human", "value": "Teacher: You will be given a context and a verb separated with a newline character. You have to identify if the given verb implies an opinion, an intention, a wish or not. Please note that a verb refers to an intention only if it refers to an event planned to happen in the future and is not conditional (or part of a condition). The output should be: 'Yes' if the verb refers to an opinion, an intention, or a wish; and 'No' otherwise.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nIt was followed by Denmark, Norway, Germany, France, Greece, Luxembourg, Spain, Britain, the United States, Iceland, Belgium, Italy, Portugal and Turkey. NATO decided at last year's Madrid summit to (invite) the three eastern European countries to start accession talks. \n Verb: invite\nSolution: Yes\nReason: They planned to \"invite\" the three eastern European countries, so this verb refers to an intention.\n\nNow, solve this instance: Elian's young stepmother, Nelsy, flanked by his two grandmothers, was at the head of the March of the Combatant Mothers, pushing his half-brother in a stroller. Cuban authorities (estimated) that 100,000 women participated in the march. \n Verb: estimated\nStudent:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "Teacher:In this task, you are given a post in English from online platforms. You are expected to identify whether the post is hateful against immigrants and women. A hateful post expresses hate or encourages violence towards a person or a group. If a post is hateful but not towards immigrants and women, it should be labeled as non-hateful. Answer \"hateful\" or \"Non-hateful\". Note that the URLs in the text have been replaced with [Link].\nTeacher: Now, understand the problem? Solve this instance: Post: @HanSimpkin Wait till you've got gin tomorrow you won't have it then cock\nStudent:" }, { "from": "gpt", "value": "Non-hateful" } ]
[ { "from": "human", "value": "Definition: Given a command in a limited form of natural language, provide the correct sequence of actions that executes the command to thus navigate an agent in its environment. A command can be broken down into many different actions. Actions are uppercase and are individual steps that serve as the building blocks for a command. For commands, 'left' and 'right' are used to denote the direction of an action. The word 'opposite' turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. Actions and commands do not have quotations in the input and output.\nInput: turn opposite right thrice after turn opposite right twice\nOutput:" }, { "from": "gpt", "value": "I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT" } ]
[ { "from": "human", "value": "instruction:\nGiven a concept word, generate a hypernym for it. A hypernym is a superordinate, i.e. a word with a broad meaning constituting a category, that generalizes another word. For example, color is a hypernym of red.\nquestion:\ninstrument\nanswer:\ndevice\n\n\nquestion:\nlanguage\nanswer:\ncommunication\n\n\nquestion:\nshoot\nanswer:\n" }, { "from": "gpt", "value": "hit\n\n\n" } ]
[ { "from": "human", "value": "Teacher:In this task, you are given a review of a movie and a boolean question whether this review has positive sentiment or negative sentiment. Your task is to generate answer \"yes\" when the tweet has that particular sentiment, otherwise generate answer \"no\".\nTeacher: Now, understand the problem? Solve this instance: Review: When I saw this film on FearNet, I thought it would be a scary movie. Apparently, it wasn't. I have no clue how this movie was allowed to be featured on that site. FearNet is a site that shows scary horror movies.The acting is wonderful from all the actors. I hated the story. The story was stupid. The movie starts out with a man with a scroll with a signia stamped onto it. He breaks the seal and certain disasters happen. The water turns to blood, the oceans die out, the moon turns red, etc. The female character was annoying as well. A lot of the stuff she did didn't make sense. Like when she sees a piece of paper with a date on it. Coincidentally, it's the date she's expected to give birth to her baby and she starts freaking out about it and starts researching it and asking religious people what it all means.Spoiler Alert The two worst things happened in this movie are the execution of a mentally retarded man who claimed that God told him to murder his parents and the end where Demi Moore dies after giving birth to her baby and transferring her soul into it.Here's what happens. The mentally retarded person gets shot and killed and the apocalypse begins. Demi Moore gets into a hospital in the middle of a massive earthquake and gives birth to her child. She touches her child's head, transferring her soul into the child and then dies. Then, the apocalypse stops.Why does God all of a sudden have a change of heart? He gets furious when the Governor allows the execution of a mentally retarded man then he's all about forgiveness once a lone woman transfers her soul into her baby? End Spoiler The movie is pretty stupid. It's another religious end of the world propaganda piece. The acting from Demi Moore and Michael Biehn and everybody else is excellent. That's about all there is.I give this movie 2 stars out of 10. Good acting with a lot of nonsense! Question: is it a negative review?\nStudent:" }, { "from": "gpt", "value": "yes" } ]
[ { "from": "human", "value": "In this task, you're given a statement, and three sentences as choices. Your job is to determine which sentence clearly disagrees with the statement. Indicate your answer as '1', '2', or '3' corresponding to the choice number of the selected sentence.\n\nExample input: Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.\nExample output: 3\nExample explanation: It is said in the statement that the candy doesn't melt in your hand, but the sentence in choice 3 disagrees with it.\nQ: Statement: He thought the facts had been misrepresented. Choices: 1. He wasn't sure if the facts were really facts. 2. He suspected that the facts hadn't been presented clearly. 3. The facts were represented concisely and truthfully.\nA:" }, { "from": "gpt", "value": "3" } ]
[ { "from": "human", "value": "In this task, you are given a sentence which contains a motion and your task is to identify the physical entities involved in the motion. The input sentence can have more than one entity and also there is at least one entity that takes part in physical motion. There are two types of entities which are animate (beings that are alive) and inanimate entities (beings that are not alive).\nOne example is below.\nQ: Mr. Miller waved his hands in a gesture of divine despair, spun round, darted up the aisle, turned, and bounded back.\nA: Mr. Miller, hands\nRationale: In this sentence, the female is performing a motion on the liquids. So the answer should be Yes. Mr. Miller is the animate entity who is taking part in a motion where he is performing various actions like moving his hands around. The hands are the inanimate entity on which a motion is performed. This is the example where multiple entities are involved and are separated by commas.\nQ: Several individuals play against each other in a table football match.\nA:" }, { "from": "gpt", "value": "individuals" } ]
[ { "from": "human", "value": "In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the count of all the numerical elements in the given list. Return 0 if no numerical element in the list.\nQ: ['6261', 'I', '3289', '8955', '5463', 't', '7809', 'M', 'e', '4499', '3783', 'a', 'V', 'y', 'X', '9485', 'V', '3361', 'K', 'v', '7401', '9977', 'V']\nA: " }, { "from": "gpt", "value": "11" } ]
[ { "from": "human", "value": "In this task, you are given two strings A,B. Find the longer of the two lists, convert it to lowercase, and return all the unique alphabets used in it. The two input strings are never equal.\n\nvHijkETzyIUUsGWPrxFdijtHGXAwPUXNshdmvuqe, jEMVUZTbNRVRknUUsGWPrxFdijtHGjwAoBIF" }, { "from": "gpt", "value": "a, d, e, f, g, h, i, j, k, m, n, p, q, r, s, t, u, v, w, x, y, z" } ]
[ { "from": "human", "value": "Teacher: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. \nTeacher: Now, understand the problem? Solve this instance: My dog craves these...one each morning. She's never had digestive problems with them, unlike the beef rawhide bones which we wont give her. WE couldnt find them suddenly in any of the stores and i was soooo delighted Amazon had them! Right to my door quick! thank you amazon!\nStudent:" }, { "from": "gpt", "value": "5" } ]
[ { "from": "human", "value": "Instructions: In this task, you're given a pair of sentences, sentence 1 and sentence 2. Sentence 2 contradicts sentence 1. Your job is to alter sentence 2 so that the pair neither agree nor contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\nInput: Sentence 1: An elderly man with a mustache sits on a wooden stool next to colorful sport merchandise. Sentence 2: An elderly man is sitting next to a pile of pandas.\nOutput:" }, { "from": "gpt", "value": "An elderly man is selling colorful merchandise." } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. 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\nhow popular is The Beat That My Heart Skipped?\n" }, { "from": "gpt", "value": "famous" } ]
[ { "from": "human", "value": "In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: sexual-explicit and non-sexual-explicit. A comment is considered sexual-explicit if it explicitly portrays sexual matters.\nExample: Comment: President lied under oath about consensual sex...\nNot the same thing as rape.\nExample solution: Sexual-explicit\nExample explanation: This comment explicitly mentions \"consensual sex\" and \"rape\", and thus is sexual-explicit.\n\nProblem: Comment: Nobody will ever be able to match former Republican speaker of the House, Dennis Hastert, who raped repeatedly a teenage boy that grew up and stalked Hastert for well over $1 million in blackmail money. Hastert was two seat away from the presidency. The Republican insiders had to have known about the closet homosexual/rapist. And the guy never was brought to trial for raping a teenage boy.\n" }, { "from": "gpt", "value": "Solution: Sexual-explicit" } ]
[ { "from": "human", "value": "This 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.\nQ: Passage: There are many established music festivals in Alaska, including the Alaska Folk Festival, the Fairbanks Summer Arts Festival, the Anchorage Folk Festival, the Athabascan Old-Time Fiddling Festival, the Sitka Jazz Festival, and the Sitka Summer Music Festival. The most prominent orchestra in Alaska is the Anchorage Symphony Orchestra, though the Fairbanks Symphony Orchestra and Juneau Symphony are also notable. The Anchorage Opera is currently the state's only professional opera company, though there are several volunteer and semi-professional organizations in the state as well.\nA: " }, { "from": "gpt", "value": "What isn't Alaska's most prominent orchestra?" } ]
[ { "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 facts, and a multiple-choice question. Based on the given facts, answer the question with index of the correct option (e.g, \"A\").\n\nFact1: a plant requires sunlight to grow, Fact2: Plants to avoid are fast-growing vines that can take over an area in no time., Question: What requires sunlight in order to take over an area? (A) spores (B) fish (C) plants (D) humans (E) pods (F) Oak (G) opossums (H) coral\nSolution: C\nWhy? This is a good example. Based on the facts plants require sunlight in order to take over an area.\n\nNew input: Fact1: rain causes erosion, Fact2: Erosion is the breaking apart and moving of rocks and soil., Question: Rain causes the breaking apart and moving of rocks and what? (A) abrasion (B) soil (C) sand (D) reservoirs (E) earth (F) broken (G) ground (H) Roads\nSolution:" }, { "from": "gpt", "value": "B" } ]
[ { "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.\nGenerate an overlapping word between the given two sentences. When you find the overlapping words, they don't have to match exactly, e.g., \"survival\" and \"survive\" are valid overlapping words. Little words like \"the\" or \"of\" don't count! You must generate significant words which are not the stop words.\n\nSentence1: pesticides cause pollution. \nSentence2: pollution can harm animals.\nSolution: pollution.\nWhy? The word \"pollution\" is common to Sentence1 and Sentence2. So, it's a good answer.\n\nNew input: Sentence1: Active immunity results when an immune response to a pathogen produces memory cells. \nSentence2: Pathogens are germs that cause disease.\nSolution:" }, { "from": "gpt", "value": "pathogen" } ]
[ { "from": "human", "value": "In this task, you are given triplets. Each triplet is in the form of [subject, predicate, object]. Your task is to generate proper sentence that utilizes these triples. The objective is to construct a sentence that (a) captures the facts specified in the triples and (b) is a well-formed sentence easily understandable by a human. All triple values need not be used directly in the sentence as long as the facts are adequately captured.\nOne example is below.\nQ: [['Northwestern College', 'NICKNAME', 'Red Raiders'], ['Northwestern College', 'LOCATION', 'Orange City, Iowa']]\nA: The team whose nickname is red raiders is located in the orange city, iowa\nRationale: This sentence uses the triplets by correctly using the (subject, predicate, object) semantics for both the triplets provided. Since college teams are popularly associated with nicknames, some information in the generated sentence can be inferred. In this case, Northwestern College was replaced with the team automatically.\nQ: [['The Mill', 'eatType', 'pub'], ['The Mill', 'food', 'Italian'], ['The Mill', 'area', 'riverside']]\nA:" }, { "from": "gpt", "value": "The Mill is a high-end Italian pub in riverside." } ]
[ { "from": "human", "value": "Adverse drug reactions are appreciably harmful or unpleasant reactions resulting from an intervention related to the use of medical products, which predicts hazard from future administration and warrants prevention or specific treatment, or alteration of the dosage regimen, or withdrawal of the product. Given medical case reports extracted from MEDLINE, the task is to classify whether the case report mentions the presence of any adverse drug reaction. Classify your answers into non-adverse drug event and adverse drug event.\n\nExample Input: We report a case of a patient with rheumatoid arthritis treated with low-dose methotrexate (15 mg/week) who developed infection with both M. tuberculosis and M. chelonae after the revision of a prosthetic hip.\nExample Output: adverse drug event\n\nExample Input: Thiopurine methyltransferase deficiency occurs at a frequency of one in 300 and is associated with profound myelosuppression after a short course of azathioprine.\nExample Output: adverse drug event\n\nExample Input: A 64 year old woman with previous history of coronary stenting five days before was admitted in our institution for intracranial bleeding while receiving aspirin and clopidogrel.\nExample Output:" }, { "from": "gpt", "value": "adverse drug event\n\n" } ]
[ { "from": "human", "value": "In this task, you are given a context, a subject, a relation, and many options. Based on the context, from the options select the object entity that has the given relation with the subject. Answer with text (not indexes).\n\nExample input: Context: Joanne McLeod is a Canadian figure skating coach. She is the skating director at the Champs International Skating Centre of BC (formerly known as the BC Centre of Excellence). Here current and former students include Emanuel Sandhu, Mira Leung, Kevin Reynolds, Jeremy Ten, Nam Nguyen, and many others. In 2012, McLeod became the first level 5 certified figure skating coach in British Columbia., Victor Kraatz, MSC (born April 7, 1971) is a Canadian former ice dancer. In 2003, he and his partner, Shae-Lynn Bourne, became the first North American ice dancers to win a World Championship., Allie Hann-McCurdy (born May 23, 1987 in Nanaimo, British Columbia) is a Canadian ice dancer. McCurdy began skating at age eight and was a singles skater until age 12 when she switched to ice dancing. In 2003 she teamed up with Michael Coreno, with whom she was the 2010 Four Continents silver medalist and the 2008 Canadian bronze medalist. The pair retired in June 2010, to coach at the Gloucester Skating Club., Maikki Uotila - Kraatz ( born 25 February 1977 ) is a Finnish ice dancer . She is a former Finnish national champion with Toni Mattila . She married Victor Kraatz on June 19 , 2004 . The two coach in Vancouver , where they are the ice dancing directors at the BC Centre of Excellence . She and Kraatz have two sons , born September 14 , 2006 and July 10 , 2010 ., Burnaby is a city in British Columbia, Canada, located immediately to the east of Vancouver. It is the third-largest city in British Columbia by population, surpassed only by nearby Surrey and Vancouver., Canada (French: ) is a country in the northern half of North America. Its ten provinces and three territories extend from the Atlantic to the Pacific and northward into the Arctic Ocean, covering , making it the world's second-largest country by total area and the fourth-largest country by land area. Canada's border with the United States is the world's longest land border. The majority of the country has a cold or severely cold winter climate, but southerly areas are warm in summer. Canada is sparsely populated, the majority of its land territory being dominated by forest and tundra and the Rocky Mountains. About four-fifths of the country's population of 36 million people is urbanized and live near the southern border. Its capital is Ottawa, its largest city is Toronto; other major urban areas include Montreal, Vancouver, Calgary, Edmonton, Quebec City, Winnipeg and Hamilton., British Columbia (BC) is the westernmost province of Canada, with a population of more than four million people located between the Pacific Ocean and the Rocky Mountains. \nBritish Columbia is also a component of the Pacific Northwest and the Cascadia bioregion, along with the U.S. states of Idaho, Oregon, Washington and Alaska., The \"Champs International Skating Centre of British Columbia\" (formerly known as the 'BC Centre of Excellence') is one of two major figure skating training centers in Canada. Located in Burnaby, British Columbia, it is home to many great national and international skaters. The programs there are overseen by a staff, including Joanne McLeod, who coaches 3-time Canadian men's national champion Emanuel Sandhu; Bruno Marcotte, who competed at the 2002 Winter Olympics; Victor Kraatz, the 2003 World Champion in ice dancing, and Maikki Uotila, who was a national champion in Finland. The center operates out of Canlan Ice Sports Burnaby 8 Rinks. Notable skaters who train there include Emanuel Sandhu, Mira Leung, Allie Hann-McCurdy & Michael Coreno, Jessica Millar & Ian Moram, Jeremy Ten, and Kevin Reynolds. This skating school is sometimes known as a training site for international competitors to practice for competitions in Vancouver. Champs International hosts its annual competition known as the BC/YK SummerSkate Competition every August., Shae-Lynn Bourne, MSC (born January 24, 1976) is a Canadian ice dancer. In 2003, she and partner Victor Kraatz became the first North American ice dancers to win a World Championship. They competed at three Winter Olympic Games, placing 10th at the 1994 Winter Olympics, 4th at the 1998 Winter Olympics, and 4th at the 2002 Winter Olympics., Vancouver, officially the City of Vancouver, is a coastal seaport city on the mainland of British Columbia, Canada, and the most populous city in the province., Subject: maikki uotila, Relation: country_of_citizenship, Options: (A) american (B) british (C) canada (D) finland (E) montreal\nExample output: finland\nExample explanation: This is a good example, as maikki uotila is citizen of the finland.\nQ: Context: Utah (or ) is a state in the western United States. It became the 45th state admitted to the U.S. on January 4, 1896. Utah is the 13th-largest by area, 31st-most-populous, and 10th-least-densely populated of the 50 United States. Utah has a population of more than 3 million (Census estimate for July 1, 2016), approximately 80% of whom live along the Wasatch Front, centering on the state capital Salt Lake City. Utah is bordered by Colorado to the east, Wyoming to the northeast, Idaho to the north, Arizona to the south, and Nevada to the west. It also touches a corner of New Mexico in the southeast., Gainesville is the county seat and largest city in Alachua County, Florida, United States, and the principal city of the Gainesville, Florida Metropolitan Statistical Area (MSA). The population of Gainesville in the 2013 US Census estimates was 127,488, a 2.4% growth from 2010. Gainesville is the largest city in the region of North Central Florida. It is also a component of the Gainesville-Lake City Combined Statistical Area, which had a 2013 population of 337,925., The University of Utah (also referred to as the U, the U of U, or Utah) is a public coeducational space-grant research university in Salt Lake City, Utah, United States. As the state's flagship university, the university offers more than 100 undergraduate majors and more than 92 graduate degree programs. The university is classified in the highest ranking: \"R-1: Doctoral Universities Highest Research Activity\" by the Carnegie Classification of Institutions of Higher Education. The Carnegie Classification also considers the university as \"selective\", which is its second most selective admissions category. Graduate studies include the S.J. Quinney College of Law and the School of Medicine, Utah's only medical school. As of Fall 2015, there are 23,909 undergraduate students and 7,764 graduate students, for an enrollment total of 31,673., A medical school is a tertiary educational institutionor part of such an institutionthat teaches medicine, and awards a professional degree for physicians and surgeons. Such medical degrees include the Bachelor of Medicine, Bachelor of Surgery (MBBS, MBChB, BMBS), Doctor of Medicine (MD), or Doctor of Osteopathic Medicine (DO). Many medical schools offer additional degrees, such as a Doctor of Philosophy, Master's degree, a physician assistant program, or other post-secondary education., Salt Lake City, often shortened to Salt Lake or SLC, is the capital and the most populous municipality of the U.S. state of Utah. With an estimated population of 190,884 in 2014, the city lies at the core of the Salt Lake City metropolitan area, which has a total population of 1,153,340 (2014 estimate). Salt Lake City is further situated within a larger metropolis known as the Salt Lake City-Ogden-Provo Combined Statistical Area. This region is a corridor of contiguous urban and suburban development stretched along an approximately segment of the Wasatch Front, comprising a total population of 2,423,912 . It is one of only two major urban areas in the Great Basin (the other is Reno, Nevada), and the largest in the Intermountain West., The State University System of Florida (SUS, or SUSF out-of-state) is a system of twelve public universities in the U.S. state of Florida. As of 2015, over 341,000 students were enrolled in Florida's state universities. Together with the Florida College System, which includes Florida's 28 community colleges and state colleges, it is part of Florida's system of public higher education. The system, headquartered in Tallahassee, is overseen by a Chancellor and governed by the Florida Board of Governors., Professor (commonly abbreviated as \"prof.\") is an academic rank at universities and other post-secondary education and research institutions in most countries. Literally, \"professor\" derives from Latin as a \"person who professes\" being usually an expert in arts or sciences, a teacher of the highest rank., The University of Florida (commonly referred to as Florida or UF) is an American public land-grant, sea-grant, and space-grant research university on a campus in Gainesville, Florida. It is a senior member of the State University System of Florida and traces its origins to 1853, and has operated continuously on its Gainesville campus since September 1906., James Bernard Machen ( born March 26 , 1944 ) is an American university professor and administrator . Machen is a native of Mississippi , and earned multiple academic degrees before becoming a university administrator and president . Machen previously was the president of the University of Utah in Salt Lake City , Utah and the University of Florida in Gainesville , Florida . He also sits on the Sanford - Burnham Medical Research Institute 's Board of Trustees . On June 8 , 2012 , Machen announced he would be stepping down as President in 2013 . However , in January 2013 , it was revealed that Machen would continue serving as the President of University of Florida ., Subject: bernie machen, Relation: position_held, Options: (A) 3 (B) 4 (C) chancellor (D) master (E) physician (F) professor (G) reno\nA:" }, { "from": "gpt", "value": "chancellor" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a pair of action statements. Your task is to check if you can conclusively identify which statement is less ethical or not. Answer: 'no' if one of the statements is less ethical, and 'yes' otherwise.\nProblem:ACTION1: sleeping with my brother's boyfriend ACTION2: being pissed off at a classmate who is bugging me for help\nSolution:" }, { "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're given a context, a sentence, and a character. The sentence describes an action or job of the given character. Also, the context provides more information about the sentence or the character. Your task is to return one of the emotions which are expressed by the Character in the given sentence. For that you can use the Context; however, Context is not provided in all the inputs. Also, in some inputs, there can be zero emotion; for that return 'None'.\n\nContext: A cook was carrying an armful of oranged in the kitchen. \n Sentence: He dropped one on the floor by accident. \n Character: Cook\nSolution: annoyed\nWhy? The cook dropped one orange on the floor, so, he must feel annoyed at that time.\n\nNew input: Context: Jamal and Darnell were friends who both grew up in the ghetto. Jamal started dealing drugs, while Darnell worked hard in school. Darnell got a scholarship to a big university and moved away. Years later, Jamal got killed in a drug deal gone wrong. \n Sentence: In Jamal's memory, Darnell founded a support group in the ghetto. \n Character: Jamal\nSolution:" }, { "from": "gpt", "value": "None" } ]
[ { "from": "human", "value": "In this task, you're given an article and an answer. Your task is to generate the question for the answer based on the given article.\nExample: Article: There are a lot of public libraries in Britain. These libraries have more than one hundred and fifteen million books, not including those libraries of public schools. Public libraries not only lend books, music records but also help children, patients in hospitals and others to get special play readings, film shows and so on. The first public libraries were founded in about the year 1850. Today's public libraries usually have a reading-room, a lending room and a reference room. The greatest and most famous library in Britain is that of the British Library in London. It was founded in 1973 and has over 10, 000, 000 books. It has nearly every magazine, newspaper and book published in Britain and other parts across the world. \n Answer: 10,000,000 or less.\nExample solution: How many books are there in the British Library?\nExample explanation: In the Article, 10,000,000 is mentioned for the number of books available in the British Library, so this is a good question.\n\nProblem: Article: The new world of today introduced new threats that were not known in the previous generations: Internet predators . Often we do a lot of our researching, shopping, talking; just about everything online nowadays. New advancements in revolution comes along with the unwanted attackers. There are people out there who gain pleasure from, interrupting and taking from our peaceful lives what's not rightfully theirs. But like with everything, there are indeed counteractive measures that can be set in place to fend off these predators from such damage. I'd like to introduce the Guardian Eye. Within this program is a complex program which has several functions to create a safe atmosphere for whomever uses the computer, It has the ability to track and log every key stroke, every website that has ever been accessed, takes screenshots of web pages, blocks web pages according to content and even sends you messages via email once conspicuous activity has been reported and logged. Just think, you or child could be browsing and searching through the Internet and inappropriate content pops up with several different windows. You try to click out of the windows but you accidentally click one which releases spyware, infecting your computer. Guardian Eye blocks unwanted content from popping up or appearing to the users, which I thought was extremely convenient. In this way there is not even the slightest temptation. This product helps prevent damage from being done to your computer and worse, your identity. It's quite the product and it offers a little version so you may try it out first. If you'd like the full package, it's a once time fee 39.99 and can be installed on unlimited computers for your convenience. It's a nice deal and I'm considering getting it again considering I do a lot of writing on various websites myself. \n Answer: It stops spyware from entering the computer.\n" }, { "from": "gpt", "value": "Solution: In what way is Guardian Eye most useful to kids?" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you are given a text from tweets. Your task is to classify given tweet text into two categories: 1) positive, and 2) negative based on its content.\n\nWell tomorrow is the big day..my bday! not sure what i am doing except working \n" }, { "from": "gpt", "value": "negative" } ]
[ { "from": "human", "value": "Detailed Instructions: Read the given query and classify it as a 'Good' or 'Bad' query depending on how well the query is formed, 'Bad' being the expected output for a not so well formed query and 'Good' being the expected output for a well formed query. A query may be wrong based on common sense or general facts, but if it is well formed, you should answer with Good.\nSee one example below:\nProblem: What is the scientific name of the tortoise ?\nSolution: Good\nExplanation: The output for the query is Good because the query has no grammatical, punctuation or spelling errors.\n\nProblem: The chloride ion is an example of a ?\nSolution:" }, { "from": "gpt", "value": "Bad" } ]
[ { "from": "human", "value": "Definition: 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.\nInput: 1, 2, ['J', 'L', 'E']\nOutput:" }, { "from": "gpt", "value": "0" } ]
[ { "from": "human", "value": "Teacher: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.\nTeacher: Now, understand the problem? Solve this instance: look around right thrice and walk around right thrice\nStudent:" }, { "from": "gpt", "value": "I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK 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" } ]
[ { "from": "human", "value": "In 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?). \",\nOne example: Sentence: Efforts to control future SARS outbreaks depend on the accurate and early identification of SARS-CoV infected patients. \n Section: background\nSolution is here: True\nExplanation: The section is correct because it provides the background information regarding how they could control future SARS outbreaks depending on the accuracy of identification of some infected patients having SARS-CoV.\n\nNow, solve this: Sentence: with their peak incidence ( in the 1980s ) concomitant with the HIV pandemic. \n Section: method\nSolution:" }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nYou 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.\n\nHow do you remove keys from a computer keyboard for cleaning?\nSolution: Place the tip of your finger under the corner of a key and gently twist to pop it off.\nWhy? 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.\n\nNew input: How do you bring a pot of water on the stove to a full rolling boil?\nSolution:" }, { "from": "gpt", "value": "Turn the stove on to its coolest setting, then wait until the water is full of large, strong bubbles." } ]
[ { "from": "human", "value": "Detailed Instructions: 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.\nSee one example below:\nProblem: Rope and its Usage\nSolution: Intambo nomsebenzi ewenzayo.\nExplanation: 'Intambo' means rope, 'nomsebenzi ewenzayo' roughly translates to 'the work it does', which is a native way of phrasing it.\n\nProblem: However, the B turret in some was later replaced by an Exocet mounting.\nSolution:" }, { "from": "gpt", "value": "Kananjalo , iinqaba eyiB kwezinye ethubeni yathathelwa indawo yiExocet yonyuso ." } ]
[ { "from": "human", "value": "Definition: In this task you will be given a text passage from a trivia quiz. You should choose the category this question belongs to from these categories: History, Science, Social Science, Fine Arts, Literature. You can only choose one category, so if in doubt, please choose the closest match.\nInput: The minimalist composer Steve Reich has set several of this man's works to music in pieces such as Proverbs. His lesser known works include Remarks on Color and Culture and Value, and he and Emil Post are independently credited with the development of the modern truth table. In one notable work, this man claimed that many philosophical problems are merely \"bewitchments\" rising from the misuse of language, while his most famous work contains seven major propositions, including \"The world is everything that is the case. \" FTP, name this philosopher whose most notable works include Philosophical Investigations and Tractatus Logico-Philosophicus.\nOutput:" }, { "from": "gpt", "value": "Social Science" } ]
[ { "from": "human", "value": "In this task, you are given two facts, and a multiple-choice question. Based on the given facts, answer the question with index of the correct option (e.g, \"A\").\n\nFact1: a light bulb requires electrical energy to produce light, Fact2: Most of the energy a light bulb uses turns into heat., Question: What happens to the power a light bulb uses? (A) It makes magnetic energy (B) It gets cold (C) It turns into heat (D) hydrogen and oxygen (E) It decreases (F) It expands (G) It turns into static (H) They may not survive." }, { "from": "gpt", "value": "C" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task, you're given a review from Amazon and your task is to generate the name of the category of the product based on the review given by the user. The categories are: kitchen, office product, watch, wireless, other, toy, digital video download, camera, jewelry, pet products, sports, industrial supplies, baby product, grocery, drugstore, home improvement, pc, shoes, automotive, digital ebook purchase, musical instruments, beauty, book, electronics, lawn and garden, apparel, home, video games, luggage, furniture, personal care appliances.\nPart 2. Example\nArrived broken. Manufacturer defect. Two of the legs of the base were not completely formed, so there was no way to insert the casters. I unpackaged the entire chair and hardware before noticing this. So, I'll spend twice the amount of time boxing up the whole useless thing and send it back with a 1-star review of part of a chair I never got to sit in. I will go so far as to include a picture of what their injection molding and quality assurance process missed though. I will be hesitant to buy again. It makes me wonder if there aren't missing structures and supports that don't impede the assembly process.\nAnswer: furniture\nExplanation: The customer gives a review of the product which belongs to the furniture category because we can see it from the way the customer describes his experience sharing how he unpackaged his chair.\nPart 3. Exercise\nThese are trash. Major static when plugged into my Samsung galaxy s10 (that i didn't have with standard headphones) and the bass is too strong and weirdly muffled at the same time. Tried placing a call, the person on the other end said they were hearing their voice echoing. Returning.\nAnswer:" }, { "from": "gpt", "value": "electronics" } ]
[ { "from": "human", "value": "Instructions: Given a sentence, generate what should be the most likely next statement. The next statement should be reasonable and logically correct.\nInput: Snoop Dog moves through an opening. Its bright lights\nOutput:" }, { "from": "gpt", "value": "illuminate a crystal chandelier still dangling from a ceiling." } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you will be given a list of numbers. The goal is to divide all the numbers in the list by a constant such that the sum of the resulting list is 1. The output should be rounded to 3 decimals.\nSee one example below:\nProblem: [1, 2, 3]\nSolution: [0.167, 0.333, 0.500]\nExplanation: The output list sums to 1.0 and has the same weight as the input 0.333 is twice as large as 0.167, .5 is 3 times as large as 0.167, and 0.5 is 1.5 times as large as 0.333. This is a good example.\n\nProblem: [-35.775, -29.711]\nSolution:" }, { "from": "gpt", "value": "[0.546 0.454]" } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task, you are given a sentence. You are expected to recognize the name of gene or protein. Although there might be several correct answers, you need to write one of them.\nPROBLEM: The purpose of this study was to evaluate the in vitro activity of the principal metabolites of ATRA [ 4 - hydroxy - retinoic acid ( 4 - OH - RA ) , 18 - hydroxy - retinoic acid ( 18 - OH - RA ) , 4 - oxo - retinoic acid ( 4 - oxo - RA ) , and 5 , 6 - epoxy - retinoic acid ( 5 , 6 - epoxy - RA ) ] in NB4 , a human promyelocytic leukemia cell line that exhibits the APL diagnostic t ( 15 ; 17 ) chromosomal translocation and expresses the PML - RAR alpha fusion protein .\n\nSOLUTION: fusion protein\n\nPROBLEM: HLA - DQ tetramers identify epitope - specific T cells in peripheral blood of herpes simplex virus type 2 - infected individuals : direct detection of immunodominant antigen - responsive cells .\n\nSOLUTION: HLA - DQ\n\nPROBLEM: In addition , the proliferative advantage of p12 ( I ) - transduced PBMCs was evident mainly at low concentrations of IL - 2 .\n\nSOLUTION:" }, { "from": "gpt", "value": "IL - 2\n\n" } ]
[ { "from": "human", "value": "Teacher:In this task, you're given a story (which contains five sentences only). Your task is to find all the characters which are available in the given story.\nTeacher: Now, understand the problem? Solve this instance: Sentence1: I wanted to paint my house. Sentence2: I went to the store to buy paint. Sentence3: I bought some green paint. Sentence4: I painted the house green! Sentence5: My wife hated it and said she wanted me to paint it back to white.\nStudent:" }, { "from": "gpt", "value": "I (myself), Wife" } ]
[ { "from": "human", "value": "Definition: In this task, you will be shown a sentence, and you should determine whether it is overruling or non-overruling. In law, an overruling sentence is a statement that nullifies a previous case decision as a precedent by a constitutionally valid statute or a decision by the same or higher ranking court which establishes a different rule on the point of law involved. Classify your answers into overruling or non-overruling\nInput: finally, to the extent that schenck holds that there is no fiduciary duty on the part of the introducing broker in circumstances similar to those presented in the case at bar, we reject the holding.\nOutput:" }, { "from": "gpt", "value": "overruling" } ]
[ { "from": "human", "value": "Given two sentences regarding the stereotypes of religions, 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\nTarget: Muslim \nThe Muslim woman wore a hijab. The woman does not have a driver's license." }, { "from": "gpt", "value": "stereotype" } ]
[ { "from": "human", "value": "Q: In this task you will be given a list of integers. You should find the minimum absolute difference between 2 integers in the list. The absolute difference is the absolute value of one integer subtracted by another. The output should be a single integer which is the smallest possible absolute distance.\n[18, -57, 24, 45]\nA:" }, { "from": "gpt", "value": "6" } ]
[ { "from": "human", "value": "In this task, you will be given a sentence or two along with a change aspect. You should change the given text in the given aspect. Aspects are explained below:\n Tense: Change the tense of the verbs in the text. If they're in past tense, change them to present, and if they're in present tense, change them to past tense.\nNumber: Change the number of the nouns in the given text. Make plurals into singles and single into plurals. Remember to change the corresponding pronouns accordingly.\nVoice: If the verbs are in active voice, change them to be passive, otherwise, change them to be in active voice.\nAdverb: add one or multiple adverbs to the text.\nGender: If the text contains female names and pronouns, substitute them with male names and pronouns. Do the same for sentences with mala names and pronouns.\nQ: sentence: The dog chased the cat , which ran up a tree . It waited at the bottom . aspect: Tense\nA: " }, { "from": "gpt", "value": "The dog is chasing the cat , which is running up a tree . It is waiting at the bottom ." } ]
[ { "from": "human", "value": "instruction:\nIn this task, you're given a context passage. Your job is to generate relevant questions that can be answered by directly referring to the passage.\nquestion:\nBailey is taking a class with Aubrey and the two are taking a test.\nanswer:\nWhat does Bailey need to do before this?\n\n\nquestion:\nIt was indeed a nice reunion since no explanations or arguments was made - we just saw each other and hugged - but , the reason for the reunion is something that I wouldn't wish to happen ever again . Despite the tears and pain of losing \" auntie - second mom , \" I am still thankful that she didn't suffer a painful experience before she finally went home . I know , she is now pain free and happy with Jesus in heaven . But , in my selfish state of feeling and mindset , I wished she's still here with us ... But God's ways are far better than ours - He knows what's best for all of us ... right now , I just have to think that \" aunt - second mom \" is real happy in heaven .\nanswer:\nWhy do I believe she is with Jesus ?\n\n\nquestion:\nLee french kissed their partner. They are in a romantic relationship.\nanswer:\n" }, { "from": "gpt", "value": "What does Lee need to do before this?\n\n\n" } ]
[ { "from": "human", "value": "In this task, you are given the abstract of a research paper. Your task is to generate a summary of this abstract. Your summary should not be very short, but it's better if it's not more than 30 words.\n\nInput: Consider Input: Hierarchical label structures widely exist in many machine learning tasks, ranging from those with explicit label hierarchies such as image classification to the ones that have latent label hierarchies such as semantic segmentation. Unfortunately, state-of-the-art methods often utilize cross-entropy loss which in-explicitly assumes the independence among class labels. Motivated by the fact that class members from the same hierarchy need to be similar to each others, we design a new training diagram called Hierarchical Complement Objective Training (HCOT). In HCOT, in addition to maximizing the probability of the ground truth class, we also neutralize the probabilities of rest of the classes in a hierarchical fashion, making the model take advantage of the label hierarchy explicitly. We conduct our method on both image classification and semantic segmentation. Results show that HCOT outperforms state-of-the-art models in CIFAR100, Imagenet, and PASCAL-context. Our experiments also demonstrate that HCOT can be applied on tasks with latent label hierarchies, which is a common characteristic in many machine learning tasks.\n\nOutput: We propose Hierarchical Complement Objective Training, a novel training paradigm to effectively leverage category hierarchy in the labeling space on both image classification and semantic segmentation.\n\n\nInput: Consider Input: Abstraction of Markov Decision Processes is a useful tool for solving complex problems, as it can ignore unimportant aspects of an environment, simplifying the process of learning an optimal policy. In this paper, we propose a new algorithm for finding abstract MDPs in environments with continuous state spaces. It is based on MDP homomorphisms, a structure-preserving mapping between MDPs. We demonstrate our algorithm's ability to learns abstractions from collected experience and show how to reuse the abstractions to guide exploration in new tasks the agent encounters. Our novel task transfer method beats a baseline based on a deep Q-network.\n\nOutput: We create abstract models of environments from experience and use them to learn new tasks faster.\n\n\nInput: Consider Input: With the rise in employment of deep learning methods in safety-critical scenarios, interpretability is more essential than ever before. Although many different directions regarding interpretability have been explored for visual modalities, time-series data has been neglected with only a handful of methods tested due to their poor intelligibility. We approach the problem of interpretability in a novel way by proposing TSInsight where we attach an auto-encoder with a sparsity-inducing norm on its output to the classifier and fine-tune it based on the gradients from the classifier and a reconstruction penalty. The auto-encoder learns to preserve features that are important for the prediction by the classifier and suppresses the ones that are irrelevant i.e. serves as a feature attribution method to boost interpretability. In other words, we ask the network to only reconstruct parts which are useful for the classifier i.e. are correlated or causal for the prediction. In contrast to most other attribution frameworks, TSInsight is capable of generating both instance-based and model-based explanations. We evaluated TSInsight along with other commonly used attribution methods on a range of different time-series datasets to validate its efficacy. Furthermore, we analyzed the set of properties that TSInsight achieves out of the box including adversarial robustness and output space contraction. The obtained results advocate that TSInsight can be an effective tool for the interpretability of deep time-series models.\n\n" }, { "from": "gpt", "value": "Output: We present an attribution technique leveraging sparsity inducing norms to achieve interpretability.\n\n\n" } ]
[ { "from": "human", "value": "Instructions: In this task you will be given a list of numbers. A list is shown by two brackets and comma-separated numbers inside, like: [1,2,3]. You should remove all of the even numbers from the list. If every number in the input list is even an empty list should be returned. Zero should be counted as an even number.\nInput: [8, 54, 86, 62, 63, 92, 119, 75]\nOutput:" }, { "from": "gpt", "value": "[63, 119, 75]" } ]
[ { "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\n[EX Q]: 9, 11, ['I', '713', 'V', 'Z', '3693', '1861', '817', 'I', 'H', 'b', '9967', 'O', 'M', 'u', '7767', '853', '5445']\n[EX A]: 9967bH\n\n[EX Q]: 1, 6, ['4847', 'W', '283', '1771', '4461', '7905', '1167', 'q', 'Y', '9587', '8979', '1935', 'l', '7099', 'T', 'r', '3255', '1705', 'o', '8363', 'r', 'H', 'Z', '1011', '8449', '3821', 't', '3355', '417']\n[EX A]: 790544611771283W4847\n\n[EX Q]: 2, 2, ['u', '2523']\n[EX A]:" }, { "from": "gpt", "value": "2523\n\n" } ]
[ { "from": "human", "value": "Given an entity as input, output another entity which is part of the input entity. These are entities of meronym. In linguistics, meronymy is a semantic relation between a meronym denoting a part and a holonym denoting a whole. In simpler terms, a meronym (i.e., output entity) is in a part-of relationship with its holonym (i.e., input entity).\nOne example: plant\nSolution is here: stem\nExplanation: The answer is correct. Because a stem is one of two main structural axes of a vascular plant, the other being the root. Therefore, stem (i.e., meronym) is the part of plant (i.e., holonym).\n\nNow, solve this: protosteles\nSolution:" }, { "from": "gpt", "value": "xylem element" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task you are given a tweet and you must identify whether the tweet contains any offense or any form of (untargeted) profanity. Label the post as NOT if the post does not contain offense or profanity. Non-offensive posts do not include any form of offense or profanity. label the post as OFFENSIVE if the post contains offensive language or a targeted (veiled or direct) offense. Twitter user mentions were substituted by @USER and URLs have been substitute by URL.\nProblem:@USER He's got his wee fake tap fae Turkey on to prove how loyal he is.\nSolution:" }, { "from": "gpt", "value": "OFFENSIVE" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task, you are given a positive review and your task is to convert it to a negative review by making minimal changes. Avoid changing the context of the review.\nPart 2. Example\nall around great place to grab a drink or two .\nAnswer: all around bad place to grab a drink or two .\nExplanation: The output converts the given positive review to negative review by replacing the word 'great' with 'bad'. It does not change the context of the input\nPart 3. Exercise\ni have had a great experience every time from start to finish .\nAnswer:" }, { "from": "gpt", "value": "i have had a bad experience every time from start to finish ." } ]
[ { "from": "human", "value": "Q: In this task, you are given inputs i and A, where i is an integer and A is a list. You need to list all the elements of A preceding the last i elements. i will always have a value less than the length of A.\n3, ['5633', '4261', '6091', 'C', 'd', '353', 'A', '3291', 'E']\nA:" }, { "from": "gpt", "value": "5633, 4261, 6091, C, d, 353" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a sentence and your task is to identify whether the sentence contains motion or not, by classifying the sentence into Yes or No. The sentence belongs to the 'Yes' category if there is an occurrence of a motion of a physical entity otherwise the sentence belongs to the 'No' category. The sentence contains motion if it (i) involves the movement of a physical object. (ii) contains verb in present tense indicating the action performed. Sometimes there can be verb which indicates a motion but the motion might have happened in the past and the answers to such sentences is 'No'\nSee one example below:\nProblem: The man then paints a side table black with lights shining off of the black painted wood.\nSolution: Yes\nExplanation: Here the man is in motion as he is painting a side table black table.\n\nProblem: Several young men board a small powered boat on a very nice and sunny day.\nSolution:" }, { "from": "gpt", "value": "Yes" } ]
[ { "from": "human", "value": "Detailed Instructions: You will be given a sentence. Check whether the sentence is grammatically correct and is meaningful. If the sentence is grammatically correct, then answer with '1', otherwise answer with '0'.\nQ: Dorothy is needing new shoes.\nA:" }, { "from": "gpt", "value": "0" } ]
[ { "from": "human", "value": "In this task, you are given two sets, and a question. You need to find whether an element is at the intersection of two given sets. A Set is shown by two curly braces and comma-separated numbers inside, like {1, 2, 3}. The intersection of two given sets is the largest set which contains all the elements that are common to both sets. An element is at the intersection of two given sets, A and B, if common to both A and B. Classify your answers into 'Yes' or 'No'.\nOne example is below.\nQ: Set1: '{1, 6, 10, 12, 13, 14, 15, 16}', Set2: '{1, 2, 4, 6, 11, 14, 15, 20}'. Is the element '11' in the intersection of Set1 and Set2 ?\nA: No\nRationale: The intersection of Set1 and Set2 is {1, 6, 14, 15}. 11 is not an element of this set. So, the answer is No.\nQ: Set1: '{1, 5, 6, 7, 10, 12, 13, 15}', Set2: '{17, 10, 13}'. Is the element '5' in the intersection of Set1 and Set2 ?\nA:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "Detailed Instructions: Provide the parts-of-speech tag of a word present in a sentence specified within curly braces ( '{{ ... }}' ). The parts-of-speech tags are coarse labels that represent a category of words with similar grammatical properties. The list of part-of-speech tags i.e tagset of this corpus is - \n '.': Period symbol is used for symbols denoting Punctuations/Separations such as comma, period, backticks etc., \n 'ADJ': Adjectives are words that typically modify nouns and specify their properties or attributes, \n 'ADP': Adposition is a cover term for prepositions and postpositions, \n 'ADV': Adverbs are words that typically modify verbs for such categories as time, place, direction or manner, \n 'CONJ': A word used to connect clauses or sentences or to coordinate words in the same clause, \n 'DET': Determiners are words that modify nouns or noun phrases and express the reference of the noun phrase in context, \n 'NOUN': Nouns are a part of speech typically denoting a person, place, thing, animal or idea, \n 'NUM': A numeral is a word, functioning most typically as a determiner, adjective or pronoun, that expresses a number and a relation to the number, such as quantity, sequence, frequency or fraction, \n 'PRT': Particles are function words that must be associated with another word or phrase to impart meaning and that do not satisfy definitions of other universal parts of speech, \n 'PRON': Pronouns are words that substitute for nouns or noun phrases, whose meaning is recoverable from the linguistic or extralinguistic context, \n 'PROPN': A proper noun is a noun (or nominal content word) that is the name (or part of the name) of a specific individual, place, or object, \n 'VERB': A verb is a member of the syntactic class of words that typically signal events and actions, can constitute a minimal predicate in a clause, and govern the number and types of other constituents which may occur in the clause, \n 'X': The tag X is used for words that for some reason cannot be assigned a real part-of-speech category.\nProblem:Sentence: By -1 constantly seeking -2 to own the cheapest widget , index-arbitrage traders hope -1 to add between 1 % and {{ 3 }} % U* to the annual return of the S&P 500 . \nWord: 3\nSolution:" }, { "from": "gpt", "value": "NUM" } ]
[ { "from": "human", "value": "Detailed Instructions: Given a sentence, generate a new sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\nProblem:The local news will show milestones happening in your region .\nSolution:" }, { "from": "gpt", "value": "The local news will show meetings happening in your region ." } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given two sentences, sentence 1 and sentence 2, and the genre they belong to. Your job is to determine if the two sentences belong to the same genre or not. Indicate your answer with Y and N respectively. Genres available include: face-to-face, government, letters, 9/11, slate, telephone, travel, verbatim, oup, fiction. Sentences belonging to 'face-to-face' genres relate to conversations or dialogues, 'government' encompasses information released from public government websites, 'letters' refers to any written work for philanthropic fundraising, '9/11' relates to information pertaining to the 9/11 attacks, 'oup' includes non-fiction works on the textile industry and child development, 'slate' refers to any cultural topic that appears in the slate magazine, 'telephone' includes telephonic dialogue, 'travel' deals with information in travel guides, 'verbatim' includes short posts regarding linguistics, and 'fiction' includes popular works of fiction like 'The Secret Adversary' etc.\nQ: Sentence 1: Young British Artists From the Saatchi Collection (Royal Academy of Art, London). Sentence 2: US industrial companies rely on Japanese techniques to function. Genre: slate.\nA:" }, { "from": "gpt", "value": "N" } ]
[ { "from": "human", "value": "In this task, given a sentence in the Filipino language, your task is to convert it into the English language.\n\nAyon kay Galina Safronova, 55, \"ang gawaing ito ay sisira sa aking lungsod, ang lungsod kung saan ako lumaki, at ang lungsod na gusto kong iligtas para sa aking mga apo,\" pahayag na nakuha ng Associated Press." }, { "from": "gpt", "value": "Galina Safronova, 55, said that \"this action will destroy my city, the city where I grew up, and the city that I want to save for my grandchildren,\" as quoted by the Associated Press news agency." } ]
[ { "from": "human", "value": "Part 1. Definition\nThis task is about identifying the object of a given sentence. The object of a sentence is the person or thing that receives the action of the verb. It is the who or what that the subject does something to. Each sentence in this task is guaranteed to contain a single object. The input is a sentence and the output is the identified object of that sentence.\nPart 2. Example\nWe're Already Here aired on June16,2009\nAnswer: June16,2009\nExplanation: This is a good example since the object of the sentence (June16,2009) is correctly identified.\nPart 3. Exercise\nHe's Gonna Take You Home is a single from 1982.\nAnswer:" }, { "from": "gpt", "value": "1982" } ]
[ { "from": "human", "value": "instruction:\nFrom the given sentence, extract the phrase (often noun or verb) that carries the given relationship. The generated phrase should be present in the sentence.\nquestion:\nGiven Relationship: 'be mail to', Sentence: 'No. The FAFSA has to be mailed to the Federal Processor in the pre-addressed envelope provided with the application or filed online http ://www.fafsa.ed .gov .'\nanswer:\nmailed\n\n\nquestion:\nGiven Relationship: 'be professor of', Sentence: 'Your nerves learn to communicate more effectively with your muscle cells , allowing the muscle to recruit more cells during each contraction , says Mark A. W. Andrews , PhD , associate professor of physiology at Lake Erie College of Osteopathic Medicine in Erie , Pa .'\nanswer:\nprofessor\n\n\nquestion:\nGiven Relationship: 'be send to', Sentence: 'Congressional Leaders Send Auto Bailout Bill to White House Congressional negotiators have sent the White House a multibillion dollar ...'\nanswer:\n" }, { "from": "gpt", "value": "sent\n\n\n" } ]
[ { "from": "human", "value": "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.\n\nInput: Consider Input: Sentence1: Arnold bought a new television. Sentence2: After a couple of weeks it stopped working. Sentence3: He tried to return it but had lost his receipt. Sentence4: Arnold was not allowed to return the television.\n\nOutput: 2, He paid cash.\n\n\nInput: Consider Input: Sentence1: When I was sixteen I stole some hats. Sentence2: I had the money to buy them, I just didn't. Sentence3: They handcuffed me and walked me through the mall. Sentence4: I was so ashamed I never stole again.\n\nOutput: 3, Before I could leave the store the security had already grabbed me.\n\n\nInput: Consider Input: Sentence1: He started going to the casino multiple times a week. Sentence2: His losses were piling up a lot faster than his wins. Sentence3: In less than a year, he was out of money completely. Sentence4: He decided he needed to do something about his addiction.\n\n" }, { "from": "gpt", "value": "Output: 1, Phil felt a rush the first time he won a hand in blackjack.\n\n\n" } ]
[ { "from": "human", "value": "Teacher: In this task, you're given the title and three arbitrary sentences out of a five-sentence story. You are also given three additional sentence options, a, b, and c, that may or may not belong to the story. Your job is to pick the two options that seamlessly connect with the rest of the story; note that the selected choices may fit into the story at any point. Indicate your selected choices in order, i.e., as 'ab'/'bc'/'ac' and not as 'ba'/'ca'/'cb'. If options are equally plausible, pick the ones that make more sense.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nTitle: Marcus Buys Khakis. Marcus needed clothing for a business casual event. He decided to buy a pair of khakis. The pair he bought fit him perfectly. Choices: a. Marcus was happy to have the right clothes for the event. b. He left in a huff for having his ideas mocked. c. All of his clothes were either too formal or too casual.\nSolution: ac\nReason: Marcus is buying clothes for a business event and not presenting an idea.\n\nNow, solve this instance: Title: Some kids decided to bully us and take our bikes away. We told our mom and she came charging outside. Yelling, she sprayed the bullies with her hose until they surrendered. Choices: a. The parents told him to do his best as they knew Alex was unteachable. b. One day my sister and I were riding our bikes outside. c. We got our bike back and no one ever bullied us again!\nStudent:" }, { "from": "gpt", "value": "bc" } ]
[ { "from": "human", "value": "In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: threat and non-threat. Threat is a statement that someone will be hurt or harmed, especially if the person does not do something in particular.\n\nComment: Interesting that Bill Maher holds the exact same views on 13 year olds having sex with adults but no one is calling him out on it, nor cancelling his engagements." }, { "from": "gpt", "value": "Non-threat" } ]
[ { "from": "human", "value": "In this task, you are given a paragraph, a question, and a candidate incorrect answer to the question. Your goal is to judge whether the provided answer is a valid incorrect answer to a given question. An incorrect answer should not truthfully answer the given question. A good incorrect answer should be closely related to the content of the paragraph and/or the question so that the readers are forced to read the whole paragraph to infer its [in]correctness. Additionally, an incorrect answer should be of the same semantic type as the given correct answer (e.g., both can be names of locations). If you think the given incorrect answer is good(and incorrect), indicate it by responding \"Yes\". Otherwise, respond \"No\". There are only two types of responses possible:\"Yes\" and \"No\".\n\nParagraph- Sent 1: Dirk Diggler was born as Steven Samuel Adams on April 15 , 1961 outside of Saint Paul , Minnesota .\nSent 2: His parents were a construction worker and a boutique shop owner who attended church every Sunday and believed in God .\nSent 3: Looking for a career as a male model , Diggler dropped out of school at age 16 and left home .\nSent 4: He was discovered at a falafel stand by Jack Horner .\nSent 5: Diggler met his friend , Reed Rothchild , through Horner in 1979 while working on a film .\nSent 6: Horner slowly introduced Diggler to the business until he became noticeable within the industry .\nSent 7: Diggler became a prominent model and began appearing in pornographic films , after which his career took off .\nSent 8: He had critical and box office hits which led him to stardom .\nSent 9: The hits and publicity led to fame and money which led Diggler to the world of drugs .\nSent 10: With the amount of money Diggler was making he was able to support both his and Rothchild 's addictions .\nSent 11: The drugs eventually caused a breakup between Diggler and Horner since Diggler was having issues with his performance on set .\nSent 12: After the breakup Diggler tried to make a film himself but the film was never completed .\nSent 13: He then attempted a music career which was also successful but led him deeper into drugs because of the amount of money he was making .\nSent 14: He then starred in a TV show which was a failure both critically and commercially .\nSent 15: Having failed and with no work , Diggler returned to the porn industry taking roles in low-budget homosexual films to help support his habit . \nQuestion: What year did Dirk drop out of school and leave home? \nIncorrect Answer: 16 yrs.\nYes.\n\nParagraph- Sent 1: The film begins with the announcement of the scheduled launch of a space vehicle carrying an Indian remote sensing satellite which would help scientists identify land suitable for agriculture .\nSent 2: Within a short range of this operation , in the same forest , the state forest department runs an NCC camp for women cadets .\nSent 3: Dhuruvan is a trainer at the camp .\nSent 4: Being a Scheduled tribe , he is deprecated for being positioned as a cadet officer in the forest security force through reservation system by his senior officer Ganapathiram .\nSent 5: But Dhuruvan 's integrity and co-living with other tribes in the forest abnegates aboriginal allegations by other forward caste officials and cadets in the department .\nSent 6: As a part of the training camp , an expedition is organized into the forest for a selected five cadets from the troop .\nSent 7: Dhuruvan selects the five most insolent and disobedient girls in the troop for the expedition intending to provide them better training .\nSent 8: As an attempt at a practical joke , the haughty girls post a complaint to Ganapathiram claiming that they did n't feel safe with Dhuruvan and that he was responsible for whatever that was to happen to them .\nSent 9: Meanwhile , the expedition begins and while Dhuruvan is caught up in some procedures at the forest check post , the girls non-chanlantly try to drive the jeep and run it down the slope of a hill .\nSent 10: After losing their vehicle , the troop decides to stay in the forest for the night and go by an alternate route the next morning .\nSent 11: But the plot thickens , when Kalpana describes two white men with advanced armaments in the Indian forest heading towards the direction of the Indian satellite research station in the forest . \nQuestion: Was Dhuruvan apart of a camp? \nIncorrect Answer: ok.\nNo.\n\nParagraph- Sent 1: The film begins with the announcement of the scheduled launch of a space vehicle carrying an Indian remote sensing satellite which would help scientists identify land suitable for agriculture .\nSent 2: Within a short range of this operation , in the same forest , the state forest department runs an NCC camp for women cadets .\nSent 3: Dhuruvan is a trainer at the camp .\nSent 4: Being a Scheduled tribe , he is deprecated for being positioned as a cadet officer in the forest security force through reservation system by his senior officer Ganapathiram .\nSent 5: But Dhuruvan 's integrity and co-living with other tribes in the forest abnegates aboriginal allegations by other forward caste officials and cadets in the department .\nSent 6: As a part of the training camp , an expedition is organized into the forest for a selected five cadets from the troop .\nSent 7: Dhuruvan selects the five most insolent and disobedient girls in the troop for the expedition intending to provide them better training .\nSent 8: As an attempt at a practical joke , the haughty girls post a complaint to Ganapathiram claiming that they did n't feel safe with Dhuruvan and that he was responsible for whatever that was to happen to them .\nSent 9: Meanwhile , the expedition begins and while Dhuruvan is caught up in some procedures at the forest check post , the girls non-chanlantly try to drive the jeep and run it down the slope of a hill .\nSent 10: After losing their vehicle , the troop decides to stay in the forest for the night and go by an alternate route the next morning .\nSent 11: But the plot thickens , when Kalpana describes two white men with advanced armaments in the Indian forest heading towards the direction of the Indian satellite research station in the forest . \nQuestion: Where is the NCC camp for women cadets located? \nIncorrect Answer: Near the Central forest department.\n" }, { "from": "gpt", "value": "Yes.\n\n" } ]
[ { "from": "human", "value": "TASK DEFINITION: Given an entity, a before event, an after event, and an attribute related to the entity, generate a sentence as output. Your sentence should show the changes in the attribute of the entity.\nPROBLEM: entity: liquid \nbefore: thinner \nafter: thick \nattr: thickness\n\nSOLUTION: thickness of liquid was thinner before and thick afterwards\n\nPROBLEM: entity: lime \nbefore: unselected \nafter: selected \nattr: knowledge\n\nSOLUTION: knowledge of lime was unselected before and selected afterwards\n\nPROBLEM: entity: tank cover \nbefore: on tank \nafter: lifted off tank \nattr: location\n\nSOLUTION:" }, { "from": "gpt", "value": "location of tank cover was on the tank before and lifted off the tank afterwards\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a context tweet and an answer. Your job is to generate a question for the given answer based on the given tweet paragraph. Note that your question should be answerable based on the given tweet, and the answer to your question should be the given answer.\nQ: Context: This morning, I am formally announcing an investigation into the Flint water crisis. A.G. Bill Schuette (@SchuetteOnDuty) January 15, 2016 Answer: bill schuette\nA:" }, { "from": "gpt", "value": "who is investigating the flint water crisis?" } ]
[ { "from": "human", "value": "You are given a negative review and your task is to convert it to a positive review by one or more making minimal changes. Avoid changing the context of the review.\n\nLet me give you an example: we stood there in shock , because we never expected this .\nThe answer to this example can be: we loved every moment when we were there .\nHere is why: The output converts the given negative review to positive review by repharsing the sentence. It does not change the context of the input.\n\nOK. solve this:\nhad to wait a month to get in .\nAnswer:" }, { "from": "gpt", "value": "got in quickly" } ]
[ { "from": "human", "value": "In this task, you're given the title of a five-sentence story, the first four sentences, and two options for the fifth sentence as a and b. Your job is to pick the sentence option that does not connect with the rest of the story, indicating your choice as 'a' or 'b'. If both sentences are plausible, pick the one that makes less sense.\nOne example: Title: Marcus Buys Khakis. Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: All of his clothes were either too formal or too casual. Sentence 3: He decided to buy a pair of khakis. Sentence 4: The pair he bought fit him perfectly. Choices: a. Marcus was happy to have the right clothes for the event. b. He left in a huff for having his ideas mocked.\nSolution is here: b\nExplanation: Marcus is buying clothes for a business event and not presenting an idea.\n\nNow, solve this: Title: Runaway Dog. Sentence 1: Jane needed extra money. Sentence 2: She decided to walk dogs for extra cash. Sentence 3: Her second day things got too intense. Sentence 4: One of her walking dogs ran away. Choices: a. Jane lost her job. b. He apologized for the long wait.\nSolution:" }, { "from": "gpt", "value": "b" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nRead the given sentence and if it is a general advice then indicate via \"yes\". Otherwise indicate via \"no\". advice is basically offering suggestions about the best course of action to someone. advice can come in a variety of forms, for example Direct advice and Indirect advice. (1) Direct advice: Using words (e.g., suggest, advice, recommend), verbs (e.g., can, could, should, may), or using questions (e.g., why don't you's, how about, have you thought about). (2) Indirect advice: contains hints from personal experiences with the intention for someone to do the same thing or statements that imply an action should (or should not) be taken.\n\nLook online for local careers services , they can spice up your resume and run mock - interviews to give you notes on how to present yourself .\nOutput:" }, { "from": "gpt", "value": "yes" } ]
[ { "from": "human", "value": "Detailed Instructions: Given a story, answer the question about the story. The question is the last sentence in the input. These stories can be difficult due to their length and how each story has at least 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.\nQ: James entered the patio. Lucas entered the patio. The tomato is in the blue_crate. Lucas exited the patio. James moved the tomato to the red_suitcase. James exited the patio. Lucas entered the patio. Lucas entered the cellar. Evelyn entered the cellar. The potato is in the blue_pantry. Evelyn exited the cellar. Lucas moved the potato to the green_cupboard. Lucas exited the cellar. Evelyn entered the cellar. Avery entered the cellar. Evelyn is in the cellar. The potato is in the green_cupboard. Evelyn exited the cellar. Avery moved the potato to the blue_pantry. Avery exited the cellar. Evelyn entered the cellar. Lucas entered the cellar. Avery entered the cellar. The lime is in the green_cupboard. Avery exited the cellar. Lucas moved the lime to the blue_pantry. Lucas exited the cellar. Avery entered the cellar. Where is the lime really?\nA:" }, { "from": "gpt", "value": "blue_pantry" } ]
[ { "from": "human", "value": "In this task, you're given two sentences. Indicate if the first sentence clearly entails the second sentence (i.e., one can conclude the 2nd sentence by reading the 1st one). Indicate your answer with '1' if the first sentence entails the second sentence, otherwise answer with '0'.\nQ: Sentence 1: Rich and poor nations struck a historic deal on Sunday to slash billions of dollars in farm subsidies, create more open industrial markets and revive stalled world trade talks that could boost global growth. Sentence 2: Rich and poor nations crashed into a historic deal on Sunday.\nA: " }, { "from": "gpt", "value": "0" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task, you are given a question and a context passage. You have to answer the question based on the given passage.\nPart 2. Example\nwhat is the first event mentioned?, Context: The Russian Revolution is the series of revolutions in Russia in 1917, which destroyed the Tsarist autocracy and led to the creation of the Soviet Union. Following the abdication of Nicholas II of Russia, the Russian Provisional Government was established. In October 1917, a red faction revolution occurred in which the Red Guard, armed groups of workers and deserting soldiers directed by the Bolshevik Party, seized control of Saint Petersburg (then known as Petrograd) and began an immediate armed takeover of cities and villages throughout the former Russian Empire.\nAnswer: Russian Revolution\nExplanation: This is a good example, and the Russian Revolution is the first event mentioned.\nPart 3. Exercise\nWhat was a tactic used?, Context: In some rare cases, such as with Ethiopia and Qing Dynasty China, the local governments were able to use the treaties to at least mitigate the impact of European colonization. This involved learning the intricacies of European diplomatic customs and then using the treaties to prevent a power from overstepping their agreement or by playing different powers against each other.\nAnswer:" }, { "from": "gpt", "value": "playing different powers against each other" } ]
[ { "from": "human", "value": "Instructions: In this task you will be given a list of integers. You should only return an integer if the first digit is the same as the last digit in the number. If an integer has a single digit, then it should be returned. If there are no integers that start and end with the same digit then an empty list (\"[]\") should be returned.\nInput: [210, -778, 265, 679, 134, 169, 334, 971, -130, -282, 1, 625, 806, -920, 14, -690, 646, 252, 271, -471, -795]\nOutput:" }, { "from": "gpt", "value": "[-282, 1, 646, 252]" } ]
[ { "from": "human", "value": "Classify the given tweet into the three categories: (1) 'Hate Speech', (2) 'Offensive' and (3) 'Neither'. 'Hate Speech' is kind of a threating statement or sometimes include call for violence while 'offensive' statement just offensds someone. 'Neither' is when it doesn't fall into Hate Speech or Offensive category.\n\n@LanceTHESPOKEN Statement of the Day: Ppl who RT @ChiefsatWar are even dumber than he is. The ole birds of a feather type of deal." }, { "from": "gpt", "value": "Neither" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you need to replace a letter in the sentence with another given letter.\nQ: Sentence: 'graffiti on a train compartment and a metal container placed nearby'. Replace the letter 'i' with 'f' in the sentence.\nA:" }, { "from": "gpt", "value": "graffftf on a trafn compartment and a metal contafner placed nearby" } ]
[ { "from": "human", "value": "In this task you are given a sentence. You must judge whether the main verb of the sentence is in present or past tense. Label the instances as \"Present\" or \"Past\" based on your judgment. If there is no verb in the given text, answer \"Present\".\nExample: She shone her light around the space, following the glow of the flashlight's ray along the walls.\nExample solution: Past\nExample explanation: The verb \"shone\" is in past tense.\n\nProblem: She never disappears until someone actually needs something. \"\n" }, { "from": "gpt", "value": "Solution: Present" } ]
[ { "from": "human", "value": "In this task you are expected to provide an SQL statement from an english description of what that SQL statement does. The description may include multiple steps but you should only ouput one SQL statement that accomplishes every step. An SQL query works by selecting data from a table where certain conditions apply. A table contains columns where every row in that table must have a value for each column. Every table has a primary key that uniquely identifies each row, usually an id. To choose which columns are returned you specify that after the \"SELECT\" statement. Next, you use a \"FROM\" statement to specify what tables you want to select the data from. When you specify a table you can rename it with the \"AS\" statement. You can reference that table by whatever name follows the \"AS\" statement. If you want to select data from multiple tables you need to use the \"JOIN\" statement. This will join the tables together by pairing a row in one table with every row in the other table (Cartesian Product). To limit the number of rows returned you should use the \"ON\" statement. This will only return rows where the condition specified after the statement is true, this is usually an equals operator with primary keys. You can also use the \"WHERE\" statement to specify that only rows with column values statisfying a certain condition, should be returned. The \"GROUP BY\" statement will group rows together that have equal column values for whatever columns follows the statement. The \"HAVING\" statement will return groups that statisfy whatever condition follows the statement. Any column(s) being returned from grouped rows must either be an aggregate function, (AVG, MAX, COUNT, SUM, ...) of a column, or the column(s) that the data was grouped by. To sort the returned data you can use the \"ORDER BY\" command which will order the data by whatever aggregate function or column follows the statement. The \"DESC\" statement will sort in descending order and the \"ASC\" statement will sort in ascending order. Finally, you can use the \"LIMIT\" statement to return a certain number of rows. When \"\" is used in an SQL statement every column is returned. For example, SELECT FROM table WHERE attribute = 1, will select every column from rows with the attribute column equal to 1.\nQ: find the average student_capacity and the average student_capacity in Dorm table whose gender equals X\nA: " }, { "from": "gpt", "value": "SELECT Avg ( student_capacity ) , Avg ( student_capacity ) FROM Dorm WHERE gender = \"X\"" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you must modify the text given in the input to generate a paraphrased sentence. Your output sentence must retain the same meaning, but does not necessarily have to include all the details as the input text.\nProblem:sentence_B_original: a young man with brown hair and sunglasses sits by cans of soda\nSolution:" }, { "from": "gpt", "value": "A young man with brown hair and sunglasses is sitting in front of some cans of soda" } ]
[ { "from": "human", "value": "Teacher:In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: sexual-explicit and non-sexual-explicit. A comment is considered sexual-explicit if it explicitly portrays sexual matters.\nTeacher: Now, understand the problem? Solve this instance: Comment: Gee i wish otapper was around so the korean boy king could boss him around and kick our ass. But ... barry otapper is gone time to drop a nuke\nStudent:" }, { "from": "gpt", "value": "Sexual-explicit" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you will be given two sentences separated by \", so\". You should decide whether the first sentence can be the cause of the second sentence. If you can see a possible causation, answer with \"plausible\", otherwise answer with \"not plausible\".\n\nThe homeowners disliked their nosy neighbors, so they didn't have any problems\nOutput:" }, { "from": "gpt", "value": "not plausible" } ]
[ { "from": "human", "value": "Given a pair of words, deduce the type of relationship between them. The various types of relations are: 'HYPER', 'COORD' and 'RANDOM'. Let's denote the first word by X and the second word by Y. A COORD relationship holds when X and Y belong to the same semantic class. A HYPER relationship applies when X is a specific instance of Y. If niether COORD nor HYPER are applicable then the relationship is RANDOM.\nOne example: X: turtle, Y: flow\nSolution is here: RANDOM\nExplanation: Turtle and flow have no relation, so RANDOM is the correct label.\n\nNow, solve this: X: beetle, Y: being\nSolution:" }, { "from": "gpt", "value": "RANDOM" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given inputs i and A, where i is an integer and A is a list. You need to list all the elements of A preceding the last i elements. i will always have a value less than the length of A.\nQ: 9, ['A', 'O', '4855', '6527', 'Q', '9795', '3093', '1031', 'T', '4899', '8805', 'M', 'P', 'U', 'C', 'y', '4461', 'C', 'N', '9821', 'I', '6589', 'F', 'm', 'O', '4787', '4767', '2367', 'P']\nA:" }, { "from": "gpt", "value": "A, O, 4855, 6527, Q, 9795, 3093, 1031, T, 4899, 8805, M, P, U, C, y, 4461, C, N, 9821" } ]
[ { "from": "human", "value": "Given a category and a set of five words, find the word from the set that does not belong (i.e. is the least relevant) with the other words in the category. Words are separated by commas.\n\nEx Input:\nCategory: weather \nWords: 70, endure, decent, cold, fair\n\nEx Output:\ndecent\n\n\nEx Input:\nCategory: accomodation \nWords: apartment, cabin, squashed, smooth, flat\n\nEx Output:\nsmooth\n\n\nEx Input:\nCategory: employment activity \nWords: water, promote, empower, instruct, fire\n\nEx Output:\n" }, { "from": "gpt", "value": "water\n\n\n" } ]
[ { "from": "human", "value": "Q: In this task, you're given the title and three arbitrary sentences out of a five-sentence story. You are also given three additional sentence options, a, b, and c, that may or may not belong to the story. Your job is to pick the two options that seamlessly connect with the rest of the story; note that the selected choices may fit into the story at any point. Indicate your selected choices in order, i.e., as 'ab'/'bc'/'ac' and not as 'ba'/'ca'/'cb'. If options are equally plausible, pick the ones that make more sense.\nTitle: We took the kids to a preseason practice. The kids loved seeing their players. They thought the qb skills was the best. Choices: a. They had games set up for them to play. b. The thief took his medal. c. We were really happy to take them.\nA:" }, { "from": "gpt", "value": "ac" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. You are given a short text as a title. Your task is to generate a poem as output that is related to the given title and should feel like written by kids. The output should be a run-on sentence (two or more complete sentences connected without any punctuation). The poem should not be too long or too complex, because it should feel like it is written by younger person without high level of literature education.\n\nRosess\n" }, { "from": "gpt", "value": "rose be red violet be blue you love me and i love you" } ]
[ { "from": "human", "value": "In this task, you will be shown a conversation and a question. You need to write an implausible answer to the question. Even though there exist multiple wrong answers, we only need a single wrong answer. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\n\n[Q]: W: Oh, this is amazing! It's so lifelike. Oh, just look at the sky and the sea. A work of a talent! M: Yeah. I can't agree more. It's outstanding in this gallery., Question: Where are the two speakers?\n[A]: By the sea.\n\n\n[Q]: W: I have no idea how to finish the timetable. M: You don't have to be very creative. It's very standard and more or less the same every year. For example, the sports day begins with throwing events. All jumping events take place before lunch. W: Why? M: That's because the school doesn't want the athletes to jump after eating. The jumping events take place after the throwing events. And the long distance race takes place before the jumping events. W: And after lunch? M: Actually, the school doesn't want any events to take place at that time. But they can practise for the next event. W: Do you mean the 100-meter race? M: Yes. It demands a lot of energy and seems to be the most exciting event, so it takes place at the end of the day, which is around 5:00 p. m., Question: What does the man say about the 100-meter race?\n[A]: It takes place at 6:00 p.m.\n\n\n[Q]: W: Hi, Jack. Who are you writing to? M: I'm writing to my parents telling them I'll stay here this summer. W: You're not going home? I thought you were going on a trip to Japan with your family. M: Well, I intended to go with them, but I thought again and changed my mind. W: Tell me. I'm interested in knowing what keeps you from joining your beloved family and staying here. It certainly is not studying. M: No, certainly not. Michael arranged for me to work at his uncle's institution. W: How much will you be paid? M: Judy, I don't do it for money, but for experience. Besides, it's voluntary work. W: You work without payment? That's really something. M: When will you leave for home? W: Tomorrow. We'll fly to Hawaii two days after. I really have to pack now. M: Go then. Have a nice vacation! W: I'll send you postcards., Question: What's the man going to do?\n[A]:" }, { "from": "gpt", "value": "To prepare for his exams.\n\n\n" } ]

Subsets and Splits

No community queries yet

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