Search is not available for this dataset
conversations
listlengths 2
2
|
|---|
[
{
"from": "human",
"value": "In this task, you are given a text from a social media post. Your task is to classify the given post into two categories: 1) yes if the given post is potentially offensive to anyone (i.e., a subset of people, any particular person, etc.), 2) no, otherwise. Note that potentially offensive posts can contain sexual, racial, religious biased or offensive language. Warning: the examples and instances may contain offensive language.\n\na relationship can't always be 50/50, sometimes ur partner is gonna be going through something and u gotta pick up the slack for them..\nNo\n\nok yea i listen to weird music but this guy is playing some metal mexican rap shit and I really need to leave this class\nNo\n\nThis bitch literally just said \"normal people shouldn't work out in this gym because so many body builders workout here\"\n"
},
{
"from": "gpt",
"value": "Yes\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task you will be given a list of numbers and you need to subtract every value in the list with the index it is at. The index of an elements shows its numerical order in the list(for example, in the list [7,10,4,5], the index of 7 is 1 and the index of 4 is 3) You should start the index at 1, so the first element in the list will be subtracted by one. For every element in the list you need to find \"element - index\" where the index of the beginning element is 1 and increments by 1 for each element. Put your result list in brackets.\nQ: [-10, 6, -18]\nA:"
},
{
"from": "gpt",
"value": "[-11, 4, -21]"
}
] |
[
{
"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.\nOne example: Category: construction \nWords: excavator, crane, pelican, hoist, upraise\nSolution is here: pelican\nExplanation: A pelican is not related to construction because it is a type of bird.\n\nNow, solve this: Category: chocolate food \nWords: fix, chocolate, pudding, fudge, cake\nSolution:"
},
{
"from": "gpt",
"value": "fix"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nIn this task, you are given a sentence which is either in the Gujarati language or English language. You task is to identify the language of input sentence. Input sentence can be in Gujarari or English language only and also it cannot have two languages at a time.\nPart 2. Example\nA herd of sheep standing together grazing in a pasture.\nAnswer: English\nExplanation: Input sentence is in English language.\nPart 3. Exercise\nA man speaking into a microphone on a stage with a bicycle and dressed in cyclist gear.\nAnswer:"
},
{
"from": "gpt",
"value": "English"
}
] |
[
{
"from": "human",
"value": "Definition: Given a sentence and two mentions from the text (arguments), indicate a phrase (a verb or noun phrase) that describes the relationship between the provided arguments.\nInput: Sentence: 'It is what the Church founded by Christ says it is .', Argument/Subject 1: 'church', Argument/Subject 2: 'christ'\nOutput:"
},
{
"from": "gpt",
"value": "say in"
}
] |
[
{
"from": "human",
"value": "Given a part of privacy policy text, identify the purpose for which the user information is collected/used. The purpose should be given inside the policy text, answer as 'Not Specified' otherwise\nOne example is below.\nQ: The site collects your IP address or device IDs for advertising. Collection happens when you implicitly provide information on the website.\nA: Advertising\nRationale: The given policy text states that it uses user information for 'advertising' explicitly\nQ: You can make a choice about your privacy not described by our label scheme the use of cookies and tracking elements by a third party, which collects or receives it for advertising.\nA:"
},
{
"from": "gpt",
"value": "Advertising"
}
] |
[
{
"from": "human",
"value": "Teacher:In 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.\nTeacher: Now, understand the problem? Solve this instance: [249.085, -35.387, -97.119, -33.367, 35.424]\nStudent:"
},
{
"from": "gpt",
"value": "23.727"
}
] |
[
{
"from": "human",
"value": "In this task, you're given an article and an answer. Your task is to generate the fill-in-the-blank question for this answer based on the given article. The blanks are always at the end of the question, and can be filled with more than one word or phrase.\n\nArticle: For some reason, it takes constant reminders that weprimates need nurturing. In a recent study of 46 babychimpanzee orphans, Kim Bard of the University of Portsmouth in England and her colleagues demonstrated that primate babies that have tight relationships with mother figures do much better oncognitive tests than babies who receive only food, shelter, and friendship with peers. But this is not breaking mews. In fact, it's old news. In the 1950s, Harry Harlow conducted a series of experiments with baby monkeys that showed, without doubt, that lack of love and comfort makes for a crazy monkey. Harlow constructed a cage that included a wire monkey \"mother\" topped with a plastic face. In this wire he fixed Mom with a milk bottle. The cage also held another wire mother covered with terry cloth. The baby monkeys spent all their time with the cloth mother and only went to the wire mother to feed, demonstrating that a soft touch beat something to eat any day. Harlow's monkey work was important because, at the time, child care \"experts\" and everybody's grandmother had a \"no touch, no comfort\" policy toward children. They advised parents not to respond to crying babies, felt babies should sleep alone to grow up independent, and for God's sake put those kids down. But Harlow's work changed all that. Mothers were soon permitted to have their newborns next to them in the hospital. The current chimp research based on Harlow's work shows that mother love not only makes for a psychologically well-adjusted child, but also makes for a smart kid. Bard and her colleagues evaluated the abilities of the chimps when they were 12 months old with standard human tests for children of that age, tests that ask little kids to imitate some action. The highly raised chimps did better than the ones that were not loved, and what do you know, the well-raised chimps did even better than human kids on this small IQ test. So we hear it once again. We are primates, social animals which need care and love. We need to be held and talked to and made to feel that at least one person wants to be with us all the time. And if we get that kind of connection, we are sure to be fine, even better than fine. \n Answer: was nothing new to people about the findings"
},
{
"from": "gpt",
"value": "The study Kim Bard and his colleagues did _ ."
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you will be presented with a passage, and you need to write an **implausible** answer to to fill in the place of \"_\". Your answer should be incorrect, but should not be out of context. Try using words that are related to the context of the passage, but are not the correct answer. Even though there exist multiple wrong answers, we only need a single wrong answer.\n\nJonah Lomu, who tragically died aged just 40 on Wednesday, will forever be remembered for destroying England in the 1995 World Cup semi-final. Aged just 20 at the time, the giant wing scored four tries in Cape Town - one, inside the first two minutes, remains the most iconic moment in the history of the game. Legendary journalist Ian Wooldridge OBE - who wrote for the Daily Mail until his death in 2007 - was there to witness Lomu's superhuman effort. And although his prediction of an All Blacks win in the final the following week proved wide of the mark, no-one sums up Lomu's genius better.New Zealand rugby legend Jonah Lomu died on Wednesday aged 40Lomu made his name at '95 World Cup, scoring four tries against EnglandLate Ian Wooldridge compared him to Pele and Muhammad Ali at the time \n Question:Ironically it brought them the highest score they have ever achieved against the _ but it was small consolation when they also conceded more points than any England team ever has in an international.\n"
},
{
"from": "gpt",
"value": "Jonah Lomu"
}
] |
[
{
"from": "human",
"value": "You are given a math word problem and you are supposed to apply multiple mathematical operators like addition, subtraction, multiplication or division on the numbers embedded in the text to answer the following question and then only report the final numerical answer.\n\nQ: Olivia was making baggies of cookies with 9 cookies in each bag . If she had 13 chocolate chip cookies and 41 oatmeal cookies , how many baggies could she make ?\n\nA: 6\n****\nQ: April 's discount flowers was having a sale where each rose was 9 dollars . If April started with 11 roses and had 8 roses left , how much money did she earn ?\n\nA: 27\n****\nQ: Tiffany had 6 pages of math homework and 4 pages of reading homework . If each page had 3 problems on it , how many problems did she have to complete total ?\n\nA:"
},
{
"from": "gpt",
"value": "30\n****\n"
}
] |
[
{
"from": "human",
"value": "Definition: In this task, you are given a summary for US Congressional and California state bill, your task is to generate a Title for this bill. The preferred titles are under forty words and mention the purpose of the bill.\nInput: Requires the Office Director to establish criteria by regulation for the protection of human subjects in research conducted, supported, or otherwise subject to regulation by the Federal Government (Federal research projects). Provides that in the case of covered agencies: (1) such regulations supersede all regulations for such criteria that were in effect before this Act's enactment date; and (2) the Director has exclusive authority to issue such regulations after such date. Deems current regulations to have been promulgated by the Director and authorizes their continuation or modification by the Director.\nApplies such regulations to each Federal agency that: (1) as of October 1, 1999, was subject to the basic policy under current regulations for protection of human research subjects; and (2) takes appropriate administrative action after such date to provide that regulations under this Act apply to the agency. Authorizes the Director to exempt any Federal research project from such regulations. Continues exemptions under current regulations unless modified by the Director. Applies the following provisions under existing regulations to Federal research projects of an agency that currently is not subject to such provisions only to projects that are approved after this Act's enactment date: (1) additional protections pertaining to research, development, and related activities involving fetuses, pregnant women, and human in vitro fertilization; (2) additional protections pertaining to biomedical and behavioral research involving prisoners as subjects; and (3) additional protections pertaining to children as research subjects.\nSets forth provisions similar to those under existing law that require entities applying to carry out Federal research projects to establish institutional review boards, but replaces the authority of the Secretary of Health and Human Services with that of the Director. Continues the existence of current institutional review boards that meet this Act's requirements.\nRequires the Director to establish an Interagency Coordinating Committee on Protection of Human Research Subjects to develop recommendations on carrying out this Act, review regulations, and report to specified congressional committees.\nProvides that, after this Act's enactment, any office or unit within an agency that was established for the protection of human research subjects in Federal research has only such duties as may be assigned by the Director and authorizes the Director to terminate such office or unit.\nOutput:"
},
{
"from": "gpt",
"value": "Human Research Protection and Promotion Act of 2000"
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: In this task, you are given an input stream, and your task is to produce a grammatically correct version of the input sentence. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a grammatically correct version of the input stream. Stream words are in [] and have been separated with a comma. The sentence can contain words that have case, punctuation, stem-based, intra-word, and digit punctuation errors that need to be corrected. For example, the text should be uppercased/lowercased as per necessity (like the beginning of a sentence, proper nouns, etc.), and digits need to be normalized (6 as six and so on). Note that you don't need to normalize the years. You don't need to fully edit the sentences, if end of the input stream contains sentence fragments, keep them as is.\nPROBLEM: ['our', 'squirrel', 'friend', 'here', 'likes', 'to', 'collect', 'acorns', 'because', 'really', \"that's\", 'how', 'he', 'is', 'able', 'to', 'live', 'and', \"let's\", 'say', 'every', 'day', 'he', 'collects', 'exactly', 'three', 'acorns', 'and', 'so', 'what', \"I'm\", 'curious', 'about', 'is', 'how', 'many', 'acorns', 'will', 'he', 'have', 'after', 'doing', 'this', 'for', 'five', 'days', 'so', 'one', 'way', 'to', 'think', 'about', 'it', 'is', 'every', 'day', 'he', 'is', 'able', 'to', 'collect', 'a', 'group', 'of', 'three', 'acorns', 'so', 'you', 'could', 'view', 'this', 'as', 'maybe', 'what', \"he's\", 'able', 'to', 'collect', 'in', 'day', 'one', 'and', 'then', 'in', 'day', 'two', \"he's\", 'able', 'to', 'collect', 'a', 'second', 'group', 'of', 'three', 'acorns', 'in', 'day', 'three', \"he's\"]\n\nSOLUTION: ['our', 'squirrel', 'friend', 'here', 'likes', 'to', 'collect', 'acorns,', 'because,', 'really,', \"that's\", 'how', 'he', 'is', 'able', 'to', 'live.', 'And', \"let's\", 'say', 'every', 'day', 'he', 'collects', 'exactly', 'three', 'acorns.', 'And', 'so', 'what', \"I'm\", 'curious', 'about', 'is', 'how', 'many', 'acorns', 'will', 'he', 'have', 'after', 'doing', 'this', 'for', 'five', 'days?', 'So', 'one', 'way', 'to', 'think', 'about', 'it', 'is', 'every', 'day', 'he', 'is', 'able', 'to', 'collect', 'a', 'group', 'of', 'three', 'acorns.', 'So', 'you', 'could', 'view', 'this', 'as', 'maybe', 'what', \"he's\", 'able', 'to', 'collect', 'in', 'day', 'one.', 'And', 'then', 'in', 'day', 'two,', \"he's\", 'able', 'to', 'collect', 'a', 'second', 'group', 'of', 'three', 'acorns.', 'In', 'day', 'three,', \"he's\"]\n\nPROBLEM: [\"let's\", 'see', 'if', 'we', 'can', 'write', 'the', 'fraction', '11', 'over', '25', 'or', 'we', 'could', 'call', 'it', '11', '25th', 'to', 'see', 'if', 'we', 'can', 'write', 'that', 'as', 'a', 'decimal', 'and', \"we're\", 'going', 'to', 'round', 'it', 'to', 'the', 'nearest', 'thousands', 'place', 'and', 'so', 'another', 'way', 'of', 'viewing', 'this', '', '11', 'over', '25', 'this', 'is', 'the', 'same', 'thing', 'as', '11', 'divided', 'by', '25', 'so', 'we', 'can', 'literally', 'say', 'we', 'can', 'literally', 'divide', '25', 'into', '11', 'and', 'whatever', 'we', 'get', 'that', 'is', 'going', 'to', 'be', 'the', 'decimal', 'representation', 'of', '11', '25th', 'and', 'since', \"we're\", 'going', 'to', 'go', 'into', 'the', 'into', 'the', 'places', 'less', 'than']\n\nSOLUTION: [\"Let's\", 'see', 'if', 'we', 'can', 'write', 'the', 'fraction', '11', 'over', '25,', 'or', 'we', 'could', 'call', 'it', '11', '25th', 'to', 'see', 'if', 'we', 'can', 'write', 'that', 'as', 'a', 'decimal.', 'And', \"we're\", 'going', 'to', 'round', 'it', 'to', 'the', 'nearest', 'thousandths', 'place.', 'And', 'so', 'another', 'way', 'of', 'viewing', 'this', '', '11', 'over', '25,', 'this', 'is', 'the', 'same', 'thing', 'as', '11', 'divided', 'by', '25', 'so', 'we', 'can', 'literally', 'say', 'we', 'can', 'literally', 'divide', '25', 'into', '11,', 'and', 'whatever', 'we', 'get,', 'that', 'is', 'going', 'to', 'be', 'the', 'decimal', 'representation', 'of', '11', '25th', 'and', 'since', \"we're\", 'going', 'to', 'go', 'into', 'the', 'into', 'the', 'places', 'less', 'than']\n\nPROBLEM: ['last', 'video', 'we', 'observed', 'that', 'benzene', 'exhibits', 'aromatic', 'stabilization', 'and', 'when', 'chemists', 'first', 'made', 'cyclooctatetraene', 'which', '', 'this', 'molecule', 'right', 'here', 'they', 'assumed', 'it', 'would', 'react', 'like', 'benzene', 'because', 'it', 'looks', 'like', 'it', 'has', 'alternating', 'single', 'double', 'bonds', 'and', 'it', 'has', 'a', 'ring', 'and', 'so', 'they', 'just', 'assumed', 'that', 'it', 'would', 'behave', 'like', 'benzene', 'it', 'turns', 'out', 'cyclooctadiene', 'does', 'not', 'react', 'like', 'benzene', 'so', 'benzene', 'did', 'not', 'react', 'the', 'way', 'cyclohexene', 'did', 'up', 'here', 'so', 'cyclohexene', 'will', 'give', 'us', 'a', 'mix', 'of', 'enantiomers', 'when', 'the', 'bromine', 'adds', 'across', '', 'double', 'bond', 'benzene', 'does', 'not', 'do', 'that', 'cyclooctatetraene', 'does', 'as', 'a']\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "['Last', 'video,', 'we', 'observed', 'that', 'benzene', 'exhibits', 'aromatic', 'stabilization.', 'And', 'when', 'chemists', 'first', 'made', 'cyclooctatetraene,', 'which', '', 'this', 'molecule', 'right', 'here,', 'they', 'assumed', 'it', 'would', 'react', 'like', 'benzene.', 'Because', 'it', 'looks', 'like', 'it', 'has', 'alternating', 'single,', 'double', 'bonds,', 'and', 'it', 'has', 'a', 'ring.', 'And', 'so', 'they', 'just', 'assumed', 'that', 'it', 'would', 'behave', 'like', 'benzene.', 'It', 'turns', 'out', 'cyclooctatetraene', 'does', 'not', 'react', 'like', 'benzene.', 'So', 'benzene', 'did', 'not', 'react', 'the', 'way', 'cyclohexene', 'did', 'up', 'here.', 'So', 'cyclohexene', 'will', 'give', 'us', 'a', 'mix', 'of', 'enantiomers', 'when', 'the', 'bromine', 'adds', 'across', '', 'double', 'bond.', 'Benzene', 'does', 'not', 'do', 'that.', 'Cyclooctatetraene', 'does,', 'as', 'a']\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Categorize the comment on the basis of toxicity. If the comment is toxic (harmful, malicious, derogatory, threat, insult, identity attck, etc.) output Yes, otherwise output No.\nProblem:And I eat Wendy's twice a week and have a pro-grade cardiovascular system.\n\nGenetics, circumstance, and moderation all matter, but by all means keep body-shaming people, hand-waving, and equating it somehow to the existence of fast food.\nSolution:"
},
{
"from": "gpt",
"value": "No"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you need to reverse all words of a given length in the sentence. The number of letters in a word determine its length. For example, the length of the word \"apple\" is 5.\nProblem:Sentence: 'an enormous wedding cake is roped off on a sidewalk'. Reverse all words of length '5' in the given sentence.\nSolution:"
},
{
"from": "gpt",
"value": "an enormous wedding cake is depor off on a sidewalk"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you need to replace a letter in the sentence with another given letter.\n\nSentence: 'a professional tennis player leaping for the ball'. Replace the letter 'e' with 'g' in the sentence.\nOutput:"
},
{
"from": "gpt",
"value": "a profgssional tgnnis playgr lgaping for thg ball"
}
] |
[
{
"from": "human",
"value": "instruction:\nGiven a story, answer the question about the story. The question is the last sentence in the input. The story has one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios. Note that there are distractor sentences in each story that are unrelated to the question and are designed to confuse the reader.\nquestion:\nEmily entered the master_bedroom. Ethan entered the master_bedroom. The turnip is in the green_treasure_chest. Ethan exited the master_bedroom. Emily moved the turnip to the green_cupboard. Where was the turnip at the beginning?\nanswer:\ngreen_treasure_chest\n\n\nquestion:\nAlexander entered the hall. Logan entered the hall. The grapes is in the blue_suitcase. Phone rang. Logan exited the hall. Alexander moved the grapes to the green_treasure_chest. Where will Logan look for the grapes?\nanswer:\nblue_suitcase\n\n\nquestion:\nAria entered the workshop. Oliver entered the workshop. The strawberry is in the green_pantry. Oliver exited the workshop. Aria moved the strawberry to the red_treasure_chest. Aria exited the workshop. Oliver entered the workshop. Where will Oliver look for the strawberry?\nanswer:\n"
},
{
"from": "gpt",
"value": "red_treasure_chest\n\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you will be shown an incorrect English sentence. You need to generate a corrected form of the input sentence.\nQ: First , the hunter is the most dengres things in this world for the bird . \nA:"
},
{
"from": "gpt",
"value": "First , the hunter is the most dangerous things in the world for the bird . "
}
] |
[
{
"from": "human",
"value": "In this task, you are given an input list A. You need to extract and sort the unique digits used in the list in ascending order. Return -1 if there is no digit in the list.\nExample: ['q', '31', 'a', 'd', '53', '85', 'p', '77']\nExample solution: 1, 3, 5, 7, 8\nExample explanation: Here, the numbers in the list are '31', '53', '85' and '77', and the unique digits used in the list are '1, 3, 5, 7, 8' in ascending order.\n\nProblem: ['j', 'h', 'q', 'd', '251']\n"
},
{
"from": "gpt",
"value": "Solution: 1, 2, 5"
}
] |
[
{
"from": "human",
"value": "Definition: In this task you need to indicate the plausibility of reasoning for the pronoun coreference relations. Each of the provided inputs contains a sentence with a target pronoun and a sentence that justifies which noun phrase the pronoun refers to. Correct reasons do not need to use all the knowledge from the sentence. The resolution of the pronoun coreference relations typically involve one or multiple following knowledge types about commonsense: First: 'Property', the knowledge about property of objects (e.g., ice is cold). Second: 'Object', the knowledge about objects (e.g., cats have ears). Third: 'Eventuality', the knowledge about eventuality (e.g., 'wake up' happens before 'open eyes'). Forth: 'Spatial', the knowledge about spatial position (e.g., object at the back can be blocked). Fifth: 'Quantity', the knowledge about numbers (e.g., 2 is smaller than 10). Sixth: all other knowledge if above ones are not suitable. You should answer 'Correct' if the reasoning made sense, otherwise, you should answer 'Wrong'.\nInput: Sentence: The sun was covered by a thick cloud all morning, but luckily, by the time the picnic started, it was out.\n Reason: The 'it' refers to the sun because A thick cloud was covered the sun at every morning. \n Question: Is the above reasoning correct or wrong? \nOutput:"
},
{
"from": "gpt",
"value": "Wrong"
}
] |
[
{
"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.\nBased on the given context, craft a common-sense question, especially those that are LONG, INTERESTING, and COMPLEX. The goal is to write questions that are easy for humans and hard for AI machines! To create such questions, here are some suggestions: A. What may (or may not) be the plausible reason for an event? B. What may (or may not) happen before (or after, or during) an event? C. What may (or may not) be a plausible fact about someone (or something)? D. What may (or may not) happen if an event happens (or did not happen)? You can also create other types of questions. DO NOT make your question answerable without looking at the context, or question of which the correct answer can be directly extracted from the context. DO NOT ask a question that requires very specialized knowledge that is not common sense. DO NOT ask too simple or too short questions. Your question must be related to the context and answerable with common sense. Try to add more variations and complexity to the questions.\n\nContext: I was told, in person over the phone, that my shoes were on their way. They have my money. I have no shoes.\nSolution: What may happen before I called them?\nWhy? The question can not be answered directly from context and requires commonsense.\n\nNew input: Context: I ' m not a monster , if that is what you all think . I did not take a perverse pleasure at firing a weapon at a man . All I can think about is who he was .\nSolution:"
},
{
"from": "gpt",
"value": "Why is the narrator rationalizing firing a weapon ?"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given a sentence in Tagalog language, translate the sentence to English language keeping the meaning of the original sentence intact.\nProblem:Tagalog sentence: Ang mga Arabo magalang sa kaalaman ng mahusay na pagsasalita ng Arabic at ang mga diskarte ng retorika alam ang Koran upang maging hindi kukulangin sa mapaghimala.\nSolution:"
},
{
"from": "gpt",
"value": "Those Arabs skilful in the knowledge of the eloquence of Arabic and the techniques of rhetoric knew the Koran to be no less than miraculous."
}
] |
[
{
"from": "human",
"value": "Detailed 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.\nQ: [139, 10, 118]\nA:"
},
{
"from": "gpt",
"value": "[139]"
}
] |
[
{
"from": "human",
"value": "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'.\nOne example: ['238', 'h', '92', 'U', '2799']\nSolution is here: Numbers Win\nExplanation: Here, the count of alphabets is 2, and that of numbers is 3. Since there are more numbers than alphabets, hence the answer is 'Numbers Win'.\n\nNow, solve this: ['x', '8107', '4201', '4515', '4175', '6157', '8025', '1281', 'y', '9', '7551', 'B', '8865', '6121', '9513', '5171', '4335', 'E', '2241', '8617', '705', '6553', '2647', 'V', '8499', 'O', 'g', '3603', '4625', 'z', 'l', 'o', 'p', '1625', 'H', '7375', '2733', '6405', 'U', '9923', 'm', 'z', 'u', 'H', '6765', '8903', '1321', '2775']\nSolution:"
},
{
"from": "gpt",
"value": "Numbers Win"
}
] |
[
{
"from": "human",
"value": "Definition: In this task, you're given a statement, further information available on a particular linked term from the statement, and a question. Your job is to generate the answer to the question by using the information provided. If there is no clear answer obtainable, output 'none'.\nInput: Context: Her only match took place on July 16 at FCW Summer SlamaRama, where she was involved in a battle royal, which was won by Sonia. Link Information: none Question: How many championships did the wrestler who won the battle royal at the FCW Summer SlamaRama on July 16 win?\nOutput:"
},
{
"from": "gpt",
"value": "Answer: none"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given sentences from movie reviews. The task is to classify a sentence as \"POS\" if the sentiment of the sentence is positive or as \"NEG\" if the sentiment of the sentence is negative\nProblem:As action-adventure , this space-based homage to Robert Louis Stevenson 's Treasure Island fires on all plasma conduits .\nSolution:"
},
{
"from": "gpt",
"value": "POS"
}
] |
[
{
"from": "human",
"value": "In this task you will be given an arithmetic operation in Italian and you have to find its answer. The operations 'addition' and 'subtraction' have been replaced with their italian translations i.e you need to perform addition when you see 'aggiunta' and subtraction in case of 'sottrazione'.\nOne example: 10 sottrazione 7\nSolution is here: 3\nExplanation: Here, 'sottrazione' represents the subtraction operation. So, the answer is 3 (10-7=3).\n\nNow, solve this: 8082 aggiunta 3954 sottrazione 6139 sottrazione 6498 aggiunta 8167 aggiunta 9295 sottrazione 8605 sottrazione 1944 sottrazione 6095\nSolution:"
},
{
"from": "gpt",
"value": "217"
}
] |
[
{
"from": "human",
"value": "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'.\nInput: ['d', '3249', 'N', '2307', 'q', 'C', '2111', 'R', 'H', '6829', 'f', '4049', 'P', '1633', '541', 'd']\nOutput:"
},
{
"from": "gpt",
"value": "Alphabets Win"
}
] |
[
{
"from": "human",
"value": "Definition: You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. Your task is to classify the conversation either convey 'No emotion' or 'Happiness' by providing '1' and '0', respectively.\nInput: Person1: Welcome ! Welcome to Little Italy . We're the most Italian family here ! \n Person2: So I've heard . That's why I'm having such a great time . \n Person1: If I hadn't married an Italian man , I probably wouldn't be pregnant so often . And maybe I could raise pigs instead of bambinos ! \n Person2: Huh ? Um ... well , it's nice to see that some people still have big families . \n Person1: It is nice , but it would be nicer if my macho husband would get off his tush and help me . Ha-ha ... Have this . It's from Italy ! \nOutput:"
},
{
"from": "gpt",
"value": "0"
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: 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'.\nPROBLEM: Set1: '{7}', Set2: '{10, 15}'. Is the element '15' in the intersection of Set1 and Set2 ?\n\nSOLUTION: No\n\nPROBLEM: Set1: '{9, 2, 19, 4}', Set2: '{2, 3, 4, 6, 9, 12, 13, 17}'. Is the element '19' in the intersection of Set1 and Set2 ?\n\nSOLUTION: No\n\nPROBLEM: Set1: '{2, 3, 5, 9, 12, 16, 17, 18, 19}', Set2: '{16}'. Is the element '17' in the intersection of Set1 and Set2 ?\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "No\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task if the pronoun is female or gender-neutral you are to replace it with a male pronoun. If there are no pronouns add a male-gendered word to the sentence.\nSee one example below:\nProblem: She designed monumental Loviisa war cemetery in 1920.\nSolution: He designed monumental Lovissa war cemetery in 1920.\nExplanation: The feminine pronoun was changed to a masculine pronoun.\n\nProblem: well my boyfriend always used to take me.\nSolution:"
},
{
"from": "gpt",
"value": "Well my husband always used to take me."
}
] |
[
{
"from": "human",
"value": "In this task, you will be shown a short story with a beginning, two potential middles, and an ending. Your job is to choose the middle statement that makes the story coherent / plausible by writing \"1\" or \"2\" in the output. If both sentences are plausible, pick the one that makes most sense.\n\nBeginning: On the bus it was very crowded. Middle 1: the bus didn't have any open seats. Middle 2: The bus had one open seat that smelled aweful. Ending: As a result, no one sat in the open seat.\n2\n\nBeginning: Sue really wanted a new boots. Middle 1: Sue found a great pair of boots at a thrift store. Middle 2: She didn't find any boots at the store. Ending: Now Sue shops at the thrift stores all the time.\n1\n\nBeginning: Lane played the drums and wanted to be in a band. Middle 1: Lane worked hard at drum lessons. Middle 2: Lane worked hard at cooking lessons. Ending: Soon Lane was playing with the band and loving it.\n"
},
{
"from": "gpt",
"value": "1\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. Given a statement about date and time, state whether the statement is true or false. The number of date/time operands in the statement ranges between 2 and 3. Let's say the values are denoted by t1, t2 and t3. The statements follow one of the following ten templates: 't1 occurs before t2, t1 doesn't occur before t2, t1 occurs after t2, t1 doesn't occur after t2, t1 occurs between t2 and t3, t1 doesn't occur between t2 and t3, t1 occured before t2 but after t3, t1 occured after t2 but before t3, t1 didn't occur before t2 but after t3, t1 didn't occur after t2 but before t3'. The output should be either 'True' or 'False'.\n\nSeptember 30, 1981 occured after September 09, 1989 but before Apr 28, 1972\n"
},
{
"from": "gpt",
"value": "False"
}
] |
[
{
"from": "human",
"value": "Teacher:In 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.\nTeacher: Now, understand the problem? Solve this instance: food is very fresh and amazing !\nStudent:"
},
{
"from": "gpt",
"value": "food was old and stale"
}
] |
[
{
"from": "human",
"value": "Q: In this task you will be given a list of integers. For every element in the list, if the element is positive you should multiply it by 2. If the element is negative you should multiply it by -3. The output should be a list of integers that is the result of applying that logic to the input list.\n Note: A list is presented with comma separated numbers inside two brackets.\n[15, -62, -28, 30, 25, 67, 42, -67, 93, 11, 44]\nA:"
},
{
"from": "gpt",
"value": "[30, 186, 84, 60, 50, 134, 84, 201, 186, 22, 88]"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nA ploynomial equation is a sum of terms. Here each term is either a constant number, or consists of the variable x raised to a certain power and multiplied by a number. These numbers are called weights. For example, in the polynomial: 2x^2+3x+4, the weights are: 2,3,4. You can present a polynomial with the list of its weights, for example, equation weights = [6, 4] represent the equation 6x + 4 and equation weights = [1, 3, 4] represent the equation 1x^2 + 3x + 4. In this task, you need to compute the result of a polynomial expression by substituing a given value of x in the given polynomial equation. Equation weights are given as a list.\nPart 2. Example\nx = 3, equation weights = [4, 2]\nAnswer: 14\nExplanation: Here, the weights represent the polynomial: 4x + 2, so we should multiply 4 by 3, and add it to 2 which results in (4*3 + 2 =) 14.\nPart 3. Exercise\nx = 8, equation weights = [2, 4]\nAnswer:"
},
{
"from": "gpt",
"value": "20"
}
] |
[
{
"from": "human",
"value": "Teacher: You will be given a person's personality, and a history of a conversation this person has had. You will be given four candidate sentences to complete the conversation, based on the context. Choose one and answer with the text.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nPersonality: I like spending time with my friends and family.\nI like listening to all genres of music except country music.\nI like to read a lot of books.\nChat history: -Hi.\n -Hey how are you?\n -Good and yourself?\n -Good, just listening to music and hanging out with my family.\n -What do you do for a living?\n -I am a teacher. How about you?\n -I'm a vet at the animal shelter.\n -That is awesome, what do you like to do for fun?\n -I love running. Its my way to detox.\n -Running is great. Do you have any other hobbies?\n -Not really... what do you teach?\n -I teach reading, I love books and helping children learn how to read.\n -Where are you from?\nCandidates 1) Care to chat with a hamburger lover? Its my fav food. 2) I bet that is a great place to draw. I sell art for a living. 3) I am from Illinois, how about you? 4) They're great pets! I just started an organic only diet.\nSolution: I am from Illinois, how about you?\nReason: The third choice is the best answer to the last part of the conversation, that asks where the person is from.\n\nNow, solve this instance: Personality: A hobby of mine is the drums.\nOne of my favorite artists is drake.\nI also enjoy cooking.\nI like to go out to eat.\nChat history: -Hi, I just finished listening to Drake. What do like doing?\n -How are you doing tonight.\n -I like messing around on the drums.\n -I like to play sport and baking.\n -I really like cooking too. Going out to eat is also a fun thing.\n -It is so sad what happen in Fl.\n -You mean with the hurricane?\n -Yes my son was with his dad in Fl when it all happen.\nCandidates 1) Cooking. I'm a big foodie. 2) Did they get flooded at their place? 3) I'm a girl and I've several girls of own. 4) Yeah I do, its a lot of fun.\nStudent:"
},
{
"from": "gpt",
"value": "Did they get flooded at their place?"
}
] |
[
{
"from": "human",
"value": "Q: In this task, a passage will be given and the goal is to generate a question about temporal relations based on that passage. A temporal relation describes the relation between two things with respect to time e.g., something happens/starts/terminates/... immediately/shortly/usually/... before/after/during/... something else.\n Your question should include an event, or ask about an event, and should not be a yes/no question.\nPassage: The unrest blew into a full-scale armed uprising in the south, with the port town of Vlore at its hub. Prodi told reporters: \"Italy has an important mission to reconstruct Albania.\"\nA:"
},
{
"from": "gpt",
"value": "What event has already finished?"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you're given the title of a five-sentence story and the first four sentences. Your job is to write the last sentence of the story to not connect with the rest of the story. Ensure that the generated sentence is contextually relevant to the story.\nSee one example below:\nProblem: 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.\nSolution: He left in a huff for having his ideas mocked.\nExplanation: Marcus is buying clothes for a business event and not presenting an idea.\n\nProblem: Title: Blake's Burger. Sentence 1: Blake made a burger for dinner. Sentence 2: He used a huge amount of ground beef. Sentence 3: The beef wasn't allowed to cook thoroughly. Sentence 4: Blake ate his burger anyway.\nSolution:"
},
{
"from": "gpt",
"value": "Because it was thundering her mom made her come inside."
}
] |
[
{
"from": "human",
"value": "In this task, you're given the title of a five-sentence story and the first four sentences. Your job is to write the last sentence of the story such that it seamlessly connects with the rest of the story.\nQ: Title: Ike's Mickey Shoes. Sentence 1: Ike's mom was at a garage sale. Sentence 2: She remembered that Ike loved Mickey Mouse. Sentence 3: She found a pair of Mickey Mouse shoes there. Sentence 4: Ike bought the shoes for her son.\nA: "
},
{
"from": "gpt",
"value": "Ike was so happy when his mom gave him his new shoes."
}
] |
[
{
"from": "human",
"value": "In this task, you're given four sentences of a story written in natural language, and one last sentence (Sentence5). Your job is to classify whether the last sentence completes the rest of the story coherently or not by providing 'Yes' or 'No'.\n\nQ: Sentence1: Pearl collected CDs with ugly cover art. Sentence2: She prized a jazz CD with two dolphins photoshopped together. Sentence3: Her sister stole the CD while angry with her. Sentence4: Pearl's heart sank and she implored her sister to return it. \n Sentence5: Pearl's sister was seeking revenge.\n\nA: Yes\n****\nQ: Sentence1: I hired a social media manager. Sentence2: I thought they would drive more traffic to my website. Sentence3: They spent most of their time reading other people's posts. Sentence4: My traffic actually went down in the following month. \n Sentence5: I decided to fire my new social media manager.\n\nA: Yes\n****\nQ: Sentence1: Sai normally hated picture days at school. Sentence2: They were tedious and he never looked as nice as some other kids. Sentence3: To try and help Sai feel better, his mom bought him a new sweater. Sentence4: Sai wore the sweater to picture day and got a lot of compliments. \n Sentence5: Sal felt great.\n\nA:"
},
{
"from": "gpt",
"value": "Yes\n****\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you're given the title of a five-sentence story and the first four sentences. Your job is to write the last sentence of the story to not connect with the rest of the story. Ensure that the generated sentence is contextually relevant to the story.\nProblem:Title: Too Much Wine. Sentence 1: Tom had a blind date. Sentence 2: He was nervous about it. Sentence 3: He got to the restaurant early and started drinking. Sentence 4: After a while he had too many glasses of wine.\nSolution:"
},
{
"from": "gpt",
"value": "They booked a hotel in Waikiki and had a staycation for a whole week."
}
] |
[
{
"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: ['9989', 'B', 'j', 'T', 'X', 'C', 'J', '2961', 'D', 'P', '1259', 'h', '6903', '1169', 's', 'o', 'P', '1921', '5553', 'h', '6713', 'W', '179', '2763', '4437', 'h', '4987', 'V', 'L', '9495', '717', '7263', 'O', '4283', '7805', 'l', 'Z', 'S']\nA: "
},
{
"from": "gpt",
"value": "17"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you need to count the number of words in a sentence that end with the given letter. Answer with numbers and not words.\nProblem:Sentence: 'a dog is laying on a blanket by a toy'. How many words end with the letter 'y' in the sentence.\nSolution:"
},
{
"from": "gpt",
"value": "2"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to determine if the two sentences clearly agree/disagree with each other, or if this can't be determined. Indicate your answer as yes or no respectively.\nOne example is below.\nQ: Sentence 1: Next to the MGM Grand you will find M and M World. Sentence 2: The candy has many fans who love its attractions.\nA: no\nRationale: It is not clear that M and M world is popular.\nQ: Sentence 1: i didn't know you could do that Sentence 2: I didn't know you could seal a door with putty.\nA:"
},
{
"from": "gpt",
"value": "no"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a list. This list contains many lists of integers. The list is several items written within a []. Your task is to find the maximum number among the members of each inner list. The output should be a list comprised of the maximums with the same order as the internal lists.\n\nExample input: [[5, 3], [2, 9, 8], [3, 3], [5, 2, 7, 1]]\nExample output: [5, 9, 3, 7]\nExample explanation: Input of this example is a list containing four inner lists. The maximum value of the first inner list is 5, the maximum value of the second list is 9, the maximum value of the third list is 3, and the maximum value of the fourth list is 7. So the output should be [5, 9, 3, 7], and this is a good example.\nQ: [[5, 56], [-32, -191], [5, -174, -126, 1], [-111, -7, -102, -131]]\nA:"
},
{
"from": "gpt",
"value": "[56, -32, 5, -7]"
}
] |
[
{
"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 integers. You should remove all of the integers that are divisible by 3 from the list. If every integer in the input list is divisible by 3 then an empty list should be returned. Zero is divisible by 3.\n\n[2, 5, 9, 6, 11]\nSolution: [2, 5, 11]\nWhy? 6 and 9 are removed from the list because they are divisible by 3.\n\nNew input: [-39, 7]\nSolution:"
},
{
"from": "gpt",
"value": "[7]"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nIn this task, you will be presented with a question in Dutch language, and you have to write the location names from the question if present. B denotes the first item of a phrase and an I any non-initial word. Identifier used for the location name - LOC. . There can be instances with no location name entity, then return 'None'.\nPart 2. Example\nJean Alavoine ( Fra )\nAnswer: Fra: B-LOC\nExplanation: In the given sentence, Fra is identified as the location, which is correct.\nPart 3. Exercise\nOp basis waarvan verbiedt de politie het skaten ?\nAnswer:"
},
{
"from": "gpt",
"value": "None"
}
] |
[
{
"from": "human",
"value": "In 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 write the character's motivation by doing a specific job, which is given in the sentence. You can use context to find the motivation; however, all the inputs do not provide context. Also, in some inputs, there can be zero motivation; output, 'None' in this case.\n\nExample Input: Context: Raynard forgot to study for a big exam. He failed the test. He begged his teacher for a chance to retake the test. The teacher allowed Raynard to retake the test. \n Sentence: Raynard got an A grade on the retake. \n Character: Raynard\nExample Output: to show he can do it if he study.\n\nExample Input: Context: Colin worked as an on-call electrician. He was called in to help rewire a house for a small family. Collin was very kind to the family while he worked on their house. The children of the family had the idea to make Collin a treat. \n Sentence: On his last day of work, Collin received a batch of fresh cookies. \n Character: Colin\nExample Output: None\n\nExample Input: Context: Kelly's toddler was suffering from a horrible cough. \n Sentence: It was keeping her awake at night. \n Character: Toddler\nExample Output:"
},
{
"from": "gpt",
"value": "to clear his lungs out\n\n"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nGiven a premise, an initial context, an original ending, and a counterfactual context, the task is to generate a new story ending aligned with the counterfactual context and as close to the original ending as possible. Each instance consists of a five-sentence story. The premise is the first sentence of a story, and the second sentence, which is the initial context, provides more information about the story's context and the story's general plot. The original ending is the last three sentences of the story. Also, a counterfactual context is a slight modification to the initial context. You should write a new story ending that edits the original story ending as little as possible to regain coherence with the counterfactual context. To sum up, you should write the last three sentences of a story based on the premise(first sentence) and the counterfactual context(second sentence) of the story.\n\nPremise: Susie was sitting on her barstool. \n Initial Context: She kept kicking the counter with her feet. \n Original Ending: Suddenly, her kick sent her falling backwards. The chair hit the ground with a thud and broke. Susie hurt her head and was really scared. \n Counterfactual Context: She kept herself steady with her feet.\nSolution: Suddenly, an earthquake sent her falling backwards. The chair hit the ground with a thud and broke. Susie hurt her head and was really scared.\nWhy? The generated new ending is perfect. It considers the counterfactual context and changes required parts in original ending.\n\nNew input: Premise: Carlos has been single for several Year's. \n Initial Context: One day Carlos and his friend Dan go to a dance club. \n Original Ending: Carlos meets a nice girl there and they exchange phone numbers. The next week they go out for a cup of coffee. Carlos hopes he has finally met someone he can love. \n Counterfactual Context: One day Carlos and his friend decided not to go to their usual dance club.\nSolution:"
},
{
"from": "gpt",
"value": "Carlos meets a nice girl there and they exchange phone numbers. The next week they go out for a cup of coffee. Carlos hopes he has finally met someone he can love. "
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given a question. You have to answer the question based on your information.\n\nWho did the 47th Governor appoint as a justice of the Supreme Court of Texas?\nOutput:"
},
{
"from": "gpt",
"value": "Judge Debra Lehrmann"
}
] |
[
{
"from": "human",
"value": "You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. Your task is to label each of the continuous conversations done by one speaker with the emotion detected in that particular part. Your labels can be one among the following: 'No emotion', 'surprise', 'happiness', 'sadness', 'anger', 'disgust'.\n\nEx Input:\n Person1: I'm afraid I've spilt ink all over the table-cloth . \n Person2: Oh , never mind about that . \n Person1: I'm terribly sorry . Won't you let me pay for it ? \n Person2: No , I won't hear of it . \n\nEx Output:\nNo emotion,No emotion,No emotion,No emotion\n\n\nEx Input:\n Person1: Let me hold the door for you , miss . \n Person2: Thank you . You're very kind . \n\nEx Output:\nhappiness,happiness\n\n\nEx Input:\n Person1: The weather is terrible . \n Person2: Yes . It was sunny and warm yesterday but the wind is really blowing hard now . \n Person1: I'm wearing my heavy jacket . \n Person2: I'm going to put on more clothes , too . \n Person1: Will it snow today ? \n Person2: I don't know . Do you like snowing ? \n Person1: Yes , when it snows , every where is white . It's very beautiful . \n Person2: You can read the newspaper . Maybe it will tell you whether it will snow or not . \n Person1: Good idea . \n\nEx Output:\n"
},
{
"from": "gpt",
"value": "No emotion,No emotion,No emotion,No emotion,No emotion,No emotion,happiness,happiness,happiness\n\n\n"
}
] |
[
{
"from": "human",
"value": "Given two entities as input, classify as \"yes\" if second entity is the part of the first entity. Otherwise classify them as \"no\". These are entities of meronym In linguistics, meronymy is a semantic relation between a meronym denoting a part and a holonym denoting a whole. In simpler terms, a meronym (i.e., second entity) is in a part-of relationship with its holonym (i.e., first entity).\nOne example is below.\nQ: Entity 1: plant \n Entity 2: leaf\nA: yes\nRationale: The answer is correct. Because the leaf is part of the plant. Therefore, here leaf is meronym and the plant is holonym.\nQ: Entity 1: matrix \n Entity 2: cellulose fibre\nA:"
},
{
"from": "gpt",
"value": "yes"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nYou need to answer the question 'Are the given steps in order?', given a set of steps describing a process. Your answer must be either Yes or No. If the answer is No, that means the steps are out of order and do not make sense in the order they are in. If the answer is Yes, that means the steps are in order and make sense in the order that they are in. A set of steps are not in order if the steps reference information that is introduced in a later step\n\n ['Food', 'Water enter the body', 'Bloodstream', 'Food and water enter the pancreas', 'The pancreas breaks down carbs', 'Helps digest other foods and liquids.'] \nOutput:"
},
{
"from": "gpt",
"value": " Yes "
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given inputs i, j, and A, where i and j are integers and A is a list. You need to 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.\nProblem:2, 9, ['a', 'n', '8853', '4119', '3525', 'X', 'c', '7039', '8483', '8003', '7521', 'K']\nSolution:"
},
{
"from": "gpt",
"value": "84837039cX352541198853n"
}
] |
[
{
"from": "human",
"value": "Teacher: In this task, you are given sentences from movie reviews. The task is to classify a sentence as \"POS\" if the sentiment of the sentence is positive or as \"NEG\" if the sentiment of the sentence is negative\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nIt 's a lovely film with lovely performances by Buy and Accorsi .\nSolution: POS\nReason: The sentiment of the sentence is positive. Hence, the label is 'POS'.\n\nNow, solve this instance: A movie that falls victim to frazzled wackiness and frayed satire .\nStudent:"
},
{
"from": "gpt",
"value": "NEG"
}
] |
[
{
"from": "human",
"value": "Given an trivia question precisely answer the question with a word/phrase/name. External resources such as Wikipedia could be used to obtain the facts.\n\nEx Input:\nWho became President of Germany in June 2010?\n\nEx Output:\nchristian wulff\n\n\nEx Input:\nWhich Oscar winning director was at one time married to James Cameron?\n\nEx Output:\nkathryn bigelow\n\n\nEx Input:\nWhich popular Welsh entertainer wrote the First World War song Keep the Home Fires Burning?\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "ivor novello\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: obscene and non-obscene. A comment is obscene if it is considered offensive to the public sense of decency, for example because it too obviously relates to sex or contains language regarded as taboo in polite usage.\nExample: Comment: Damn! Another cloudy day, and it's all Obama's doing!\nExample solution: Obscene\nExample explanation: This is obscenity because it hints on sexual content that is offensive to the public sense of decency.\n\nProblem: Comment: It's a false Christianity that supposes one can love someone by going along with their rejection of God's will, and even \"celebrate it\"!\n\nIt's a false Christianity to suppose that one have a \"private interpretation\" of the divine positive law. \n\nIt's a false Christianity to think that funerals are merely our action, and that their main purpose is \"to give us closure\".\n\n'Loving our neighbor as yourself' is much much much bigger than you're thinking about. \n\nAnd it is telling that you left out the first part of that passage. \n\nChristianity is about learning to love with the very heart of Christ, which took Him to the Cross, in obedience to His Father and out of love for us.\n\nThe little view of Christianity generates a bunch of sad and petulent people.\n"
},
{
"from": "gpt",
"value": "Solution: Non-obscene"
}
] |
[
{
"from": "human",
"value": "Q: Translate the given Spanish text to English\nThe amount of activated nitrogenous compound and non-oxidizing biocide is selected to result in a synergistic biocidal effect.\nA:"
},
{
"from": "gpt",
"value": "La cantidad del compuesto nitrogenad, activado, y el biocida no oxidante se elige para obtener un efecto biocida sinergico."
}
] |
[
{
"from": "human",
"value": "In this task you will be given a list of strings and you need to concatenate them.\n\n['G', 'in', 'S', 'By', 'n', 'z', 'otherwise', 'm', 'H', 'alluded', 'U', 'E', 'at', 'I']"
},
{
"from": "gpt",
"value": "GinSBynzotherwisemHalludedUEatI"
}
] |
[
{
"from": "human",
"value": "This task is about using the specified sentence and converting the sentence to Resource Description Framework (RDF) triplets of the form (subject, predicate object). The RDF triplets generated must be such that the triplets accurately capture the structure and semantics of the input sentence. The input is a sentence and the output is a list of triplets of the form [subject, predicate, object] that capture the relationships present in the sentence. When a sentence has more than 1 RDF triplet possible, the output must contain all of them.\nQ: Bacon sandwiches are popular in the UK and condiments are ingredients used in them.\nA: "
},
{
"from": "gpt",
"value": "[['Bacon sandwich', 'COUNTRY', 'United Kingdom'], ['Bacon sandwich', 'INGREDIENT', 'Condiment']]"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you are given a sentence which is either in the Swedish language or English language. You task is to identify the language of input sentence. Input sentence can be in Swedish or English language only and also it cannot have two languages at a time.\nInput: The challenge is to make the system the very best.\nOutput:"
},
{
"from": "gpt",
"value": "English"
}
] |
[
{
"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.\n\nEx Input:\n[-710, 977, -491, -5, -961, -44, -203, 56, -234, -556, -356, 169]\n\nEx Output:\n[-710, 980, -490, 0, -960, -40, -200, 60, -230, -560, -360, 170]\n\n\nEx Input:\n[184, -554, -959, 376, -783, -481, -86]\n\nEx Output:\n[180, -550, -960, 380, -780, -480, -90]\n\n\nEx Input:\n[-547, 601, -305, 570, 719, 667, 757, -846, 589, 434]\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "[-550, 600, -300, 570, 720, 670, 760, -850, 590, 430]\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given news articles and you need to generate a highlight, i.e., a short summary, with a maximum length of 10 lines.\n\n(CNN) -- A former NFL player and his mother have been indicted in a scheme to steal more than $690,000 by fraudulently obtaining five home equity loans in six days, according to the New Jersey Attorney General's Office. Irving Fryar, 51, and his mother, Allene McGhee, 72, were charged with second-degree conspiracy and theft by deception in New Jersey Superior Court Wednesday. The indictment alleges that Fryar schemed with McGhee to obtain five home equity loans totaling more than $690,000 between December 16 and 21, 2009, using McGhee's Willingboro home as collateral for all of the loans. The pair allegedly deceived five banks by acquiring the loans within six days and purposefully failing to disclose the existence of any other loans. The indictment further charges that McGhee's loan applications falsely claimed that she earned thousands of dollars a month as an event coordinator for her son's church, New Jerusalem House of God in Burlington County. Fryar himself allegedly received or spent more than $200,000 of the fraudulently obtained loan proceeds, the attorney general's office said. Fryar and McGhee made only a few payments on four of the loans, and those banks eventually wrote the loans off as losses, authorities said. \"This is not a case in which Mr. Fryar and his mother simply omitted or misstated information on loan applications,\" said acting Attorney General John Hoffman. \"This indictment alleges that they engaged in an elaborate criminal scheme that was designed to defraud these banks of hundreds of thousands of dollars.\" Neither Fryar nor McGhee responded to CNN's requests for comment. It is unclear whether either has hired an attorney. A court date has not yet been set, according to the attorney general's office. Between 1984 and 2000, Fryar played for four NFL teams: the New England Patriots, the Miami Dolphins, the Philadelphia Eagles and the Washington Redskins. He is the head football coach at Robbinsville High School in Robbinsville, New Jersey. CNN's Rob Frehse contributed to this report.\nEx-football player and his mother took out five home loans, indictment says .\nIrving Fryar and Allene McGhee secured loans over six days in 2009, papers say .\nThe pair got $690,000 from the loans, the New Jersey Attorney General's Office says .\nFryar played for four teams from 1984 to 2000; he's now a high school football coach .\n\n(CNN) -- Dancers have put on a dazzling display atop extravagant floats at the legendary annual Rio Carnival. Thousands of revelers cheered as dancers shimmied and shook their colorful costumes through the streets of the Brazilian city. Seven-year-old Julia Lira took her place as the drum corps queen for the Viradouro School of Samba despite criticism that she was too young to fill a role normally reserved for voluptuous adult dancers.\nParade of color during annual Rio Carnival in Brazil .\nDancers included seven-year-old Julia Lira, despite criticism that she was too young .\n\n(CNN) -- On Monday, news broke that about 200 girls had been kidnapped from their school in Chibok, in the northeastern state of Borno -- a region at the center of Nigeria's five-year terrorist insurgency. The very next day, the Nigerian military announced that all but nine of the girls had been rescued. This turned out to be untrue. The school's principal and the girls' parents complained that the girls were still missing. In August last year, a military spokesman announced the death of Abubakar Shekau, the leader of Islamist extremist group Boko Haram, at the hands of the military. But like the news of the release of the schoolgirls, it proved to be fiction. 'Misleading sources' Incidents like this have come to shape the way the military is perceived in the wildly unpredictable battle against Boko Haram. Posts on the military's social media accounts regularly boast of \"smoking out\" or ambushing terrorists or recovering weapons -- often written in way that brings to mind Iraq's infamous former information minister under Saddam Hussein, dubbed \"Comical Ali,\" who claimed coalition forces were in retreat even as American tanks rolled almost unchallenged across the country in 2003. Like him they've also ended up pinning the blame for inaccurate reporting on \"misleading\" sources. Even when there is truth to its narratives -- and there have been major successes, including a crackdown that started in early 2013 that killed several top Boko Harem commanders and driven others across the border into Chad, Niger and Cameroon -- the triumphalism seems odd when juxtaposed with the harsh reality of events like the Chibok abduction, or the one at another government school in neighboring Yobe State in February, in which more than fifty schoolboys were murdered in their dormitories, with nary a soldier in sight until several hours later. Perhaps the military resorts to this impulsively buoyant tone because it believes it cannot afford to sound anything otherwise. Or perhaps it's simply because it can get away with it -- because the Nigerian authorities have a long and remarkable history of getting away with anything they say. That tenuous relationship with fact makes it relatively easy for senior government officials to publicly dispute government finances to the tune of billions of dollars; and for an assortment of newspaper headlines to display wildly differing casualty figures the morning after a bombing incident. Death 'cheap and plentiful' And then there's the scale of Nigeria's tragedies. For a country that is not at war, death is cheap and plentiful. So cheap and so sweeping in its audacity that Nigerians readily make jokes about it. That might help explain the trademark blunted edge of Nigerian outrage. If it happens often enough, the mind is soon inured, and eagerly accepting of the sense of resignation that might offer the best protection against the emotional impact of the next cycle of negative breaking news. All of the above combine to create the context in which the Nigerian military -- wielding political power for 29 of Nigeria's first 39 years after independence -- has learned to operate. Not since the civil war, almost 50 years ago, has it been tested this much. The closest it got were the lengthy tours of duty in Liberia and Sierra Leone, in which it played a prominent role at the head of the West African ECOMOG Force, intended more as a \"peacekeeping\" unit than a combat force. Indeed what we are seeing may be evidence of its struggle to adapt to new rules of engagement, fighting an enemy driven by convictions much deeper than those displayed by the pro-democracy activists and diamond-obsessed rebels it contended with in the 1990s; possessing access to sophisticated weapons, and operating in terrain far better suited to insurgents than conventional armies. Abuse claims . The increasing militarization of the troubled zones has since spurred accusations of human rights abuses, from local and international observers. An International Crisis Group report from April 2014 has called for an end to the use of \"heavy-handed military and police methods that risk pushing yet more restless, jobless and frustrated youths into violence and extremism.\" Communication strategies also require overhaul. In the age of social media, the military needs to realize that propaganda is now a lot more likely to be found out and discredited. News reports suggest that the military, long hampered by aging hardware, is now acquiring new weapons and equipment. That's heartwarming. In a country where institutional graft is the rule and not the exception, it is crucial to ensure that the military budgets are spent to boost the military's capability, and troops' morale -- and not pocketed by bigwigs. International cooperation also needs to be stepped up; and it does seem that the government is now more willing than ever to work with Europe and America. Nigerians have long been wary of allowing the American military the sort of foothold it has in countries like Yemen and Pakistan, but there's certainly room for more intense cooperation that does not involve abdicating total control. Finally the military will need to prepare to adapt itself to the reality of the government's planned shift to a \"soft\" counter-terrorism strategy, embodied in a document unveiled by National Security Adviser, Sambo Dasuki, a retired Army Colonel, in March. Amid the backlash it has faced recently, the beleaguered military can count on the support of a growing number of Nigerians, who think that it is being under appreciated for the work it is doing. Just this week a \"Support The Nigerian Military\" page launched on Facebook, in honor of \"our military men and women on the field who risk their lives daily to keep us safe.\"\n"
},
{
"from": "gpt",
"value": "Ogunlesi: Nigeria's military has issued incorrect statements in fight against extremists .\nOften blame their inaccurate reporting on \"misleading sources,\" he says .\nOgunlesi says the military may be trying to paint a constantly positive picture .\nOgunlesi says it has had some successes in its five-year war with Islamist extremists .\n\n"
}
] |
[
{
"from": "human",
"value": "Given a trivia question, classify broad topical category from this list: 'theater', 'geology', 'book', 'tv', 'astronomy', 'aviation', 'military', 'government', 'boxing', 'projects', 'metropolitan_transit', 'law', 'venture_capital', 'broadcast', 'biology', 'people', 'influence', 'baseball', 'spaceflight', 'media_common', 'cvg', 'opera', 'olympics', 'chemistry', 'visual_art', 'conferences', 'sports', 'language', 'travel', 'location', 'award', 'dining', 'martial_arts', 'comic_strips', 'computer', 'user', 'tennis', 'music', 'organization', 'food', 'event', 'transportation', 'fictional_universe', 'measurement_unit', 'meteorology', 'distilled_spirits', 'symbols', 'architecture', 'freebase', 'internet', 'fashion', 'boats', 'cricket', 'film', 'medicine', 'finance', 'comic_books', 'celebrities', 'soccer', 'games', 'time', 'geography', 'interests', 'common', 'base', 'business', 'periodicals', 'royalty', 'education', 'type', 'religion', 'automotive', 'exhibitions'.\n\n[Q]: Who wrote 'The Carpet People', 'Hogfather', 'The Last Continent', 'Men At Arms', and 'Mote'?\n[A]: book\n\n\n[Q]: The second longest river in China, the Yellow River, is known locally as what?\n[A]: location\n\n\n[Q]: Ethanol and isopropyl are types of what?\n[A]:"
},
{
"from": "gpt",
"value": "chemistry\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you're given the title of a five-sentence story and the first four sentences. Your job is to write the last sentence of the story to not connect with the rest of the story. Ensure that the generated sentence is contextually relevant to the story.\n\nQ: Title: The Wet Shirt. Sentence 1: Will had been swimming at the lake with his friends. Sentence 2: It was time to get dressed and head back home. Sentence 3: Will was trying to put his shirt back on but found it soaking wet. Sentence 4: He tried his best to squeeze the water from the shirt.\n\nA: Ethan's coach dressed up as a vampire baseball player.\n****\nQ: Title: Shy. Sentence 1: Dennis was interested in science. Sentence 2: He participated in the science fair. Sentence 3: He had a great project, but he was very shy. Sentence 4: He couldn't speak up when asked to explain his project.\n\nA: Aaron was pleased with his decision.\n****\nQ: Title: New boots. Sentence 1: Don wanted a pair of boots. Sentence 2: He already had a few pairs. Sentence 3: He decided to treat himself to another. Sentence 4: He was excited when he found a sale.\n\nA:"
},
{
"from": "gpt",
"value": "Timothy's boss still didn't fire him.\n****\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given a piece of financial news and its polarity, classify it into 'true' if the polarity is correct and classify into 'false' if the polarity is incorrect. Output must be 'true' or 'false'. \nProblem:news:Operating profit was EUR 139.7 mn , up 23 % from EUR 113.8 mn .\npolarity:negative\nSolution:"
},
{
"from": "gpt",
"value": "false"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\nInput: Sentence 1: Two kids, one in a white shirt and one in a black shirt, laying on pillows. Sentence 2: The children are wearing all gree clothing.\nOutput:"
},
{
"from": "gpt",
"value": "Two kids are wearing shirts."
}
] |
[
{
"from": "human",
"value": "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.\n\nSomeone ate my rocks.\nSomeone ate my jellybeans."
},
{
"from": "gpt",
"value": "first"
}
] |
[
{
"from": "human",
"value": "Given a scientific question, generate a correct answer to it.\nExample: Who proposed the theory of evolution by natural selection?\nExample solution: darwin\nExample explanation: This is a direct fact that Charles Darwin proposed the theory of evolution.\n\nProblem: Bacteria may become untreatable if they develop what in response to multiple antibiotics?\n"
},
{
"from": "gpt",
"value": "Solution: resistance"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you're given the title of a five-sentence story and the first four sentences. Your job is to write the last sentence of the story to not connect with the rest of the story. Ensure that the generated sentence is contextually relevant to the story.\nInput: Title: Linda loses her Job. Sentence 1: Linda was a very hard working woman. Sentence 2: She felt like she wasn't getting paid fairly. Sentence 3: She stormed into her bosses office. Sentence 4: Demanding a raise to rival that of her male counterparts.\nOutput:"
},
{
"from": "gpt",
"value": "Charles was happy to be learning to play tennis."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task you are given a story and a question regarding that story. You must judge whether the question is answerable based on the info given to you. Label the instances as \"Answerable\" or \"Not Answerable\" based on your judgment. the story and the question are separated by a new line character.\nProblem:Alexis was from Chile. Alexis played a lot of soccer in the street. Alexis became very good at soccer. Alexis had a tryout with a professional team. Alexis made the team!\nWhy did Alexis make the team?\nSolution:"
},
{
"from": "gpt",
"value": "Answerable"
}
] |
[
{
"from": "human",
"value": "You're given a fill-in-the-blank question where the answer is PersonX. You need to minimally change the given question so that the answer flips to PersonY. This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"sympathetic\" to \"stern\"). You should not change any content in the given question beyond a word or two i.e. the trigger word/phrase. PersonX and PersonY should not be equally likely to fill the blank. For your question, PersonY should be a well-agreed answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people or generic names (e.g., Donald Trump, John Doe, etc.) in your question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that PersonX and PersonY have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY. Although there are many correct answers, you only need to write one of them.\nExample: Context word: upset. \nQuestion: PersonX yelled at PersonY because _ was so upset about the news. \nAnswer: PersonX.\nExample solution: PersonX comforted at PersonY because _ was so upset about the news.\nExample explanation: On replacing the trigger word \"yelled\" with its antonym \"comforted\", the answer flips to PersonY which is as per the given instruction. So, this is a valid question.\n\nProblem: Context Word: hair. \nQuestion: PersonX's hair is longer than PersonY's because _ has decided to donate his hair to locks of love. \nAnswer: PersonX\n"
},
{
"from": "gpt",
"value": "Solution: PersonX's hair is shorter than PersonY's because _ has decided to donate his hair to locks of love."
}
] |
[
{
"from": "human",
"value": "In this task you're given a question and you have to paraphrase the question to create the output question while retaining the meaning of the original question.\nOne example: What can one do after MBBS?\nSolution is here: What do i do after my MBBS ?\nExplanation: In this example both the question ask the same thing about what to do after MBBS hence second question is the correct output \n\nNow, solve this: How do I know my shoe size?\nSolution:"
},
{
"from": "gpt",
"value": "How can I tell if my Nike running shoes are a wide size?"
}
] |
[
{
"from": "human",
"value": "In this task you will be given a passage and a yes/no question based on the passage. You should answer the question using the information from the passage.\n\nInput: Consider Input: passage: The 2018 Major League Baseball All-Star Game was the 89th Major League Baseball All-Star Game. The game was hosted by the Washington Nationals and was played at Nationals Park on July 17, 2018. It was televised nationally by Fox. The American League beat the National League 8--6, in 10 innings.\n question: is the all-star game being played?\n\nOutput: No\n\n\nInput: Consider Input: passage: In traffic laws, a hit-and-run is the act of causing a traffic accident and not stopping afterwards. It is considered a supplemental crime in most jurisdictions.\n question: is a hit and run a criminal offense?\n\nOutput: Yes\n\n\nInput: Consider Input: passage: The 21 World Cup tournaments have been won by eight national teams. Brazil have won five times, and they are the only team to have played in every tournament. The other World Cup winners are Germany and Italy, with four titles each; Argentina, France and inaugural winner Uruguay, with two titles each; and England and Spain with one title each.\n question: has the u s ever won a world cup?\n\n"
},
{
"from": "gpt",
"value": "Output: No\n\n\n"
}
] |
[
{
"from": "human",
"value": "Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)].\nQ: [\"let's\", 'explore', 'a', 'few', 'more', 'methods', 'for', 'solving', 'systems', 'of', 'equations', \"let's\", 'say', 'I', 'have', 'the', 'equation', '3x', 'plus', '4y', 'is', 'equal', 'to', '2.5', 'and', 'I', 'have', 'another', 'equation', '5x', '5x', 'minus', '4y', 'is', 'equal', 'to', 'twenty', 'five', 'point', 'five', 'and', 'we', 'want', 'to', 'find', 'an', 'x', 'and', 'y', 'value', 'that', 'satisfies', 'both', 'of', 'these', 'equations', 'if', 'we', 'think', 'of', 'it', 'graphically', 'this', 'would', 'be', 'the', 'intersection', 'of', 'the', 'lines', 'that', 'represent', 'the', 'solution', 'sets', 'to', 'both', 'of', 'these', 'equations', 'so', 'how', 'can', 'we', 'proceed', 'it', 'when', 'we', 'saw', 'in', 'substitution', 'we', 'like', 'to', 'eliminate', 'one', 'of', 'the', 'variables', 'we']\nA: "
},
{
"from": "gpt",
"value": "['CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF']"
}
] |
[
{
"from": "human",
"value": "Q: Given an adjective, generate its antonym. An antonym of a word is a word opposite in meaning to it.\nbicameral\nA:"
},
{
"from": "gpt",
"value": "unicameral"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a dialogue between a user and an assistant, where users and assistants converse about geographic topics like geopolitical entities and locations. The task here is to find if the dialogue is by the user or assistant. Classify your answers into user and assistant.\nQ: Well, in 1901, the borders were included within the boundaries of the Colonies of New Zealand by Order in Council under the Colonial Boundaries Act.\nA: "
},
{
"from": "gpt",
"value": "assistant"
}
] |
[
{
"from": "human",
"value": "The input is a conversation between an automated system and a user looking for suggestions for pubs, restaurants and coffee shops in Cambridge. In the dialogue, the user may provide some criteria for the type of place they want such as price range, cuisine, etc. Given such a dialogue, output the price range the user if looking for which can take one of four values: Cheap, Moderate, Expensive and Don't Care. Output cannot be any other value than the four values. Note that if the user asks for the prices of items provided at a pub, restaurant or coffee shop but doesn't mention the price range they are looking for then the correct classification will be Don't Care. If the user does not mention a particular price, the correct classification will be Don't Care.\n\nSystem: 'Thank you for calling the Cambridge Information system. Your call will be recorded for research purposes. You may ask for information about a place to eat, such as a restaurant, a pub, or a cafe. How may I help you?'\nUser: 'sil'\nSystem: 'What kind of venue are you looking for? For example, a cafe, a pub, or a restaurant.'\nUser: 'spanish restaurant'\nSystem: 'What kind of price range are you looking for? For example, cheap, or free.'\nUser: 'restaurant'\nSystem: 'What kind of price range are you looking for? For example, cheap, or moderate.'\nUser: 'cheap'\nSystem: 'Let me confirm. You are looking for a venue in the cheap price range.'\nUser: 'cheap'\nSystem: 'What type of food would you like? For example, Cafe food, Fastfood, or Greek.'\nUser: 'spanish'\nSystem: 'Are you looking for somewhere near a particular venue? For example, All Saints Church, Cafe Jello, or the Ruskin Gallery.'\nUser: 'no'\nSystem: 'What part of town do you have in mind? For example, something in the Addenbrooke's, Romsey, or Trumpington area.'\nUser: 'none'\nSystem: 'What part of town do you have in mind? For example, Castle Hill, or Fen Ditton.'\nUser: 'none'\nSystem: 'What part of town do you have in mind? For example, something in the Castle Hill, Newnham, or Romsey area.'\nUser: 'none'\nSystem: 'What type of food would you like? For example, East asian, French, or Japanese.'\nUser: 'castle hill'\nSystem: 'What part of town do you have in mind? For example, something in the Girton, New Chesterton, or Trumpington area.'\nUser: 'spanish'\nSystem: 'There is no restaurant serving english food in the cheap price range.'\nUser: 'castle hill'\nSystem: 'Let me confirm. You are looking for an english venue.'\nUser: 'goodbye'\n"
},
{
"from": "gpt",
"value": "Cheap"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you are given text for US Congressional and California state bills, your task is to generate a summary for this bill.\n\nSECTION 1. SHORT TITLE.\n\n This Act may be cited as the ``Ensuring Safe Shelter for Homeless \nVeterans Act of 2013''.\n\nSEC. 2. CONDITIONS ON AWARD OF PER DIEM PAYMENTS BY SECRETARY OF \n VETERANS AFFAIRS FOR PROVISION OF HOUSING OR SERVICES TO \n HOMELESS VETERANS.\n\n (a) Condition.--\n (1) In general.--Section 2012(c)(1) of title 38, United \n States Code, is amended by striking ``unless the facilities'' \n and all that follows through ``may specify.'' and inserting the \n following: ``unless the Secretary certifies the following:\n ``(A) That the building where the entity provides housing \n or services for which the entity would receive such payment is \n in compliance with the codes relevant to the operations and \n level of care provided, including applicable provisions of the \n most recently published version of the Life Safety Code of the \n National Fire Protection Association or such other comparable \n fire and safety requirements as the Secretary may specify.\n ``(B) That such building and such housing or services are \n in compliance with licensing requirements, fire and safety \n requirements, and any other requirements in the jurisdiction in \n which the building is located regarding the condition of the \n building and the provision of such housing or services.''.\n (2) Effective date.--The amendment made by paragraph (1) \n shall apply with respect to an application for a per diem \n payment under section 2012 of title 38, United States Code, \n submitted on or after the date of the enactment of this Act.\n (b) Annual Inspections Required.--Section 2012 of such title is \namended by striking subsection (b) and inserting the following new \nsubsection (b):\n ``(b)(1) Not less frequently than once each fiscal year, the \nSecretary shall inspect each facility of each grant recipient or entity \neligible for payments under subsection (a) at which the recipients and \nentities provide services under section 2011 of this title or this \nsection.\n ``(2) Except as provided in paragraph (1), inspections made under \nsuch paragraph shall be made at such times as the Secretary considers \nnecessary.\n ``(3) An inspection of a facility of a recipient or entity \ndescribed in paragraph (1) made under such paragraph may be made with \nor without prior notice to the recipient or entity, as the Secretary \nconsiders appropriate.\n ``(4) No per diem payment may be provided to a grant recipient or \neligible entity under this section unless the facilities of the grant \nrecipient or eligible entity meet such standards as the Secretary shall \nprescribe.''.\n (c) Revocation of Certification Authorized.--Subsection (c) of such \nsection is amended--\n (1) by redesignating paragraphs (2) and (3) as paragraphs \n (4) and (5), respectively;\n (2) in paragraph (1), as amended by subsection (a)(1), by \n striking ``in paragraph (2)'' and inserting ``in paragraph \n (4)''; and\n (3) by inserting after paragraph (1) the following new \n paragraph (2):\n ``(2) The Secretary may revoke any certification made under \nparagraph (1) if the Secretary determines that such certification is no \nlonger accurate.''.\n (d) Congressional Notification of Termination of Per Diem \nRequired.--Such subsection is further amended by inserting after \nparagraph (2) the following new paragraph (3):\n ``(3) Not later than 30 days after the date on which the Secretary \nterminates provision of per diem payment under this section because the \nSecretary has revoked a certification under paragraph (2), the \nSecretary shall submit to the Committee on Veterans' Affairs of the \nSenate and the Committee on Veterans' Affairs of the House of \nRepresentatives notice of such termination.''.\n (e) Annual Report.--Section 2065(b) of such title is amended--\n (1) by redesignating paragraph (6) as paragraph (7); and\n (2) by inserting after paragraph (5) the following new \n paragraph (6):\n ``(6) The Secretary's evaluation of the safety and \n accessibility of facilities used to provide services under \n programs established by grant recipients or eligible entities \n under section 2011 and 2012 of this title, including the number \n of such grant recipients or eligible entities who have been \n certified by the Secretary under section 2012(c)(1) of this \n title.''.\n (f) Treatment of Current Recipients of Per Diem Payments.--\n (1) Assessment.--In the case of the recipient of a per diem \n payment under section 2012 of title 38, United States Code, \n that receives such a payment during the year in which this Act \n is enacted for the provision of housing or services, the \n Secretary of Veterans Affairs shall assess whether the building \n where such housing or services are provided is and whether the \n housing and services are in compliance as required by section \n 2012(c)(1) of such title, as amended by subsection (a)(1).\n (2) Failure to comply.--In the case described in paragraph \n (1), if the Secretary does not certify the compliance of the \n building and the housing or services under such section before \n the date that is two years after the date of the enactment of \n this Act, the Secretary may not make any additional per diem \n payments to the recipient for the provision of such housing or \n services under section 2012 of such title until the Secretary \n certifies that such building is and such housing or services \n are in compliance.\n (g) Conforming Condition on Award of Grants by Secretary of \nVeterans Affairs for Comprehensive Service Programs.--Section \n2011(b)(5)(A) of title 38, United States Code, is amended by inserting \n``, including housing and building codes,''.\n"
},
{
"from": "gpt",
"value": "Ensuring Safe Shelter for Homeless Veterans Act of 2013 - Prohibits a per diem payment from being made to providers of services for homeless veterans unless the Secretary of Veterans Affairs (VA) certifies that: (1) the building where the entity provides housing or services is in compliance with codes relevant to the operations and level of care provided; and (2) such building and the housing or services provided are in compliance with licensing, fire and safety, and other requirements of the relevant jurisdiction regarding the condition of the building and the provision of such housing or services. Authorizes the Secretary to revoke any certification upon determining that it is no longer accurate. Requires the Secretary to: (1) inspect such facilities at least annually, and (2) notify Congress of any such revocation and termination of per diem payments. Requires the Secretary's annual report on assistance to homeless veterans to include an evaluation of the safety and accessibility of such providers' facilities. Directs the Secretary to assess the compliance of the building and housing and services provided by current per diem payment recipients. Prohibits additional payments to a recipient that is not, within two years after enactment of this Act, certified to be in compliance until the Secretary certifies that the building and housing and services provided are in compliance."
}
] |
[
{
"from": "human",
"value": "Given a part of privacy policy text, classify it into one of these categories: \n (1) First Party Collection/Use (how and why a service provider collects user information), \n (2) Third Party Sharing/Collection (how user information may be shared with or collected by third parties), \n (3) User Choice/Control (choices and control options available to users), \n (4) User Access, Edit, & Deletion (if and how users may access, edit, or delete their information), \n (5) Data Retention (how long user information is stored), \n (6) Data Security (how user information is protected), \n (7) Policy Change (if and how users will be informed about changes to the privacy policy).\n--------\nQuestion: You can opt in for the use of generic personal information by a third party, which collects or receives it for a purpose outside of our label scheme.\n\nAnswer: User Choice/Control\n\n\nQuestion: You can opt out (via a link) from the use of unspecified information by an unspecified party for an unspecified purpose.\n\nAnswer: User Choice/Control\n\n\nQuestion: A user with an account can opt out (via a link) from the use of contact information by the site, which uses it for marketing purposes.\n\nAnswer:"
},
{
"from": "gpt",
"value": "User Choice/Control\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task you will be given a list, of lists, of integers. For every inner list contained in the input list, you should multiply every even number in that list. The output should be a list of integers with the same length as the number of lists in the input list. If there are no even numbers in an inner list you should output 0 for that list.\n\nExample Input: [[-42, -37, -5, 12, -3], [41, -23, -22, 47], [-12, -6, 8]]\nExample Output: [-504, -22, 576]\n\nExample Input: [[-50, 2, 25], [-27, -18, 7], [-17, 6, 9, -35], [-34, 33, -48, 19], [-31, 9], [29, -29], [47, 5], [-1, 29, 26], [-23, -7], [26, -7, 40, 36]]\nExample Output: [-100, -18, 6, 1632, 0, 0, 0, 26, 0, 37440]\n\nExample Input: [[16, -41], [-12, 8, 30], [-12, -38, -8, -7, 20], [44, 9, -35, 20, -39], [3, -25, 0, 14, 10], [-41, 17, -41, 43], [-11, -49, 46, -19, -9], [-17, 14, -45, -30, -6], [30, 33, 45, -7, -34]]\nExample Output:"
},
{
"from": "gpt",
"value": "[16, -2880, -72960, 880, 0, 0, 46, 2520, -1020]\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. You are shown a conversation between a user and system. Identify who has spoken the indicated sentence based on the conversation.\n\nSentence1: No, but I would like to find a cheap priced south african restaurant. Sentence2: I'm sorry, but we don't have and South African restaurants in the area. Is there a different type of food I can help you find? Sentence3: I would say let's look for an attraction first. Can you recommend something to do in the south part of town? Sentence4: I will go with whatever you recommend, I just need the attraction type and postcode. Sentence5: Hi, I am looking forward to trying some of your local restaurants. I do need help with some other places to go in town while I am there though. Sentence6: There are several nice parks in the area as well as theaters and museums. Sentence7: The byard art museum postal code is cb21sj. Can i help you get transportation to and from the museum? Sentence8: Try Portuguese then. Sentence9: Thanks so much for putting up with me! You've been great! Sentence10: 3 people will be dining. Please give me a reference number once you finish the reservation Sentence11: I would rather be in the south area. Sentence12: What is your food type preference? Sentence13: There are two results. Both are cheap. Do you prefer the south or centre? Sentence14: I have finished booking it for Thursday at 12:15 for 3 people at Nando, your reference number is TDQZGM38 . Do you need anything else? Sentence15: Can you book a table for me there on Thursday at 12:15? Sentence16: The only option is nandos. Sentence17: You are welcome enjoy Sentence18: How many people are in your party? Question: Who has spoken the sentence 15? (A) User (B) System\n"
},
{
"from": "gpt",
"value": "Answer: (B) System"
}
] |
[
{
"from": "human",
"value": "In this task, you are given inputs i and A, where i is an integer and A is a list. You need to output the first i elements of A, starting with the 1st element in A. i will always have a value less than the length of A\n\nInput: Consider Input: 2, ['K', 'V', 'v', '565', '1845', '961', 'E', 'T', '439', '7305', 'w', 'P']\n\nOutput: K, V\n\n\nInput: Consider Input: 11, ['7853', 'y', 'C', '7443', '2749', 'f', 'j', '3835', 'k', 'H', '8573', '9129', '6807', '7375', '5859', '1235', '2745', 'M', 'L', '9313', '1979', 'D', 'j', 'R', 'I', '8293', '9253', '2149', 'Y']\n\nOutput: 7853, y, C, 7443, 2749, f, j, 3835, k, H, 8573\n\n\nInput: Consider Input: 3, ['N', '3811', '2801', '2653', 'h', '6421', '1153', 'S', '7961', '2061', '2641', '6703', 'n', 'v', '2465', 'u', 'y', 'Y', 'u', 'n', '3393', 'U', '9771', 'F', 'N', 'Q', 'p', 'M', '3147', '3543']\n\n"
},
{
"from": "gpt",
"value": "Output: N, 3811, 2801\n\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. This task is about using the specified sentence and converting the sentence to Resource Description Framework (RDF) triplets of the form (subject, predicate object). The RDF triplets generated must be such that the triplets accurately capture the structure and semantics of the input sentence. The input is a sentence and the output is a list of triplets of the form [subject, predicate, object] that capture the relationships present in the sentence. When a sentence has more than 1 RDF triplet possible, the output must contain all of them.\n\nArem arem is a dish comprised of compressed rice, cooked in banana leaves and filled with vegetables or meat, is an Indonesian recipe.\n"
},
{
"from": "gpt",
"value": "[['Arem-arem', 'REGION', 'Indonesia'], ['Arem-arem', 'MAIN_INGREDIENTS', '\"compressed rice cooked in banana leaf with vegetables or minced meat fillings\"']]"
}
] |
[
{
"from": "human",
"value": "In this task, You are given an amazon food product review and its summary. Your task is to Generate \"True\" if given review and its summary match, otherwise generate \"False\".\n\nLet me give you an example: I have bought several of the Vitality canned dog food products and have found them all to be of good quality. The product looks more like a stew than a processed meat and it smells better. My Labrador is finicky and she appreciates this product better than most. \n Summary: Good Quality Dog Food\nThe answer to this example can be: True\nHere is why: The customer talked about dog food which was good. So, it's a correct Summary. So, the correct answer is true.\n\nOK. solve this:\nI received this as a gift a few weeks ago. It is by far the best home made pancakes I have every had. The taste and consistancy is excellent. Blueberries mix very well with this product and the container is desinged to keep the product fresh and not let moths in. You pay a little more but it is worth it in my opinion \n Summary: Stonewall Kitchen pancake mix\nAnswer:"
},
{
"from": "gpt",
"value": "True"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you need to 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 'ADJ': Adjectives are words that typically modify nouns and specify their properties or attributes, 'ADP': Adposition is a cover term for prepositions and postpositions, 'ADV': Adverbs are words that typically modify verbs for such categories as time, place, direction or manner, 'AUX': An auxiliary is a function word that accompanies the lexical verb of a verb phrase and expresses grammatical distinctions not carried by the lexical verb, such as person, number, tense, mood, aspect, voice or evidentiality, 'CCONJ': A coordinating conjunction is a word that links words or larger constituents without syntactically subordinating one to the other and expresses a semantic relationship between them, 'DET': Determiners are words that modify nouns or noun phrases and express the reference of the noun phrase in context, 'INTJ': An interjection is a word that is used most often as an exclamation or part of an exclamation, 'NOUN': Nouns are a part of speech typically denoting a person, place, thing, animal or idea, '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, 'PART': 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, 'PRON': Pronouns are words that substitute for nouns or noun phrases, whose meaning is recoverable from the linguistic or extralinguistic context, '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, 'PUNCT': Punctuation marks are non-alphabetical characters and character groups used in many languages to delimit linguistic units in printed text, 'SCONJ': A subordinating conjunction is a conjunction that links constructions by making one of them a constituent of the other. The subordinating conjunction typically marks the incorporated constituent which has the status of a (subordinate) clause, 'SYM': A symbol is a word-like entity that differs from ordinary words by form, function or both, '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, 'X': The tag X is used for words that for some reason cannot be assigned a real part-of-speech category.\nQ: Sentence: I am a member of the design group that has been developing the American Arbitration Association 's dispute management systems {{ and }} services for eCommerce B2B transactions .? \nWord: and\nA:"
},
{
"from": "gpt",
"value": "CCONJ"
}
] |
[
{
"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?). \",\nQ: Sentence: This line carries a BLV provirus of the Belgian species and has been tested to be free of a variety of possibly contaminating viruses and mycoplasms. \n Section: finding\nA: "
},
{
"from": "gpt",
"value": "True"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a review from Amazon and category of the product based on the review given by the user and your task is classify whether the given category match the review. Generate \"True\" if given review and its category match, otherwise generate \"False\".\n\n[Q]: Reviews: The bottle I received did not look like the picture. The bottle I received was a pink bottle, it didn't smell like a man's cologne but the box it came in said for men. I think the bottles got switched. \n Category: pc\n[A]: False\n\n\n[Q]: Reviews: Received this as a Christmas gift , BUT just opened it to use today. There are no attachments to connect to the float. I could not use it. Very disappointing as the other folks in my family who received the gift loved it. Would appreciate the attatchments mailed to me, or the machine replaced. \n Category: toy\n[A]: True\n\n\n[Q]: Reviews: Seriously, this is ridiculous. All of the roses were either off of the steams or broken open. How am I supposed to give this to anyone and say that this is how much I care for them??! \n Category: jewelry\n[A]:"
},
{
"from": "gpt",
"value": "False\n\n\n"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nCraft one correct answer to the question given in input. To make it more interesting, try to use non-stereotypical language if possible. Make sure your correct answer is reasonably long, consistent with the context, and requires common sense (instead of explicit extraction from the context.) In your answer, use as few words as possible from the given context. Use a response that is uncommon/non-stereotypical, so that it is less predictable. To be less repetitive, please vary your language for each question.\n\nContext: I was told, in person over the phone, that my shoes were on their way. They have my money. I have no shoes. \nQuestion: What may happen after the call?\nSolution: I will return the shoes and get back the money.\nWhy? Excellent correct answer: as it presents a non-stereotypical solution involving \"return\".\n\nNew input: Context: Jose Guillen had three of the six hits the Royals had on the day and Miguel Olivo hit a solo home run . The rest of the offense was pretty silent . Tonight , Kyle Davies ( 6 - 6 , 4.59 ) will go up against Kevin Slowey ( 11 - 9 , 3.75 ) . \nQuestion: What may be the sport I am writing about ?\nSolution:"
},
{
"from": "gpt",
"value": "I am writing about Major League Baseball ."
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn 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. \nExample: SQL: SELECT avg ( Area ) , max ( Capacity ) FROM stadium\nFeedback: Swap the average of \"Area\" with the average of \"Capacity\"\nOutput: SELECT avg(capacity) , max(capacity) FROM stadium\nThe SQL statement was adjusted to find the average of the capacity. This is a good example.\n\nNew input case for you: 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 .\nOutput:"
},
{
"from": "gpt",
"value": "SELECT date_of_enrolment , date_of_completion FROM Student_Course_Enrolment"
}
] |
[
{
"from": "human",
"value": "Here are two questions (Question1 and Question2). If these questions have the same meaning and same answer, answer \"Yes\", otherwise \"No\".\nExample: Question1: How do I get into my Instagram if I forgot my email and my Facebook password?, Question2: I forgot my password and also my email password. how can I get back that account?\nExample solution: Yes\nExample explanation: These questions have the meaning and the same answer. So, the output should be \"Yes\".\n\nProblem: Question1: Why does gel nail polish crack?, Question2: Why do gel nails crack?\n"
},
{
"from": "gpt",
"value": "Solution: Yes"
}
] |
[
{
"from": "human",
"value": "In this task, based on the given context word, you are asked to create a pair of sentences each containing a blank (_). The sentence pair should look similar and should be about two different persons (PersonX and PersonY). Additionally, the two sentences must be different in terms of trigger words (e.g., \"sympathetic\" and \"stern\") which express contrasting attributes about the two persons. The answer to the first and the second sentence must be PersonX and PersonY, respectively. PersonX and PersonY should not be equally likely to fill the blank. For each sentence, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people (e.g., Donald Trump, Putin, etc.) in your sentences. Avoid repeating the same style or phrase in twin sentences e.g., a contrasting sentence can always be created using simple negation i.e. by adding not, never, etc. Instead, try to increase diversity. Both twin sentences must contain at least 15 and at most 30 words. Twin sentences must have at least 70% overlapping words. You must utilize the given context word while writing the twin sentences. Each of the twin sentences must contain only one blank. Make sure that PersonX and PersonY have the same gender. In each sentence, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY.\n\nLet me give you an example: Context word: upset.\nThe answer to this example can be: Sentence 1: PersonX yelled at PersonY because _ was so upset about the news. \nSentence 2: PersonX comforted at PersonY because _ was so upset about the news.\nHere is why: As expected, two sentences contain mentions of PersonX and PersonY and they're quite similar. Their difference is in terms of trigger words (\"yelled\" and \"comforted\"), whcih result in them having different answers. As required by the instructions, the answer to sentence 1 and sentence 2 are PersonX and PersonY, respectively.\n\nOK. solve this:\nContext Word: homemade jewelry.\nAnswer:"
},
{
"from": "gpt",
"value": "Sentence 1: PersonX loved to buy expensive diamonds but PersonY preferred homemade jewelry. _ liked extravagant pieces. \nSentence 2: PersonX loved to buy expensive diamonds but PersonY preferred homemade jewelry. _ liked individual pieces."
}
] |
[
{
"from": "human",
"value": "Teacher: In this task, you're given a context passage, a question, and three answer options. Your task is to return an incorrect answer option to the question from the choices given. For all questions, only one of the three answer options is correct. Pick one of the two incorrect answer options as the output.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nContext: Tracy didn't go home that evening and resisted Riley's attacks. \n Question: What does Tracy need to do before this? \n Options: (A) make a new plan (B) Go home and see Riley (C) Find somewhere to go\nSolution: B\nReason: Tracy finds somewhere to go and didn't come home because she has to resist Riley's attacks. So, C is the correct answer and B is acceptable as an incorrect answer.\n\nNow, solve this instance: Context: jordan was annoying so he spit at the dummy. \n Question: How would you describe Jordan? \n Options: (A) as anti social (B) normal (C) ashamed\nStudent:"
},
{
"from": "gpt",
"value": "B"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nGiven a set of five words, generate the word from the set that does not belong (i.e. is the least relevant) with the other words. Words are separated by commas.\n\nhunt, fish, stingray, dolphin, bat\nOutput:"
},
{
"from": "gpt",
"value": "hunt"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nYou are given a concept, and a list of answers. You should generate a question about the concept that leads to the given answer(s).\n\nconcept: Kansas City Chiefs answers: ['Super Bowl IV']\nOutput:"
},
{
"from": "gpt",
"value": "when was the last time the kansas city chiefs won a superbowl?"
}
] |
[
{
"from": "human",
"value": "Definition: In this task, you are given an input i,A where i is an integer and A is an array. You need to find every ith element of A starting with the 1st element.\nInput: 1, ['Q', '4445', 'K', 'k', 'W', '907', '4593', '3525', 'n', 'I']\nOutput:"
},
{
"from": "gpt",
"value": "Q, 4445, K, k, W, 907, 4593, 3525, n, I"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In 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 write the character's motivation by doing a specific job, which is given in the sentence. You can use context to find the motivation; however, all the inputs do not provide context. Also, in some inputs, there can be zero motivation; output, 'None' in this case.\nQ: Context: Bill was looking forward to a quiet weekend at home. His daughter called him from college to say her car was broke down. Bill sighed as he put his tools in the trunk of his car. \n Sentence: He was going to spend his weekend traveling. \n Character: His daughter\nA:"
},
{
"from": "gpt",
"value": "None"
}
] |
[
{
"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 list all elements of A from the ith element to the jth element in the reverse order. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n\n[EX Q]: 2, 3, ['5347', '6237', 'S', '9709']\n[EX A]: S, 6237\n\n[EX Q]: 10, 11, ['4989', '7863', '2455', '8737', '1461', 'G', '7569', 'x', 'U', '2015', 'z', 'S', 't', '7245', 'G', 'c']\n[EX A]: z, 2015\n\n[EX Q]: 1, 3, ['T', '3727', 'z']\n[EX A]:"
},
{
"from": "gpt",
"value": "z, 3727, T\n\n"
}
] |
[
{
"from": "human",
"value": "In this task you will be given some text dialogue and you need to infer the underlying emotion of the text. The possible emotions are happy, sad, angry, or other.\nQ: you are right it's ok bayys\nA: "
},
{
"from": "gpt",
"value": "other"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you're given the middle and ending of a three-part story. Your job is to complete the short story by writing a probable beginning of the story. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the beginning, and use names (e.g. Jack, Barbara,...) instead of pronouns (e.g. he / she) wherever possible.\n\nMiddle: After graduation, Jemma decided to take a road trip. Ending: She was very excited to start seeing the country.\n"
},
{
"from": "gpt",
"value": "Jemma wanted to see America."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.