Search is not available for this dataset
conversations
listlengths 2
2
|
|---|
[
{
"from": "human",
"value": "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.\nOne example: Sentence: An editorial in the church - owned Deseret Morning News in Salt Lake City earlier this year acknowledged that \" the state 's history , a {{ conservative }} belief in free choice , and an unwillingness to stir up a hornet 's nest in the national media have likely all contributed to the kid - glove approach lawmakers and law - enforcement officers have taken when dealing with polygamous communities . \" \nWord: conservative\nSolution is here: ADJ\nExplanation: \"conservative\" is an Adjective (ADJ) since it adds to the description of the Noun (NOUN) \"belief\".\n\nNow, solve this: Sentence: Dr. Eric Fortier , 34 , of Gatineau , Que. {{ , }} used a pocket knife to attack a polar bear on Baffin Island , just south of the Arctic Circle , to save two friends who were being mauled . \nWord: ,\nSolution:"
},
{
"from": "gpt",
"value": "PUNCT"
}
] |
[
{
"from": "human",
"value": "Given a part of privacy policy text, identify the type of personal information which is collected, used, tracked or retained. The type of information should be present inside the given policy text, answer as 'Not Specified' otherwise\n\nExample input: The site collects your cookies or tracking elements for a basic service or feature. Collection happens in an unspecified way, and your data is aggregated or anonymized.\nExample output: Cookies and tracking elements\nExample explanation: The type of user information collected is clearly stated in the given policy text as 'cookies or tracking elements'\nQ: An unnamed third party does track on the first party website or app your cookies or tracking elements for targeted advertising. The data is aggregated or anonymized. You can configure your privacy with third-party user settings.\nA:"
},
{
"from": "gpt",
"value": "Cookies and tracking elements"
}
] |
[
{
"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\nIn 1996, Kiruna competed in the Norrland section.\n"
},
{
"from": "gpt",
"value": "[['[TABLECONTEXT]', 'SEASON', '1996'], ['Division 2', 'SECTION', 'Norrland'], ['[TABLECONTEXT]', '[TITLE]', 'Kiruna FF'], ['Tier 3', 'DIVISION', 'Division 2'], ['1996', 'LEVEL', 'Tier 3']]"
}
] |
[
{
"from": "human",
"value": "In this task you are given a sentence. You must judge whether subject of the main clause is singular or plural. Label the instances as \"Singular\" or \"Plural\" based on your judgment.\nOne example is below.\nQ: Coming from a xenophobic race that possesses the unique ability to pass among other species and chooses not to, the bounty hunter is a walking contradiction.\nA: Singular\nRationale: \"the bounty hunter\" is the subject of the sentence which is singular.\nQ: \" The sheriff told me. \"\nA:"
},
{
"from": "gpt",
"value": "Singular"
}
] |
[
{
"from": "human",
"value": "Q: In this task, you need to reverse the order of words in the given sentence.\nSentence: a girl standing on a snowy slope by a snowboard\nA:"
},
{
"from": "gpt",
"value": "snowboard a by slope snowy a on standing girl a"
}
] |
[
{
"from": "human",
"value": "In this task, you're given statements in native Kannada language. The statement can be written with the Kannada alphabet or the English alphabet. Your job is to evaluate if the statement is offensive or not. Label the post as \"Not offensive\" if the post does not contain offense or insult. Non-offensive posts do not include any form of offense or insult. Label the post as \"Offensive\" if the post contains offensive language. \n\n[Q]: Eega ellakade ursthayirodu kannadigare\n[A]: Offensive\n\n\n[Q]: Yar guru ninu.....super\n[A]: Not offensive\n\n\n[Q]: Loo Nim Makha muccha e Video gu Dislike yenro nim Hendti Munde Haga avr character Nodi kaliro life Andre yenu antha thu nanmakla\n[A]:"
},
{
"from": "gpt",
"value": "Offensive\n\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you are given an input list A. You need to find all the elements of the list that are alphabets in the same order as they appear in the list A. Do not change their case/capitalization.\n\n['9297', 'I', 'j', 'E', 'E', '251', '9239', 's', 'g', 'j', 'B', 'm', 'S', '8771', 'W', 'u', 'e']\n"
},
{
"from": "gpt",
"value": "I, j, E, E, s, g, j, B, m, S, W, u, e"
}
] |
[
{
"from": "human",
"value": "instruction:\nYou 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.\nquestion:\n Person1: You know that this job requires frequent business travel . Can you accept it ? \n Person2: Yes , I can . \n Person1: Mostly short business trips , but sometimes long ones are also needed . \n Person2: Then how about the expenses during the trips ? \n Person1: The company will pay all the expenses . \n Person2: Would you tell me where we often travel ? \n Person1: Usually Shanghai , Qingdao , Hong Kong and so on . \n Person2: It's great ! I like these places . \n Person1: And you need to go abroad once in a while . Can you ? \n Person2: Yes , I can . \n Person1: After the business trip , you could apply for reimbursement of all the expenses , such as passage money and accommodation charges and so on . \n Person2: I see . \n Person1: You can take a break for one or two weeks after you have a business trip every time , which depends on the circumstances . \n Person2: OK . Thank you very much for telling me all these things . \nanswer:\n1\n\n\nquestion:\n Person1: What do you think of his behaviour yesterday ? \n Person2: He's a sad dog . He came to the wedding in jeans ! \n Person1: I don't think so . He only had no common sense . \nanswer:\n0\n\n\nquestion:\n Person1: Do I have to take these books here if I want to renew them ? \n Person2: You can renew the books over the computer . \n Person1: That's so convenient . \nanswer:\n"
},
{
"from": "gpt",
"value": "1\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task you are expected to write an SQL query that will return the data asked for in the question. 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.\n\n[EX Q]: display the emails of the employees who have no commission percentage and salary within the range 7000 to 12000 and works in that department which number is 50.\n[EX A]: SELECT email FROM employees WHERE commission_pct = \"null\" AND salary BETWEEN 7000 AND 12000 AND department_id = 50\n\n[EX Q]: List the name of the pilots who have flied for both a company that mainly provide 'Cargo' services and a company that runs 'Catering services' activities.\n[EX A]: SELECT T2.pilot FROM operate_company AS T1 JOIN flight AS t2 ON T1.id = T2.company_id WHERE T1.principal_activities = 'Cargo' INTERSECT SELECT T2.pilot FROM operate_company AS T1 JOIN flight AS t2 ON T1.id = T2.company_id WHERE T1.principal_activities = 'Catering services'\n\n[EX Q]: Show the ids of the employees who don't authorize destruction for any document.\n[EX A]:"
},
{
"from": "gpt",
"value": "SELECT employee_id FROM Employees EXCEPT SELECT Destruction_Authorised_by_Employee_ID FROM Documents_to_be_destroyed\n\n"
}
] |
[
{
"from": "human",
"value": "Q: You are given a sentence in English. Your job is to translate the English sentence into Italian.\nAnd if we can find that, then we'll be able to find, within each one of us, what it is that we need to find to face the big question, which is: how do we change?\nA:"
},
{
"from": "gpt",
"value": "E se siamo convinti di questo, potremo trovare dentro di noi gli elementi per rispondere alla grande domanda: \"\" Come cambiare? \"\"."
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to generate a natural language interpretation of the given command. \n Here are the definitions of logical operators: \n 1. count: returns the number of rows in the view \n 2. only: returns whether there is exactly one row in the view \n 3. hop: returns the value under the header column of the row \n 4. and: returns the boolean operation result of two arguments \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column \n 6. nth max/nth min: returns the n-th max/n-th min of the values under the header column \n 7. argmax/argmin: returns the row with the max/min value in header column \n 8. nth argmax/nth argmin: returns the row with the n-th max/min value in header column \n 9. eq/not eq: returns if the two arguments are equal \n 10. round eq: returns if the two arguments are roughly equal under certain tolerance \n 11. greater/less: returns if argument 1 is greater/less than argument 2 \n 12. diff: returns the difference between two arguments \n 13. filter eq/not eq: returns the subview whose values under the header column is equal/not equal to argument 3 \n 14. filter greater/less: returns the subview whose values under the header column is greater/less than argument 3 \n 15. filter greater eq /less eq: returns the subview whose values under the header column is greater/less or equal than argument 3 \n 16. filter all: returns the view itself for the case of describing the whole table \n 17. all eq/not eq: returns whether all the values under the header column are equal/not equal to argument 3 \n 18. all greater/less: returns whether all the values under the header column are greater/less than argument 3 \n 19. all greater eq/less eq: returns whether all the values under the header column are greater/less or equal to argument 3 \n 20. most eq/not eq: returns whether most of the values under the header column are equal/not equal to argument 3 \n 21. most greater/less: returns whether most of the values under the header column are greater/less than argument 3 \n 22. most greater eq/less eq: returns whether most of the values under the header column are greater/less or equal to argument 3\n\nall_eq { filter_eq { all_rows ; surface ; clay } ; outcome ; runner-up } = true\n"
},
{
"from": "gpt",
"value": "select the rows whose surface record fuzzily matches to clay . for the outcome records of these rows , all of them fuzzily match to runnerup ."
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nTurn the given fact into a question by a simple rearrangement of words. This typically involves replacing some part of the given fact with a WH word. For example, replacing the subject of the provided fact with the word \"what\" can form a valid question. Don't be creative! You just need to rearrange the words to turn the fact into a question - easy! Don't just randomly remove a word from the given fact to form a question. Remember that your question must evaluate scientific understanding. Pick a word or a phrase in the given fact to be the correct answer, then make the rest of the question. You can also form a question without any WH words. For example, \"A radio converts electricity into?\"\n\nFact: water vapor chilling causes that water vapor to condense.\nOutput:"
},
{
"from": "gpt",
"value": "What causes water vapor to condense?"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a Reddit post as a text. Your task is to generate a short summary for this text. The summary must include a situation which caused humor. The summary should be one or two sentences long.\nQ: Text: my second post here, yay. so i was sitting with my friends at lunch at school, and one of my friend's (we'll call him dillpickle) girlfiend comes over, and he gets distracted. so me and my other friend (we'll call him danickinator) decides we should prank dilpickle. so we take his backpack, find his wallet (which for some reason has like $90 in it.), and then throw it at one of our mutual friends (we'll just call her athens) i the shout, \"dillpickle! athens took your wallet!\" so naturally, he would freak out and try to get the wallet back. but here's a twist: athens actually decided to take $5 out of the wallet. so dillpickle counts his money, and realizes $5 is gone. so he decides to tackle athens and trying to grab the money. he then throws her backpack off to the side. this is where i started to fuck up: i started to film it. use of cell phones during lunch is banned for some reason, so i was taking a risk. so i was filming the entire thing, and then dillpickle lets off for a minute. i whisper to athens \"do you still have the $5?\" she responds with a nod. \"give it to him, i got a plan.\" i said. take note that i am still filming this. so athens gives up the $5 and i tell dillpickle to come here. i ask \"what do you want to say for yourself?\" he then decids to hold out the $5 bill and he starts to talk. i then full on snatch the money, and dillpickle tackles me. i'm laughing and crying at the same time, and i pass it over to danickinator. he then gives it back, and it's all good, for like 15 seconds. the assistant principal then walks up and demands my phone, because i was breaking the rules. so i give it to her and the day goes on uneventfully. i walk with danickinator a few minutes later, thinking nothing bad will happen. i instantly remembered something, and i shouted \"oh fuck!\": i left pornhub on safari. luckily, i wasn't on safari when the principal took the phone away, but i instantly though of the worst: what if they call my mom and she gives them the passcode? so far, i know nothing, and i hope for the good, and not the bad.\nA: "
},
{
"from": "gpt",
"value": "filmed a fight at school, got phone taken away, and i accidentally left pornhub on."
}
] |
[
{
"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\nLet me give you an example: [[7, -3, -3, 11], [-6, -6, -5, 2], [-8, 4, -3]]\nThe answer to this example can be: [0, 72, -32]\nHere is why: The first inner list has no even integers, so the first number in the output is 0. The second list has -6, -6, 2 for even integers so the second output is 72. The third list has -8, 4 as even numbers so the third output is -32. This is a good example.\n\nOK. solve this:\n[[47, -36, -47, 38], [-3, 41, 35, -4, 12], [-23, 13, 21, -40], [-28, 33], [27, 13, -15, -23], [42, 8, 13], [36, -42, -28, -49], [-1, -5, -17, -48, -1], [-5, 2, 47, -16, 24], [50, -13, 29, 12], [14, 1, -15, 24], [-29, -25], [6, -50, -50, -49], [-49, -44, 21, -33], [-40, 9]]\nAnswer:"
},
{
"from": "gpt",
"value": "[-1368, -48, -40, -28, 0, 336, 42336, -48, -768, 600, 336, 0, 15000, -44, -40]"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. You are given a password and you need to generate the number of steps required to convert the given password to a strong password. A password is considered strong if (a) it has at least 6 characters and at most 20 characters; (b) it contains at least one lowercase letter and one uppercase letter, and at least one digit; (c) it does not contain three repeating characters in a row. In one step you can: (1) Insert one character to password, (2) delete one character from password, or (3) replace one character of password with another character.\n\npassword = .1LD9ibAMqMWTOYO1J3MGHz0QXsya\n"
},
{
"from": "gpt",
"value": "9"
}
] |
[
{
"from": "human",
"value": "Definition: You are given a science question (hard-level) and four answer options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer based on scientific facts, knowledge, and reasoning. Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D'. There is only one correct answer for each question.\nInput: Lasers are used in surgery for \n (A) making fine incisions. (B) illuminating operating fields. (C) stitching wounds. (D) disinfecting instruments.\nOutput:"
},
{
"from": "gpt",
"value": "A"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task you will be given a list of integers. You should find the minimum absolute difference between 2 integers in the list. The absolute difference is the absolute value of one integer subtracted by another. The output should be a single integer which is the smallest possible absolute distance.\nTeacher: Now, understand the problem? Solve this instance: [-90, -4, 86, -14, -100, -93, -96, 15, 10]\nStudent:"
},
{
"from": "gpt",
"value": "3"
}
] |
[
{
"from": "human",
"value": "Teacher: Given a phrase describing the relationship between two words, extract the words and the lexical relationship between them. The relation has to be of the type 'MemberOf', 'MadeOf', 'Synonym', 'Entails', 'HasA', 'HasProperty', 'PartOf', 'Antonym' or 'IsA'. The output should have the format: word1 relation word2.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\naccount can be used with the same meaning of report\nSolution: account Synonym report\nReason: The output is correct as the input describes the relationship between account and report, and the relation is that of having the same meaning, therefore they have a Synonym relationship.\n\nNow, solve this instance: miss can be used as the opposite of see\nStudent:"
},
{
"from": "gpt",
"value": "miss Antonym see"
}
] |
[
{
"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 commands (in terms of logical operations) to select relevant rows from the given table. Your job is to generate a natural language interpretation of the given command. \n Here are the definitions of logical operators: \n 1. count: returns the number of rows in the view \n 2. only: returns whether there is exactly one row in the view \n 3. hop: returns the value under the header column of the row \n 4. and: returns the boolean operation result of two arguments \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column \n 6. nth max/nth min: returns the n-th max/n-th min of the values under the header column \n 7. argmax/argmin: returns the row with the max/min value in header column \n 8. nth argmax/nth argmin: returns the row with the n-th max/min value in header column \n 9. eq/not eq: returns if the two arguments are equal \n 10. round eq: returns if the two arguments are roughly equal under certain tolerance \n 11. greater/less: returns if argument 1 is greater/less than argument 2 \n 12. diff: returns the difference between two arguments \n 13. filter eq/not eq: returns the subview whose values under the header column is equal/not equal to argument 3 \n 14. filter greater/less: returns the subview whose values under the header column is greater/less than argument 3 \n 15. filter greater eq /less eq: returns the subview whose values under the header column is greater/less or equal than argument 3 \n 16. filter all: returns the view itself for the case of describing the whole table \n 17. all eq/not eq: returns whether all the values under the header column are equal/not equal to argument 3 \n 18. all greater/less: returns whether all the values under the header column are greater/less than argument 3 \n 19. all greater eq/less eq: returns whether all the values under the header column are greater/less or equal to argument 3 \n 20. most eq/not eq: returns whether most of the values under the header column are equal/not equal to argument 3 \n 21. most greater/less: returns whether most of the values under the header column are greater/less than argument 3 \n 22. most greater eq/less eq: returns whether most of the values under the header column are greater/less or equal to argument 3\n\neq { hop { argmax { all_rows ; total } ; nation } ; south korea } = true\nOutput:"
},
{
"from": "gpt",
"value": "select the row whose total record of all rows is maximum . the nation record of this row is south korea ."
}
] |
[
{
"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 an article. Your task is to summarize the article in a sentence.\n\nThe Steam Packet Company said this was because the P&O fast craft, which is usually chartered to deal with the busy period in June, will not be available.\nA spokesman said timetable changes mean fewer sailings from Ireland and the UK.\nHe added: \"Given the current situation, we expect to see a reduction in the total number of bikes we will carry.\"\nThe loss of the ship from the Manx fleet next year means fewer sailings from Ireland, Heysham and Liverpool.\n\"The Ben-my-Chree and Manannan [Steam Packet-owned ships] have already been scheduled to operate additional Belfast sailings to accommodate Irish fans heading to the races,\" said ferry chief Mark Woodward.\n\"Adding these extra Irish services means the number of sailings from Heysham and Liverpool is slightly reduced.\n'We will keep looking for a replacement charter and have already approached several companies - none at present has indicated a willingness to release vessels\".\nOutput:"
},
{
"from": "gpt",
"value": "There will be fewer sailings available for TT fans during the 2016 motorcycling festival than this year, Isle of Man ferry operators have said."
}
] |
[
{
"from": "human",
"value": "Teacher: In this task you will be given a list of integers. You should remove any integer that is not prime. A prime integer is an integer that is only divisible by '1' and itself. The output should be the list of prime numbers in the input list. If there are no primes in the input list an empty list (\"[]\") should be returned.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\n[47, 444, 859, 530, 197, 409]\nSolution: [47, 859, 197, 409]\nReason: The integers '444' and '530' are not prime integers and they were removed from the list.\n\nNow, solve this instance: [677, 547, 554, 8, 443, 61, 608]\nStudent:"
},
{
"from": "gpt",
"value": "[677, 547, 443, 61]"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nYou are given a short text as a title. Your task is to generate a poem as output that is related to the given title and should feel like written by kids. The output should be a run-on sentence (two or more complete sentences connected without any punctuation). The poem should not be too long or too complex, because it should feel like it is written by younger person without high level of literature education.\n\nMom's toast\nOutput:"
},
{
"from": "gpt",
"value": "a monkey have a funny donkey with a pocket full of money a monkey have some honey with it's bunny a monkey have a runny nose with a smell of toast he eat the toast on top of a post my mom always have a pocket of money we must respect her it's not funny my mom want's to travel from coast to coast my mom do n't boast like when she eat her toast my mom be not a monkey with honey but my mom can be really funny"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given a statement about date and time, state whether the statement is true or false. The number of date/time operands in the statement ranges between 2 and 3. Let's say the values are denoted by t1, t2 and t3. The statements follow one of the following ten templates: 't1 occurs before t2, t1 doesn't occur before t2, t1 occurs after t2, t1 doesn't occur after t2, t1 occurs between t2 and t3, t1 doesn't occur between t2 and t3, t1 occured before t2 but after t3, t1 occured after t2 but before t3, t1 didn't occur before t2 but after t3, t1 didn't occur after t2 but before t3'. The output should be either 'True' or 'False'.\nSee one example below:\nProblem: 03:40:40 PM doesn't occur between 5:35:38 and 07:58:59 AM\nSolution: False\nExplanation: The output of 'False' is correct as the input statement is false, since 03:40:40 PM occurs after 07:58:89 AM and not between 5:35:38(AM) and 07:58:59 AM\n\nProblem: 17 Apr 1992 occured after Mar 03, 2008 but before April 28, 1990\nSolution:"
},
{
"from": "gpt",
"value": "False"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn this task you are given a sentence. You must judge whether subject of the main clause is singular or plural. Label the instances as \"Singular\" or \"Plural\" based on your judgment.\nExample: Coming from a xenophobic race that possesses the unique ability to pass among other species and chooses not to, the bounty hunter is a walking contradiction.\nOutput: Singular\n\"the bounty hunter\" is the subject of the sentence which is singular.\n\nNew input case for you: She stayed behind a boulder longer than normal and this time, just as she somehow knew he would, the dragon came from overhead.\nOutput:"
},
{
"from": "gpt",
"value": "Singular"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task you will be given a list of integers. For every element in the list, if the element is even you should divide by 4, if the element is odd you should multiply by 4 then add 2. The output should be a list of numbers that is the result of applying that logic to the input list. You should not round any decimals in the output. Zero should be counted as an even integer.\nQ: [82, -54, 89, -76, 26]\nA:"
},
{
"from": "gpt",
"value": "[20.5, -13.5, 358, -19.0, 6.5]"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: You are given a set of queries separated by '\n', and your job is to find out the query which is not a well-formed or well-structured query in terms of grammar, punctuations, or spelling errors.\nProblem:What is considered the capital of turkey ?\nWhere in Montreal can you buy prom dresses ?\nWhat is the state food for nevada ?\nWhat kinda of shampoo does justin biber uses ?\nSolution:"
},
{
"from": "gpt",
"value": "What kinda of shampoo does justin biber uses ?"
}
] |
[
{
"from": "human",
"value": "Teacher:You are given a sentence and a question. You're expected to write an **incorrect** answer to the given question, such that it is relevant to the given sentence. Your answer should not be completely out of context. Try to write short answers with one or two words.\nTeacher: Now, understand the problem? Solve this instance: Sentence: A man punches a tire and a wood board for a demonstration. The board if very stiff. Question: Which object do you think is more likely to break?\nStudent:"
},
{
"from": "gpt",
"value": "Tire"
}
] |
[
{
"from": "human",
"value": "You are given a target person and two sentences. Your task is to determine whether the second sentence conveys either a stereotype, anti-stereotype, or is unrelated with respect to the first sentence and the target. A stereotype is a widely held but oversimplified notion of a group of people. An anti-stereotype is an idea that goes against the widely held but oversimplified notion of a group of people. Sentences and targets are unrelated if there is no relevance between them.\n\nTarget: schoolboy \nThe teacher told the schoolboy to be sure to do his work. He stayed up all night to be sure to get it all done."
},
{
"from": "gpt",
"value": "anti-stereotype"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: You are given an open-domain question from an open movie database. Your task is to provide an answer to that question. Try to only include the answer. Do not put it in a sentence.\nQ: how popular of a movie was Madea's Family Reunion?\nA:"
},
{
"from": "gpt",
"value": "highly watched"
}
] |
[
{
"from": "human",
"value": "Generate an overlapping word between the given two sentences. When you find the overlapping words, they don't have to match exactly, e.g., \"survival\" and \"survive\" are valid overlapping words. Little words like \"the\" or \"of\" don't count! You must generate significant words which are not the stop words.\n\nExample input: Sentence1: pesticides cause pollution. \nSentence2: pollution can harm animals.\nExample output: pollution.\nExample explanation: The word \"pollution\" is common to Sentence1 and Sentence2. So, it's a good answer.\nQ: Sentence1: Lipids Lipids are diverse hydrophobic molecules. \nSentence2: Steroid hormones are made of diverse hydrophobic molecules.\nA:"
},
{
"from": "gpt",
"value": "diverse"
}
] |
[
{
"from": "human",
"value": "Instructions: Given a sentence and an entity, the task is to select the authors sentiment towards the enity. Sentiments can be Positive, Neutral and Negative. Select Positive if the sentence expresses a positive view towards the given entity or praises its quality or skills. Select Neutral if the sentence expresses no clear view towards the entity or has equal amounts of positive and negative statements or expressing some fact/quote by someone else. Select Negative if the sentence expresses a negative view towards like harsh remarks, criticizing entities action/decision etc. Note that URLs in the text have been replaced with [Link].\nInput: What is the sentiment of the following document towards the entity Keith Miller ? \"The numbers don't work for us \" said Miller who also chairs an industry group the Coalition of Franchisee Associations. \"Ten years ago they might have worked. But now they don't in my opinion.\"\nOutput:"
},
{
"from": "gpt",
"value": "Neutral"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you're given an article and an answer. Your task is to generate the question for the answer based on the given article.\n\nArticle: There are a lot of public libraries in Britain. These libraries have more than one hundred and fifteen million books, not including those libraries of public schools. Public libraries not only lend books, music records but also help children, patients in hospitals and others to get special play readings, film shows and so on. The first public libraries were founded in about the year 1850. Today's public libraries usually have a reading-room, a lending room and a reference room. The greatest and most famous library in Britain is that of the British Library in London. It was founded in 1973 and has over 10, 000, 000 books. It has nearly every magazine, newspaper and book published in Britain and other parts across the world. \n Answer: 10,000,000 or less.\nSolution: How many books are there in the British Library?\nWhy? In the Article, 10,000,000 is mentioned for the number of books available in the British Library, so this is a good question.\n\nNew input: Article: Picture a wasteland of old computer monitors and TVs, stretching as far as the eye can see. Imagine towers of boxes, all of them filled with broken glass and discarded electronic devices. Technology graveyards like this can be found in communities across the country. Experts say that landfills and warehouses will overflow unless a plan for the disposal and reuse of electronics is put into place . \"We can't put electronics and glass aside and tell ourselves we'll deal with them later ,\" Lauren Roman , managing director of Transparent Planet said. Roman's group works to improve the disposal of electronic waste. She says about 660 million pounds of tech-trash is produced each year in the U.S. What's behind the tech trash pile-up ?About ten years ago ,major advances were made in computer and television technology . Manufacturers began producing devices like flat -paneled LCDs and plasma screen monitors. These new products provide a clearer image and take up less space than older models. It goes without saying that consumers choose them rather than heavy glass-based technologies. The new electronics are built with materials that are difficult to recycle. In addition, the new products have decreased the demand for recycled parts from the older monitors and screens. Older, heavier computer monitors and TVs used glass-based components called CRTs. CRTs have a high lead content and can be environmentally hazardous if not recycled properly . If crushed and put in landfills, the lead from CUTs could seep into groundwater and rivers, harming the water supply. For many years, plants and recycling programs safely processed CRTs. The recycled CRTs were reused in the construction of new monitors. Monitors being made today do not use glass tubes . \"People are returning old -style TVs with CRTs , but no new ones are being made ,\" said Linnell. This is creating an imbalance in the amount of glass being disposed of and recycled properly. Many recycling companies have shut down. Others no longer have the resources or space to process these materials. This results in stockpiling. However , experts say there are ways to safely and responsibly address the tech-trash problem. \n Answer: New technology causes trouble for recyclers.\nSolution:"
},
{
"from": "gpt",
"value": "What is the main idea of the passage?"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: You are given a question and some answer options (associated with \"A\", \"B\", \"C\", \"D\"). You should choose the correct answer based on commonsense knowledge. Avoid answering questions based on associations, the set of answers are chosen deliberately to capture common sense beyond associations. Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D', 'E' and only give one answer for each question.\nProblem:More people should lower the guard and just have fun, we don't got long just what?\n(A)enjoy living (B)happy (C)enjoyable (D)get laid (E)do enjoy\nSolution:"
},
{
"from": "gpt",
"value": "A"
}
] |
[
{
"from": "human",
"value": "In this task, find the most appropriate number to replace the blank (indicated with _ ) and express it in words.\nQ: Humans have two lungs, each fed by _ bronchus.\nA: "
},
{
"from": "gpt",
"value": "one"
}
] |
[
{
"from": "human",
"value": "Given a scientific question, generate a correct answer to it.\n\nWhat phenomenon makes global winds blow northeast to southwest or the reverse in the northern hemisphere and northwest to southeast or the reverse in the southern hemisphere?\ncoriolis effect\n\nThe properties of the alkali metals are similar to each other as expected for elements in the same what?\nfamily\n\nWhy do people build dams and levees?\n"
},
{
"from": "gpt",
"value": "prevent flooding\n\n"
}
] |
[
{
"from": "human",
"value": "In this task you are given a sentence. You must judge whether the main verb of the sentence is in present or past tense. Label the instances as \"Present\" or \"Past\" based on your judgment. If there is no verb in the given text, answer \"Present\".\n\n[Q]: \" It's actually very ugly, \" he announced dryly.\n[A]: Past\n\n\n[Q]: Josephine exclaimed with such feeling that one would have thought she had just cursed like a sailor.\n[A]: Past\n\n\n[Q]: \" Let me guess, lets head back for dinner. \"\n[A]:"
},
{
"from": "gpt",
"value": "Present\n\n\n"
}
] |
[
{
"from": "human",
"value": "Definition: Given a pair of words, generate the relation between them. The first word is called the 'concept' and the second word is called the 'relatum' The relation must be one of the following: co-hyponym (coordinate), hypernym, meronym, attribute, event, or random. A coordinate relation indicates that the concept and relatum belong to the same semantic class. A hypernym relation indicates that the relatum is a category of which the concept is a specific instance. A meronym relation implies that relatum is a part/component/organ/member of the concept. An attribute relation is when the relatum is an adjective expressing an attribute of the concept. An event relation holds when the relatum is a verb referring to an action/activity/happening/event that is performed by or with the concept. If the relatum and concept are unrelated, the relation between them is 'random'. Classify your answers into coord, hyper, mero, attri, event, and random.\nInput: Concept: tanker, Relatum: bulkhead.\nOutput:"
},
{
"from": "gpt",
"value": "mero"
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: 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?). \",\nPROBLEM: Sentence: Results : None of the 137 patients ( 61 males , 76 females , aged 20-83 years , median age 57 years ) had a definite history of exposure to Huanan Seafood Wholesale Market. \n Section: finding\n\nSOLUTION: True\n\nPROBLEM: Sentence: Practice of meditation or exercise may enhance health to protect against acute infectious illness. \n Section: background\n\nSOLUTION: True\n\nPROBLEM: Sentence: outbreaks in schools and in general populations. \n Section: finding\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "True\n\n"
}
] |
[
{
"from": "human",
"value": "Definition: You are given a short poem which is written by a kid. Your task is to predict if the kid is in elementary school or high school. Anyone who is from grade 1st to 6th-grade will be considered as in elementary school, and 7th to 12th-grade kids will be considered as in high school. There are only two possible outputs, i.e., elementary and high. All inputs have at least one output and it cannot have both categories at a time.\nInput: there once be a lad name jake he love to eat steak one day he go to town and a meet a clown who instead grant him a stake\nOutput:"
},
{
"from": "gpt",
"value": "elementary"
}
] |
[
{
"from": "human",
"value": "In this task, you're given the title of a five-sentence story, the first four sentences, and two options for the fifth sentence as a and b. Your job is to pick the sentence option that seamlessly connects with the rest of the story, indicating your choice as 'a' or 'b'. If both sentences are plausible, pick the one that makes more sense.\n\nInput: Consider Input: Title: New Painting. Sentence 1: Tim wanted some art for his apartment. Sentence 2: He went to a goodwill. Sentence 3: They had several cheap pieces there. Sentence 4: Tim picked out a random one he liked. Choices: a. He received several compliments on it. b. Technician came out, fixed the problem, and now the internet is fine.\n\nOutput: a\n\n\nInput: Consider Input: Title: broken. Sentence 1: Ralph was a running back for his team. Sentence 2: The worse thing happened to him. Sentence 3: As he was running with the ball he was tackled by the legs. Sentence 4: He got his leg broken. Choices: a. I was glad I finally told her about my fantasy football decisions. b. He was going to miss the whole football season.\n\nOutput: b\n\n\nInput: Consider Input: Title: Bad Interview. Sentence 1: Jane was running for office. Sentence 2: She agreed to an interview. Sentence 3: During the interview she felt attacked. Sentence 4: She stopped answering questions and stormed off. Choices: a. It hurt her in the polls. b. Jessie's grandmother fixed breakfast in the morning.\n\n"
},
{
"from": "gpt",
"value": "Output: a\n\n\n"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nGiven 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).\nPart 2. Example\nEntity 1: plant \n Entity 2: leaf\nAnswer: yes\nExplanation: The answer is correct. Because the leaf is part of the plant. Therefore, here leaf is meronym and the plant is holonym.\nPart 3. Exercise\nEntity 1: carotene \n Entity 2: organic compound\nAnswer:"
},
{
"from": "gpt",
"value": "no"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nWrite a correct answer to the given question based on its associated fact. Make sure that your answer is contained in the associated fact. Don't be creative and introduce any new word that is not mentioned in the associated fact! Remember that the associated fact has been rearranged to form the question. So, the correct answer words must lie within the associated fact. The correct answer can be a word, phrase, or even a sentence.\n\nFact: Gravity pulls objects around the sun. \nQuestion: What pulls objects around the sun?\nOutput:"
},
{
"from": "gpt",
"value": "Gravity."
}
] |
[
{
"from": "human",
"value": "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 - \n '.': Period symbol is used for symbols denoting Punctuations/Separations such as comma, period, backticks etc., \n 'ADJ': Adjectives are words that typically modify nouns and specify their properties or attributes, \n 'ADP': Adposition is a cover term for prepositions and postpositions, \n 'ADV': Adverbs are words that typically modify verbs for such categories as time, place, direction or manner, \n 'CONJ': A word used to connect clauses or sentences or to coordinate words in the same clause, \n 'DET': Determiners are words that modify nouns or noun phrases and express the reference of the noun phrase in context, \n 'NOUN': Nouns are a part of speech typically denoting a person, place, thing, animal or idea, \n 'NUM': A numeral is a word, functioning most typically as a determiner, adjective or pronoun, that expresses a number and a relation to the number, such as quantity, sequence, frequency or fraction, \n 'PRT': Particles are function words that must be associated with another word or phrase to impart meaning and that do not satisfy definitions of other universal parts of speech, \n 'PRON': Pronouns are words that substitute for nouns or noun phrases, whose meaning is recoverable from the linguistic or extralinguistic context, \n 'PROPN': A proper noun is a noun (or nominal content word) that is the name (or part of the name) of a specific individual, place, or object, \n 'VERB': A verb is a member of the syntactic class of words that typically signal events and actions, can constitute a minimal predicate in a clause, and govern the number and types of other constituents which may occur in the clause, \n 'X': The tag X is used for words that for some reason cannot be assigned a real part-of-speech category.\n\nInput: Consider Input: Sentence: Each morning at {{ five }} Fogg crawled out of bed to bundle into flying togs over the furnace register of his home . \nWord: five\n\nOutput: NUM\n\n\nInput: Consider Input: Sentence: His formula will have to be weighed , may be altered or {{ improved }} , and it should be tested on additional bodies of material . \nWord: improved\n\nOutput: VERB\n\n\nInput: Consider Input: Sentence: The royalty applies to both principal and interest , but it never exceeds 5 {{ percent }} . \nWord: percent\n\n"
},
{
"from": "gpt",
"value": "Output: NOUN\n\n\n"
}
] |
[
{
"from": "human",
"value": "Definition: In this task you are given a sentence. You must judge whether subject of the main clause is singular or plural. Label the instances as \"Singular\" or \"Plural\" based on your judgment.\nInput: \" The twins are where ? \"\nOutput:"
},
{
"from": "gpt",
"value": "Plural"
}
] |
[
{
"from": "human",
"value": "In this task, you are given inputs i and A, where i is an integer and A is a list. You need to list all the elements of A preceding the last i elements. i will always have a value less than the length of A.\nOne example is below.\nQ: 3, ['a', '34', 'f', '931', '7', '3432', '13245', '762']\nA: a, 34, f, 931, 7\nRationale: Here, all the elements except the last 3 from the list are 'a', '34', 'f', '931', and '7'.\nQ: 2, ['d', 'f', '1767', 'p', 'K', 'V', 'A']\nA:"
},
{
"from": "gpt",
"value": "d, f, 1767, p, K"
}
] |
[
{
"from": "human",
"value": "Given a scientific question, generate a correct answer to it.\n\n[EX Q]: What do muscles need to contract?\n[EX A]: stimulus\n\n[EX Q]: What is the basic structure that holds plants upright, allowing plants to get the sunlight and air they need?\n[EX A]: stem\n\n[EX Q]: What are the two major types of seed plants called?\n[EX A]:"
},
{
"from": "gpt",
"value": "gymnosperms and angiosperms\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nA piece of text from one of these 5 languages - French, English, Dutch, Somali, Tagalog is given. Generate the language to which the text belongs.\nExample: Text: Cheval de soins pour les enfants de 3 ans!\nOutput: French\nThe given text is in French language\n\nNew input case for you: Text: Ito resulta sa\nOutput:"
},
{
"from": "gpt",
"value": "Tagalog"
}
] |
[
{
"from": "human",
"value": "Given a set of four words, generate the category that the words belong to. Words are separated by commas. The possible categories are social gathering, accomodation, physical property, measurement unit, corporate, nutritional value, boats, police punishment, location (proximity), card games, outdoor sport activity, military rank, baby animals, weather, consumer product, animals, boxing terminology, food, chocolate food, bird, type of sandwich, date status, body part, ocean, employment activity, moral characteristic, elements, poker, computers, construction, guitar part, shady activities, physical activity, kitchenware, temperature, type of rigidity, emotional status, season, mode of transportation, window material, activity, emotional display, geographical property, fried food, store status, widespread, aesthetic characteristic, alcoholic drinks, secretary duty, direction, personal characteristic, and animal.\n\nLet me give you an example: excavator, crane, hoist, upraise\nThe answer to this example can be: construction\nHere is why: These four words are all construction equipment, such as 'excavator', 'crane', and 'hoist', or describe a common activity used in construction, such as 'upraise'.\n\nOK. solve this:\negret, flamingo, crane, swift\nAnswer:"
},
{
"from": "gpt",
"value": "bird"
}
] |
[
{
"from": "human",
"value": "In this task, you will be given a list. The list is several integers and letters separated with a comma, written within a []. You can create new lists by dropping one of the items in the input list. Your task is to write a list containing all the possible lists you can make by dropping one item from the input list. For example, if the input list contains two items, you can drop one of the items each time. So the output should be a list comprising two inner lists that you have created by decreasing the items.\n\n['t', '0', '0', 'z', 'm', '2']"
},
{
"from": "gpt",
"value": "[['t', '0', '0', 'z', 'm'], ['t', '0', '0', 'z', '2'], ['t', '0', '0', 'm', '2'], ['t', '0', 'z', 'm', '2'], ['t', '0', 'z', 'm', '2'], ['0', '0', 'z', 'm', '2']]"
}
] |
[
{
"from": "human",
"value": "In this task, you will be given a passage, a question and a list of single-word events identified from the passage. The goal is to point out all events from the given event list that can answer the question. If a question is unanswerable or none of the events answer the question, output should be empty.\n\nExample Input: Passage: Currently, Avon, based in Santa Monica, Calif., has 3.3 million common shares outstanding. About 1.1 million Class C warrants were issued, the company said. Question: What event has already happened? Events: ['based', 'has', 'issued', 'said', 'outstanding']\nExample Output: issued\n\nExample Input: Passage: During that conflict, Angola was one of three countries to send troops to support Kinshasa against rebels backed by Rwanda and Uganda. The refugees are being flown either to Mbanza Kongo or to Uige in northern Angola and the UNHCR allows them to take 40 kilograms (88 pounds) of luggage, and gives them either cash subsidies or assistance packages of food and items like cooking utensils, depending on their destination. Question: What happened before Angola sent troops to support Kinshasa? Events: ['conflict', 'was', 'send', 'support', 'flown', 'allows', 'take', 'gives', 'backed']\nExample Output: conflict\n\nExample Input: Passage: They said that both Arafat and Hamas were besieged by Israel, especially the former who had been besieged for three years, but the Palestinians were never in such a crisis like that of today under the leadership of Arafat. Arafat was besieged by Israeli army in his compound in West Bank city of Ramallah in 2002 following his refusal to Israel's demands and his adherence to the Palestinian principles, in particular the Palestinians' claim to Jerusalem. Question: What happened after today's crisis began? Events: ['said', 'besieged', 'besieged', 'crisis', 'leadership', 'besieged', 'refusal', 'demands', 'adherence', 'claim']\nExample Output:"
},
{
"from": "gpt",
"value": "said\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given an ambiguous question/query (which can be answered in more than one way) and a clarification statement to understand the query more precisely. Your task to classify that if the given clarification accurately clarifies the given query or not and based on that provide 'Yes' or 'No'.\nOne example: Query: Tell me about defender \n Clarification: are you referring to the arcade game called defender\nSolution is here: Yes\nExplanation: The given clarification properly clarify the query. Hence, the output is Yes.\n\nNow, solve this: Query: Tell me about kansas city mo \n Clarification: are you looking for netflix\nSolution:"
},
{
"from": "gpt",
"value": "No"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nGiven a command in a limited form of natural language, provide the correct sequence of actions that executes the command to thus navigate an agent in its environment. A command can be broken down into many different actions. Actions are uppercase and are individual steps that serve as the building blocks for a command. For commands, 'left' and 'right' are used to denote the direction of an action. The word 'opposite' turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. Actions and commands do not have quotations in the input and output.\nPart 2. Example\njump left\nAnswer: I_TURN_LEFT I_JUMP\nExplanation: The agent must first turn left and then jump in order to jump to the left.\nPart 3. Exercise\njump opposite left twice and jump around right twice\nAnswer:"
},
{
"from": "gpt",
"value": "I_TURN_LEFT I_TURN_LEFT I_JUMP I_TURN_LEFT I_TURN_LEFT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a pair of sentences, sentence 1 and sentence 2, that neither agree with nor contradict each other. Your job is to alter sentence 2 so that the pair clearly agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\n--------\nQuestion: Sentence 1: A young female basketball player in red and white blocks another in possession of the ball who is dressed in white and maroon. Sentence 2: A female player blocks the winning shot in the basketball game.\n\nAnswer: A young female is playing basketball.\n\n\nQuestion: Sentence 1: A brown dog runs towards the camera on a dirt trail with mountains in the background. Sentence 2: A dog is wagging a tail and running.\n\nAnswer: A dog running towards a camera.\n\n\nQuestion: Sentence 1: A boy is sleeping in his dinner bowl. Sentence 2: boy had a long day\n\nAnswer:"
},
{
"from": "gpt",
"value": "boy sleeping\n\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you need to reverse the order of words in the given sentence.\n\nSentence: a church with grey clouds and cars moving down the street\n"
},
{
"from": "gpt",
"value": "street the down moving cars and clouds grey with church a"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task you are given a sentence pair from wikipedia that have high lexical overlap. If the sentences have the same meaning and are just paraphrases of each other label them as \"Paraphrase\" , if not label them as \"Not paraphrase\". The two sentences are seperated by a new line.\nTeacher: Now, understand the problem? Solve this instance: `` L.A. ( Light Album ) '' reached No . 100 in the US during a chart stay of 13 weeks , and No . 32 in the UK .\nL.A. ( Light Album ) reached No . 100 in the UK and No . 32 in the USA during a charter stay of 13 weeks .\nStudent:"
},
{
"from": "gpt",
"value": "Not paraphrase"
}
] |
[
{
"from": "human",
"value": "Q: In this task, you're given a statement, the genre to which that statement belongs, and a label indicating if the statement should be agreed with (entailment), disagreed with (contradiction), or neither (neutral). Your job is to write a sentence that describes the genre that follows the tone with respect to the statement, as indicated by the label. If sentence X agrees with sentence Y, the can be concluded from one another. If sentence X disagrees with sentence Y, they can not be correct at the same time. The sentence must also belong to the genre specified.\nStatement: But in a moment the thing's attention was directed to some other object of torture.\nLabel: contradiction.\nGenre: fiction.\nA:"
},
{
"from": "gpt",
"value": "Nothing could divert the thing's attention."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: 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.\nProblem:Sentence 1: However, during this time the country is at its most green, and the monuments, especially the Taj Mahal, take on a glistening beauty. Sentence 2: When the country is at its most green, the monuments look duller then ever.\nSolution:"
},
{
"from": "gpt",
"value": "yes"
}
] |
[
{
"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 context, a subject, a relation, and many options. Based on the context, from the options select the object entity that has the given relation with the subject. Answer with text (not indexes).\n\nContext: Utah (or ) is a state in the western United States. It became the 45th state admitted to the U.S. on January 4, 1896. Utah is the 13th-largest by area, 31st-most-populous, and 10th-least-densely populated of the 50 United States. Utah has a population of more than 3 million (Census estimate for July 1, 2016), approximately 80% of whom live along the Wasatch Front, centering on the state capital Salt Lake City. Utah is bordered by Colorado to the east, Wyoming to the northeast, Idaho to the north, Arizona to the south, and Nevada to the west. It also touches a corner of New Mexico in the southeast., Gainesville is the county seat and largest city in Alachua County, Florida, United States, and the principal city of the Gainesville, Florida Metropolitan Statistical Area (MSA). The population of Gainesville in the 2013 US Census estimates was 127,488, a 2.4% growth from 2010. Gainesville is the largest city in the region of North Central Florida. It is also a component of the Gainesville-Lake City Combined Statistical Area, which had a 2013 population of 337,925., The University of Utah (also referred to as the U, the U of U, or Utah) is a public coeducational space-grant research university in Salt Lake City, Utah, United States. As the state's flagship university, the university offers more than 100 undergraduate majors and more than 92 graduate degree programs. The university is classified in the highest ranking: \"R-1: Doctoral Universities Highest Research Activity\" by the Carnegie Classification of Institutions of Higher Education. The Carnegie Classification also considers the university as \"selective\", which is its second most selective admissions category. Graduate studies include the S.J. Quinney College of Law and the School of Medicine, Utah's only medical school. As of Fall 2015, there are 23,909 undergraduate students and 7,764 graduate students, for an enrollment total of 31,673., A medical school is a tertiary educational institutionor part of such an institutionthat teaches medicine, and awards a professional degree for physicians and surgeons. Such medical degrees include the Bachelor of Medicine, Bachelor of Surgery (MBBS, MBChB, BMBS), Doctor of Medicine (MD), or Doctor of Osteopathic Medicine (DO). Many medical schools offer additional degrees, such as a Doctor of Philosophy, Master's degree, a physician assistant program, or other post-secondary education., Salt Lake City, often shortened to Salt Lake or SLC, is the capital and the most populous municipality of the U.S. state of Utah. With an estimated population of 190,884 in 2014, the city lies at the core of the Salt Lake City metropolitan area, which has a total population of 1,153,340 (2014 estimate). Salt Lake City is further situated within a larger metropolis known as the Salt Lake City-Ogden-Provo Combined Statistical Area. This region is a corridor of contiguous urban and suburban development stretched along an approximately segment of the Wasatch Front, comprising a total population of 2,423,912 . It is one of only two major urban areas in the Great Basin (the other is Reno, Nevada), and the largest in the Intermountain West., The State University System of Florida (SUS, or SUSF out-of-state) is a system of twelve public universities in the U.S. state of Florida. As of 2015, over 341,000 students were enrolled in Florida's state universities. Together with the Florida College System, which includes Florida's 28 community colleges and state colleges, it is part of Florida's system of public higher education. The system, headquartered in Tallahassee, is overseen by a Chancellor and governed by the Florida Board of Governors., Professor (commonly abbreviated as \"prof.\") is an academic rank at universities and other post-secondary education and research institutions in most countries. Literally, \"professor\" derives from Latin as a \"person who professes\" being usually an expert in arts or sciences, a teacher of the highest rank., The University of Florida (commonly referred to as Florida or UF) is an American public land-grant, sea-grant, and space-grant research university on a campus in Gainesville, Florida. It is a senior member of the State University System of Florida and traces its origins to 1853, and has operated continuously on its Gainesville campus since September 1906., James Bernard Machen ( born March 26 , 1944 ) is an American university professor and administrator . Machen is a native of Mississippi , and earned multiple academic degrees before becoming a university administrator and president . Machen previously was the president of the University of Utah in Salt Lake City , Utah and the University of Florida in Gainesville , Florida . He also sits on the Sanford - Burnham Medical Research Institute 's Board of Trustees . On June 8 , 2012 , Machen announced he would be stepping down as President in 2013 . However , in January 2013 , it was revealed that Machen would continue serving as the President of University of Florida ., Subject: bernie machen, Relation: position_held, Options: (A) 3 (B) 4 (C) chancellor (D) master (E) physician (F) professor (G) reno\nOutput:"
},
{
"from": "gpt",
"value": "chancellor"
}
] |
[
{
"from": "human",
"value": "Teacher:Given a sentence in English language, translate the sentence to Somali language keeping the meaning of the original sentence intact\nTeacher: Now, understand the problem? Solve this instance: English sentence: 2 And certain of the Pharisees said unto them, Why do ye that which is not lawful to do on the sabbath days?\nStudent:"
},
{
"from": "gpt",
"value": "2 Laakiin Farrisiintii qaarkood waxay ku yidhaahdeen, Maxaad u samaynaysaan wixii aan xalaal ahayn in sabtida la sameeyo?"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Generate an overlapping word between the given two sentences. When you find the overlapping words, they don't have to match exactly, e.g., \"survival\" and \"survive\" are valid overlapping words. Little words like \"the\" or \"of\" don't count! You must generate significant words which are not the stop words.\nQ: Sentence1: threatening behavior by predators causes a porcupine to extend its quills. \nSentence2: Porcupines are in the rodent family.\nA:"
},
{
"from": "gpt",
"value": "porcupine"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task you are given a sentence. You must judge whether there exist two consecutive words within the sentence with flipped orders, that is, whether the sentence will make sense and be correct if the order of two consecutive words changes. Label the instances as \"Inversion\" or \"Original\" based on your judgment.\nInput: You nod to your partner.\nOutput:"
},
{
"from": "gpt",
"value": "Original"
}
] |
[
{
"from": "human",
"value": "In this task, you need to remove all words of a given length in the sentence. The number of letters in a word determine its length, for example, the length of the word \"apple\" is 5.\n--------\nQuestion: Sentence: 'several orange trees with oranges are sitting in a store'. Remove all words of length '7' in the given sentence.\n\nAnswer: orange trees with are in a store\n\n\nQuestion: Sentence: 'a person wearing blue shoes riding a skateboard'. Remove all words of length '4' in the given sentence.\n\nAnswer: a person wearing shoes riding a skateboard\n\n\nQuestion: Sentence: 'a dog is standing in the water with a purple frisbee while another dog takes a drink'. Remove all words of length '7' in the given sentence.\n\nAnswer:"
},
{
"from": "gpt",
"value": "a dog is standing in the water with a purple while dog takes a drink\n\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. 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.\n\nContext: Jordan got rid of the mess altogether despite the roommates being the ones who made it. \n Question: Why did Jordan do this? \n Options: (A) lecture her roommates (B) finally clean the mess (C) show the roommates they suck\n"
},
{
"from": "gpt",
"value": "C"
}
] |
[
{
"from": "human",
"value": "Generate a question which can yield the answer mentioned in the input. Generated question must be answered by the answer provided in input, without using any extra knowledge.\n\nQ: Context : Celluloid Man is a 2012 documentary film directed by Shivendra Singh Dungarpur that explores the life and work of legendary Indian archivist P. K. Nair, founder of the National Film Archive of India and guardian of Indian cinema. \nAnswer : India\n\nA: Which place is Celluloid Man in?\n****\nQ: Context : IEEE C2 is the Institute of Electrical and Electronics Engineers standard for National Electrical Safety Code. \nAnswer : Institute of Electrical and Electronics Engineers\n\nA: Who set the standards for IEEE C2?\n****\nQ: Context : Ernest George Horlock VC (also known as Ernest George Harlock) (24 October 1885 -- 30 December 1917) was an English recipient of the Victoria Cross, the highest and most prestigious award for gallantry in the face of the enemy that can be awarded to British and Commonwealth forces. \nAnswer : Victoria Cross\n\nA:"
},
{
"from": "gpt",
"value": "What was the award received by Ernest George Horlock?\n****\n"
}
] |
[
{
"from": "human",
"value": "In this task you are given a sentence. You must judge whether there exist two consecutive words within the sentence with flipped orders, that is, whether the sentence will make sense and be correct if the order of two consecutive words changes. Label the instances as \"Inversion\" or \"Original\" based on your judgment.\nOne example: He poured out his to heart God, and after a few minutes the need left him, for a while anyway.\nSolution is here: Inversion\nExplanation: \"heart\" and \"to\" have been inverted.\n\nNow, solve this: The only way to reestablish the moral rules was win to the games as quickly as possible.\nSolution:"
},
{
"from": "gpt",
"value": "Inversion"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you will be presented with a question in Dutch language, and you have to write the person names from the question if present. B denotes the first item of a phrase and an I any non-initial word. Phrase used for the person name - PER. There can be instances with no person name entity, then return 'None'.\nInput: publicatie\nOutput:"
},
{
"from": "gpt",
"value": "None"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a context, a subject, a relation, and many options. Based on the context, from the options select the object entity that has the given relation with the subject. Answer with text (not indexes).\n\nExample input: Context: Joanne McLeod is a Canadian figure skating coach. She is the skating director at the Champs International Skating Centre of BC (formerly known as the BC Centre of Excellence). Here current and former students include Emanuel Sandhu, Mira Leung, Kevin Reynolds, Jeremy Ten, Nam Nguyen, and many others. In 2012, McLeod became the first level 5 certified figure skating coach in British Columbia., Victor Kraatz, MSC (born April 7, 1971) is a Canadian former ice dancer. In 2003, he and his partner, Shae-Lynn Bourne, became the first North American ice dancers to win a World Championship., Allie Hann-McCurdy (born May 23, 1987 in Nanaimo, British Columbia) is a Canadian ice dancer. McCurdy began skating at age eight and was a singles skater until age 12 when she switched to ice dancing. In 2003 she teamed up with Michael Coreno, with whom she was the 2010 Four Continents silver medalist and the 2008 Canadian bronze medalist. The pair retired in June 2010, to coach at the Gloucester Skating Club., Maikki Uotila - Kraatz ( born 25 February 1977 ) is a Finnish ice dancer . She is a former Finnish national champion with Toni Mattila . She married Victor Kraatz on June 19 , 2004 . The two coach in Vancouver , where they are the ice dancing directors at the BC Centre of Excellence . She and Kraatz have two sons , born September 14 , 2006 and July 10 , 2010 ., Burnaby is a city in British Columbia, Canada, located immediately to the east of Vancouver. It is the third-largest city in British Columbia by population, surpassed only by nearby Surrey and Vancouver., Canada (French: ) is a country in the northern half of North America. Its ten provinces and three territories extend from the Atlantic to the Pacific and northward into the Arctic Ocean, covering , making it the world's second-largest country by total area and the fourth-largest country by land area. Canada's border with the United States is the world's longest land border. The majority of the country has a cold or severely cold winter climate, but southerly areas are warm in summer. Canada is sparsely populated, the majority of its land territory being dominated by forest and tundra and the Rocky Mountains. About four-fifths of the country's population of 36 million people is urbanized and live near the southern border. Its capital is Ottawa, its largest city is Toronto; other major urban areas include Montreal, Vancouver, Calgary, Edmonton, Quebec City, Winnipeg and Hamilton., British Columbia (BC) is the westernmost province of Canada, with a population of more than four million people located between the Pacific Ocean and the Rocky Mountains. \nBritish Columbia is also a component of the Pacific Northwest and the Cascadia bioregion, along with the U.S. states of Idaho, Oregon, Washington and Alaska., The \"Champs International Skating Centre of British Columbia\" (formerly known as the 'BC Centre of Excellence') is one of two major figure skating training centers in Canada. Located in Burnaby, British Columbia, it is home to many great national and international skaters. The programs there are overseen by a staff, including Joanne McLeod, who coaches 3-time Canadian men's national champion Emanuel Sandhu; Bruno Marcotte, who competed at the 2002 Winter Olympics; Victor Kraatz, the 2003 World Champion in ice dancing, and Maikki Uotila, who was a national champion in Finland. The center operates out of Canlan Ice Sports Burnaby 8 Rinks. Notable skaters who train there include Emanuel Sandhu, Mira Leung, Allie Hann-McCurdy & Michael Coreno, Jessica Millar & Ian Moram, Jeremy Ten, and Kevin Reynolds. This skating school is sometimes known as a training site for international competitors to practice for competitions in Vancouver. Champs International hosts its annual competition known as the BC/YK SummerSkate Competition every August., Shae-Lynn Bourne, MSC (born January 24, 1976) is a Canadian ice dancer. In 2003, she and partner Victor Kraatz became the first North American ice dancers to win a World Championship. They competed at three Winter Olympic Games, placing 10th at the 1994 Winter Olympics, 4th at the 1998 Winter Olympics, and 4th at the 2002 Winter Olympics., Vancouver, officially the City of Vancouver, is a coastal seaport city on the mainland of British Columbia, Canada, and the most populous city in the province., Subject: maikki uotila, Relation: country_of_citizenship, Options: (A) american (B) british (C) canada (D) finland (E) montreal\nExample output: finland\nExample explanation: This is a good example, as maikki uotila is citizen of the finland.\nQ: Context: Nobuhiko Takada (born April 12, 1962) is a Japanese former mixed martial arts fighter and professional wrestler. He was an executive of PRIDE Fighting Championships and founder of the HUSTLE professional wrestling promotion., Triton College is a public two-year community college located in River Grove, Illinois, a suburb northwest of downtown Chicago., Mixed martial arts (MMA) is a full-contact combat sport that allows both striking and grappling, both standing and on the ground, using techniques from other combat sports and martial arts. The first documented use of the term \"mixed martial arts\" was in a review of UFC 1 by television critic Howard Rosenberg in 1993. The term gained popularity when newfullcontact.com, then one of the largest websites covering the sport, hosted and republished the article. The question of who actually coined the term is subject to debate., K-1 began in 1993 and is a kickboxing platform and martial arts brand well-known worldwide mainly for its heavyweight division fights. On January 2012, K-1 Global Holdings Limited, a company registered in Hong Kong, acquired the rights to K-1, and is the current organizer of K-1 events worldwide., River Grove is a village in Cook County, Illinois, United States. The population was 10,227 at the 2010 census., The National Collegiate Athletic Association (NCAA) is a non-profit association which regulates athletes of 1,281 institutions, conferences, organizations, and individuals. It also organizes the athletic programs of many colleges and universities in the United States and Canada, and helps more than 450,000 college student-athletes who compete annually in college sports. The organization is headquartered in Indianapolis, Indiana. In 2014, the NCAA generated almost a billion dollars in revenue. 80 to 90% of this revenue was due to the Men's Division I Basketball Tournament. This revenue is then distributed back into various organizations and institutions across the United States., Tom Erikson ( born July 6 , 1964 ) is an American former amateur wrestler and mixed martial artist who competed in the super heavyweight division . Weighing between 127.1 kg ( 280 lb ; 20.01 st ) and 139.8 kg ( 308 lb ; 22.01 st ) throughout his career , `` The Big Cat '' began wrestling at an early age and was twice National Junior College Athletic Association ( NJCAA ) Junior Collegiate Champion at Triton College before achieving National Collegiate Athletic Association ( NCAA ) Division I honors twice at Oklahoma State University -- Stillwater . He embarked on his career in MMA in 1996 and went on to fight in the Pride Fighting Championships . Erikson was a long time assistant wrestling coach at Purdue University , where he has been coaching since 1997 . In 2015 Tom accepted the head wrestling coach position at Lyon College in Batesville , Arkansas ., Pride Fighting Championships (Pride or Pride FC, founded as KRS-Pride) was a Japanese mixed martial arts (MMA) organization founded by Nobuyuki Sakakibara and Nobuhiko Takada. Its inaugural event was held at the Tokyo Dome on October 11, 1997. Pride held more than sixty mixed martial arts events, broadcast to about 40 countries worldwide. Pride held the largest live MMA event audience record of 91,107 people at the Pride and K-1 co-production, \"Shockwave/Dynamite\", held in August 2002, as well as the audience record of over 67,450 people at the \"Pride Final Conflict 2003\". For ten years PRIDE was one of the most popular MMA organizations in the world., Canada (French: ) is a country in the northern half of North America. Its ten provinces and three territories extend from the Atlantic to the Pacific and northward into the Arctic Ocean, covering , making it the world's second-largest country by total area and the fourth-largest country by land area. Canada's border with the United States is the world's longest land border. The majority of the country has a cold or severely cold winter climate, but southerly areas are warm in summer. Canada is sparsely populated, the majority of its land territory being dominated by forest and tundra and the Rocky Mountains. About four-fifths of the country's population of 36 million people is urbanized and live near the southern border. Its capital is Ottawa, its largest city is Toronto; other major urban areas include Montreal, Vancouver, Calgary, Edmonton, Quebec City, Winnipeg and Hamilton., Subject: tom erikson, Relation: occupation, Options: (A) canada (B) combat sport (C) cook (D) critic (E) major (F) platform (G) professional wrestler (H) television\nA:"
},
{
"from": "gpt",
"value": "professional wrestler"
}
] |
[
{
"from": "human",
"value": "This task is about translating a given English language sentence to French.\n\nQ: I call this woman that has\n\nA: J'appelle cette femme a\n****\nQ: Uh...\n\nA: Uh...\n****\nQ: We didn't care\n\nA:"
},
{
"from": "gpt",
"value": "On s'en fichait\n****\n"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a paragraph and title from the research paper. Your task is to classify whether the given title is suitable or not for the research paper based on the given paragraph. Return \"True\" if title is proper according to paragraph else \"False\".\nQ: Paragraph: Biochar, that is, carbonized biomass similar to charcoal, has been used in acute medical treatment of animals for many centuries. Since 2010, livestock farmers increasingly use biochar as a regular feed supplement to improve animal health, increase nutrient intake efficiency and thus productivity. As biochar gets enriched with nitrogen-rich organic compounds during the digestion process, the excreted biochar-manure becomes a more valuable organic fertilizer causing lower nutrient losses and greenhouse gas emissions during storage and soil application. Scientists only recently started to investigate the mechanisms of biochar in the different stages of animal digestion and thus most published results on biochar feeding are based so far on empirical studies. This review summarizes the state of knowledge up to the year 2019 by evaluating 112 relevant scientific publications on the topic to derive initial insights, discuss potential mechanisms behind observations and identify important knowledge gaps and future research needs. The literature analysis shows that in most studies and for all investigated farm animal species, positive effects on different parameters such as toxin adsorption, digestion, blood values, feed efficiency, meat quality and/or greenhouse gas emissions could be found when biochar was added to feed. A considerable number of studies provided statistically non-significant results, though tendencies were mostly positive. Rare negative effects were identified in regard to the immobilization of liposoluble feed ingredients (e.g., vitamin E or Carotenoids) which may limit long-term biochar feeding. We found that most of the studies did not systematically investigate biochar properties (which may vastly differ) and dosage, which is a major drawback for generalizing results. Our review demonstrates that the use of biochar as a feed additive has the potential to improve animal health, feed efficiency and livestock housing climate, to reduce nutrient losses and greenhouse gas emissions, and to increase the soil organic matter content and thus soil fertility when eventually applied to soil. In combination with other good practices, co-feeding of biochar may thus have the potential to improve the sustainability of animal husbandry. However, more systematic multi-disciplinary research is definitely needed to arrive at generalizable recommendations. \n Title: The use of biochar in animal feeding Distributed under Creative Commons CC-BY 4.0\nA: "
},
{
"from": "gpt",
"value": "False"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you are to Translate German text to English\n\nSo werden Verluste im magnetischen Fluss reduziert.\n"
},
{
"from": "gpt",
"value": "Losses in magnetic flux are thus reduced."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given a short story consisting of exactly 5 sentences where the second sentence is missing. You are given two options and you need to select the one that best connects the first sentence with the rest of the story. Indicate your answer by 'Option 1' if the first option is correct, otherwise 'Option 2'. The incorrect option will change the subsequent storyline, so that at least one of the three subsequent sentences is no longer consistent with the story.\nQ: Sentence 1: Tom noticed that his porch had become very dusty. \n Sentence 3: Finally Tom realized that he needed to sweep the porch himself \n Sentence 4: He found a broom and swept the porch meticulously \n Sentence 5: Tom was happy to see the porch wasn't dusty any longer \n Option 1: He dusted it every day from then on. \n Option 2: He tried convincing his son to sweep it, but his son refused.\nA:"
},
{
"from": "gpt",
"value": "Option 2"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given two strings A,B. You must perform the following operations to generate the required output list: (i) Find the longest common substring in the strings A and B, (ii) Convert this substring to all lowercase and sort it alphabetically, (iii) Replace the substring at its respective positions in the two lists with the updated substring.\nQ: OvHjKvUZZMuvmFLqplTpFTaxCFGmuyNomSbdfhAN, BdqTAcklCuOlTpFTaxCFGmuyNomSAAgSJkZkQODhaCp\nA:"
},
{
"from": "gpt",
"value": "OvHjKvUZZMuvmFLqpacffglmmnopsttuxybdfhAN, BdqTAcklCuOacffglmmnopsttuxyAAgSJkZkQODhaCp"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task, you need to replace a letter in the sentence with another given letter.\nTeacher: Now, understand the problem? Solve this instance: Sentence: 'a persons feet are up next to a pizza box'. Replace the letter 'r' with 'g' in the sentence.\nStudent:"
},
{
"from": "gpt",
"value": "a pegsons feet age up next to a pizza box"
}
] |
[
{
"from": "human",
"value": "Teacher:Generate a question which can yield the answer mentioned in the input. Generated question must be answered by the answer provided in input, without using any extra knowledge.\nTeacher: Now, understand the problem? Solve this instance: Context : Saint George and the Princess is a fresco by the Italian master Pisanello, located in the Pellegrini Chapel of the church of Sant'Anastasia, Verona, northern Italy. \nAnswer : Sant'Anastasia\nStudent:"
},
{
"from": "gpt",
"value": "What is the name of the place where Saint George and the Princess can be found?"
}
] |
[
{
"from": "human",
"value": "In this task you will be given a claim and a perspective. You should determine whether that perspective supports or undermines the claim. If the perspective could possibly convince someone with different view, it is supporting, otherwise it is undermining.\n\n[Q]: claim: Targeted sanctions have to be used to respond to cyber-attacks.\n perspective: Sanctions are indiscriminate\n[A]: undermine\n\n\n[Q]: claim: The age of consent laws should be lowered.\n perspective: If the consent age is lowered, more people will be in danger.\n[A]: undermine\n\n\n[Q]: claim: The Guantanamo Bay detention centre should be closed.\n perspective: Conditions at Guantanamo are unjust and unacceptable: \n[A]:"
},
{
"from": "gpt",
"value": "support\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, positions of two consecutive words have been swapped. You need to output the position of the swaped words. e.g. in the sentence 'Seattle has nice a weather', the word 'a' and 'nice' have been swapped. These words are at 3rd and 4th position respectively. So, the output should be (3, 4). Note that the index of first word is 1.\nOne example is below.\nQ: I a am professional dancer.\nA: (2,3)\nRationale: words 'a' and 'am' have been swapped. The correct sentence would be 'I am a professional dancer.'. Since the position of 'a' is 2 and 'am' is 3, the answer is (2,3).\nQ: A thin crust pizza covered in green dark spinach\nA:"
},
{
"from": "gpt",
"value": "(7, 8)"
}
] |
[
{
"from": "human",
"value": "You are given a sentence from a conversation between a human and a virtual assistant. Your task is to classify the sentence into one of the following five action categories - INFORM, INFORM_INTENT, OFFER, REQUEST, REQUEST_ALTS. If the sentence is about informing something, generate 'INFORM'. If it is about requesting something, generate 'REQUEST'. If the sentence mentions requesting an alternative option than the one provided, generate 'REQUEST_ALTS'. Similarly, generate 'OFFER' if the sentence is offering some information. If the sentence is about showing intent to do something, generate 'INFORM_INTENT'.\nOne example is below.\nQ: Now seems a good moment to watch the movie.\nA: INFORM_INTENT\nRationale: The user is passively expressing his intent to watch a movie and asking for a suggestion\nQ: What else have you got?\nA:"
},
{
"from": "gpt",
"value": "REQUEST_ALTS"
}
] |
[
{
"from": "human",
"value": "In this task, you're given the title of a story consisting of five sentences, numbered 1 through 5. Your job is to determine which two sentences need to be swapped sentences in order to make a story that makes complete sense and is befittingly titled. Indicate your answer using the numbers of the two sentences in order, such as '34' or '25'. The first digit refers to the sentence which should come first in the story.\nQ: Title: The Cute Girl. Sentence 1: She left without him saying anything. Sentence 2: He noticed a really cute girl there too. Sentence 3: He kept trying to build up the courage to talk to her. Sentence 4: Tim was never really able to. Sentence 5: Tim was at the laundromat.\nA: "
},
{
"from": "gpt",
"value": "51"
}
] |
[
{
"from": "human",
"value": "Definition: You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. You are required to assign a label 'formal' if there is an absence of emotion and a presence of questions anywhere within the conversation. If such pattern is not found assign the label 'informal'.\nInput: Person1: I've got to go home and study . \n Person2:For what ? \n Person1: The test tomorrow . \n Person2:If you don't know it by now , you might as well not bother studying . \nOutput:"
},
{
"from": "gpt",
"value": "formal"
}
] |
[
{
"from": "human",
"value": "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.\n\n[EX Q]: Capital Gains Reform Act of 1997 - Amends the Internal Revenue Code to revise rules concerning capital gain for taxpayers other than corporations to establish a new general rule which provides that if for any taxable year a taxpayer other than a corporation has a capital gain, 70 percent of such gain shall be a deduction from gross income. \nReduces the alternative capital gain tax for corporations.\n[EX A]: Capital Gains Reform Act of 1997\n\n[EX Q]: Congressional Pay for Performance Act - Suspends basic pay adjustments for Members of Congress, and requires pay reductions, until the deficit is reduced to below $50,000,000,000 without the enactment of any change in the Internal Revenue Code. \nRequires an annual reduction in pay by a percentage equal to: (1) two percent times the number of hundreds of billions of dollars of the deficit in the first year after enactment; or (2) twice that percentage for any year following a year for which the deficit is not at least $100,000,000,000 less than the lowest level attained after enactment of this Act. \nSuspends pay reductions upon enactment of a declaration of war and reinstates them when the state of war is concluded. \nRestores pay adjustment procedures suspended by this Act, and provides for a rate of basic pay of twice the rate in effect as of the effective date of this Act, for the first year with respect to which the deficit is less than $50,000,000,000.\n[EX A]: Congressional Pay for Performance Act\n\n[EX Q]: Mandates annual claim maintenance fees of $100 per claim per calendar year (except shale claims subject to claim maintenance fees under the Energy Policy Act of 1992). Reduces such fees by the amount of the claim maintenance fees paid under the Omnibus Budget Reconciliation Act of 1993. Allows the Secretary of the Interior, acting through the Director of the Minerals Management Service (MMS), to waive claim maintenance fees for claim holders that, with all related parties, held no more than ten claims on lands open to location. \nStates that the claim interest of any co-owner who fails to contribute his portion of the claim maintenance fee shall become the property of the co-owners who have paid the required fee. \nSubjects the production of locatable minerals located under the general mining laws (including their concentrates and products) to a royalty payment of eight percent of the gross income. \nPrescribes guidelines for the duties of claim holders, operators, and transporters. Authorizes the Secretary to require by rule that transporters possess documentation showing the amount, origin, and intended destination of the locatable mineral, concentrate or product. Prescribes recordkeeping, reporting, and auditing requirements. \nAuthorizes the Secretary to enter into cooperative agreements with the Secretary of Agriculture to implement this Act. \nProvides for: (1) interest and substantial underreporting assessments in cases of tardy or delinquent mining claim royalty payments; and (2) several and joint liability for royalty payments on all locatable minerals, concentrates, or products derived therefrom which are lost or wasted due to negligence or noncompliance with regulations. \nDirects the Secretary to adjust dollar amounts every ten years for changes in the purchasing power of the dollar.\n[EX A]:"
},
{
"from": "gpt",
"value": "To provide for claim maintenance fees and royalties on hardrock mining claims, and for other purposes.\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you are given one French sentence. The major part of the sentences talk about health-related topics, but some of the them describe an organization and its activities. Your job is to translate the given sentences into English.\n\nSauvegarder cette page dans un fichier au format PDF\n"
},
{
"from": "gpt",
"value": "Save this page as a PDF file"
}
] |
[
{
"from": "human",
"value": "Given an object and a part, decide whether the object has that part. For example if you are asked 'gun has barrel?', you need to decide if a gun has a barrel as one of its components or parts, indicating 1 or 0 as your answer respectively. All sentences strictly follow the template 'object has part?.'\n\n[EX Q]: vest has back?\n[EX A]: 1\n\n[EX Q]: battleship has wing?\n[EX A]: 0\n\n[EX Q]: van has eye?\n[EX A]:"
},
{
"from": "gpt",
"value": "0\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: The input is a tweet which can be classified as Hate Speech, Offensive or Normal. Given such a tweet, output the class the tweet belongs to. Hate Speech will contain threatening language towards the community targeted. Offensive language will contain abusive or discriminatory language towards the community targeted.\nQ: funfact genghis khan killed more people than the holocaust did\nA:"
},
{
"from": "gpt",
"value": "Offensive"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: identity-attack and non-identity-attack. Identity attack refers to anything rude or disrespectful about someone's identity, including appearance, race, gender, and sexual orientation.\nTeacher: Now, understand the problem? Solve this instance: Comment: They are inept at foreign policy.\nThey gave cash and weapons to our enemies.\nThey ignored the middle class.\nThey tried to make the police our enemy.\nThey left the border door open for criminals to move to and STAY in our country.\nThey persecuted people who didn't agree with their agenda.\nThey forced health care insurance down our throats.\nThey were replaced.\nStudent:"
},
{
"from": "gpt",
"value": "Non-identity-attack"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nConstruct a question that every answer in the list is correct and reasonable for it.\nExample: umbrella, sunscreen, sun hat, sunglasses, cover up, shade\nOutput: at the beach, name something that might protect you from sun.\numbrella, sunscreen, sun hat, sunglasses, cover up and shade can provide protection for the people at the beach\n\nNew input case for you: cheat, cram, fail, play sick, cut school\nOutput:"
},
{
"from": "gpt",
"value": "name something students do when they forget to study for a test."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given two lists A,B. Find the longest common subsequence in the lists A and B.\nQ: ['J', 'm', 'c', 'X', 'z', 'j', 7431, 9131, 'u', 'q', 6897, 'B', 5919, 9699, 'T', 'O', 't', 'Z', '433', '8061', '9845', '6529', '5239', '5925', 'r', '5321', '5931', 'Z', 'X', '5575', '4661', '8951', 'I', 'K', 'v', '3903', 'M', 'x', '9913', '4051', 'T', 'F', 9373, 'E', 'h', 8435], ['x', 2251, 'T', 9323, 437, 4277, 7665, 8657, 4959, 'u', 'n', 'q', 'B', 3215, 'm', 'Z', 'W', 'B', 'M', 9601, 2989, 'Z', 4743, 'O', 1189, 'O', 't', 'Z', '433', '8061', '9845', '6529', '5239', '5925', 'r', '5321', '5931', 'Z', 'X', '5575', '4661', '8951', 'I', 'K', 'v', '3903', 'M', 'x', '9913', '4051', 'A', 4175, 5147]\nA:"
},
{
"from": "gpt",
"value": "O, t, Z, 433, 8061, 9845, 6529, 5239, 5925, r, 5321, 5931, Z, X, 5575, 4661, 8951, I, K, v, 3903, M, x, 9913, 4051"
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: Given a set of four words, generate the category that the words belong to. Words are separated by commas. The possible categories are social gathering, accomodation, physical property, measurement unit, corporate, nutritional value, boats, police punishment, location (proximity), card games, outdoor sport activity, military rank, baby animals, weather, consumer product, animals, boxing terminology, food, chocolate food, bird, type of sandwich, date status, body part, ocean, employment activity, moral characteristic, elements, poker, computers, construction, guitar part, shady activities, physical activity, kitchenware, temperature, type of rigidity, emotional status, season, mode of transportation, window material, activity, emotional display, geographical property, fried food, store status, widespread, aesthetic characteristic, alcoholic drinks, secretary duty, direction, personal characteristic, and animal.\nPROBLEM: down, emotional state, emotional supports, remorseful\n\nSOLUTION: emotional status\n\nPROBLEM: expression, fawn, cute, identity\n\nSOLUTION: emotional display\n\nPROBLEM: deal, mild, fair, brisk\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "weather\n\n"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task, you will be presented with a passage and have to answer a question based on your understanding of the events inferred from the passage. Among the entities, try to find the best entity that is most likely to fill in \"_\" and classify the answers based on options.\nTeacher: Now, understand the problem? Solve this instance: Washington (CNN) Bernie Sanders Tuesday vowed to break up America's biggest financial firms during his first year in office, as he laid out his vision for Wall Street reform in a New York City speech. He pledged to draft a list of firms whose failure would put the U.S. economy at risk in his first 100 days in office and require those firms to reorganize within a year, saying that \"if a bank is too big to fail, it is too big to exist.\" The Vermont senator and Democratic presidential contender repeatedly cast rival Hillary Clinton as too close to moneyed interests to seriously take on the banks that have faced $204 billion in fines since 2009.Sanders pledged to draft a list of firms whose failure would put the U.S. economy at risk in his first 100 days in officeSanders repeatedly cast rival Hillary Clinton as too close to moneyed interests to seriously take on the banks \n Questions:\"The reality is that fraud is the business model on _,\" he said. (A) Washington (B) CNN (C) Bernie Sanders (D) America (E) Wall Street (F) New York City (G) U.S. (H) Vermont (I) Democratic (J) Hillary Clinton (K) Sanders\nStudent:"
},
{
"from": "gpt",
"value": "(E)"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: sexual-explicit and non-sexual-explicit. A comment is considered sexual-explicit if it explicitly portrays sexual matters.\nQ: Comment: Nobody will ever be able to match former Republican speaker of the House, Dennis Hastert, who raped repeatedly a teenage boy that grew up and stalked Hastert for well over $1 million in blackmail money. Hastert was two seat away from the presidency. The Republican insiders had to have known about the closet homosexual/rapist. And the guy never was brought to trial for raping a teenage boy.\nA: "
},
{
"from": "gpt",
"value": "Sexual-explicit"
}
] |
[
{
"from": "human",
"value": "In this task you will be given two dialogues. You need to determine if both dialogues have the same underlying emotion. The possible emotions are happy, sad, angry, or other. If they do output 'yes', if not output 'no'.\n\n[EX Q]: Dialogue 1: 'yeah they were just awessome glad they knew it was just a prank xd hahaha true'. Dialogue 2: 'i thought u r related to movies merely renting it sake means'.\n[EX A]: no\n\n[EX Q]: Dialogue 1: 's thanks birthdaycake happy bday'. Dialogue 2: 'i'm wild too yeah we're definitely gonna have a blast awesome let's catch up'.\n[EX A]: no\n\n[EX Q]: Dialogue 1: 'whatquestionmarkanguishedfacefrowningfacewithopenmouthquestionmark i don't know but the answer is 42 you are number'. Dialogue 2: 'near me i need so much come i take you there'.\n[EX A]:"
},
{
"from": "gpt",
"value": "yes\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task you will be given a list, of lists, of numbers. Each list is presented with brackets and comma-separated values. For example, a list of numbers is [1,2,3] and a list of two lists of numbers is [[1,2],[3,4,6]]. You should sum up the values at every position of every inner list and put it as an element of your answer, that is, you should sum the first members of each inner list together and put it as the first element of the list, then sum the second members of each inner list together and put it as the second element of your list, etc. The output should be a list of numbers with the same length as the longest inner list.\n\n[[-77, -89, 41, -31, 2, 38], [-60, 74, 97, -37], [72, -27, -75]]\n"
},
{
"from": "gpt",
"value": "[-65, -42, 63, -68, 2, 38]"
}
] |
[
{
"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? Solve this instance: The script feels as if it started to explore the obvious voyeuristic potential of ` hypertime ' but then backed off when the producers saw the grosses for Spy Kids .\nStudent:"
},
{
"from": "gpt",
"value": "NEG"
}
] |
[
{
"from": "human",
"value": "Teacher:This task is to identify the language of a sentence correctly by classifying if it is English or Telugu\nTeacher: Now, understand the problem? Solve this instance: His smile says it all!\nStudent:"
},
{
"from": "gpt",
"value": "English"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you are given a Reddit post as a text. Your task is to generate a title for this text. The title should start with \"TIFU by\", followed by a situation that caused humor. The title should contain 7-12 words, ideally.\n\nText: of course this fuck up happened not today, but three months ago. \n\nso i was over at my friends house, lets call him jacob. he, his roommates and i were all hanging having a few drinks. harmless fun for a while until we got drunk and started to get bored (famous last words).\n\nwell i should also say that at the time we were all active duty military, wont say what branch because it may give away his identity.\n\nanyway, what better way is there for a few troops to quench boredom other than proving that one guy was stronger than the other? so we begin punching each other.\n\nit wasn't fighting mind you, just hit-for-hit deliberate punches to determine whose was harder.\n\nso we're a few rounds in and a bit sore when its my turn again. \ni pull back my fist, ready to go full strength on his arm. i throw the punch and crack!\n\nit would seem that after about half a bottle of vodka, my aim may have been a bit impaired. instead of hitting his arm square-on, i sort of glanced off the side and my wrist bent with it. a loud crack and an explosion of pain told me that perhaps, i may have hurt myself. so i wrapped it with an ace bandage, applied ice and resolved to go to the base clinic the next day if it didnt feel better in the morning.\n\na few pretty x-rays later, i found out i broke my wrist. more particularly my scaphoid. a relatively seriously break since one of the blood supplies to my hand runs over it. the dr./capt. told me that it would require surgery. \n\nso now i have a new piece of hardware in my wrist and a rather unsightly scar. awesome. fapping is never going to be the same.\n\n\n\n \nplayed a punching game to prove who threw harder whilst i was drunk, ended up breaking my wrist and requiring surgery and a screw. i either won that game or lost...you be the judge.\n"
},
{
"from": "gpt",
"value": "TIFU by throwing drunkin punches"
}
] |
[
{
"from": "human",
"value": "You are asked to create a question containing a blank (_), based on the given context word. Your question must contain two related but different objects; for example \"trophy\" and \"suitcase\". The expected answer to your question must be one of the objects present in the sentence. The expected answer must not be associated with any specific word in the question; instead it should depend on the context present in the question. The expected answer should not be equally likely to fill the blank. For your question, there should be a agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use animals or proper nouns (e.g., New York, Macbook, Jeff Bezos, McDonald's, ...) as your objects. Avoid repeating the same style, pattern or phrases in each question, try to increase diversity by varying sentence structure, blank placement etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Object X and Y have the same number e.g. when ObjectX is singular, Object Y must be singular, too. The two objects (Object X & Object Y) should be used ONCE in your question. Here is a list of attributes and associated pair of contrastive words which may be used to create a valid question using the objects. You can use either of the contrastive words, but not both. You should think about more such attributes and associated words and use them in your question.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\n\nEx Input:\nContext Word: gemini.\n\nEx Output:\nJeff determined that Chris was a Virgo and not a Gemini because the _ is more reserved.\n\n\nEx Input:\nContext Word: layers.\n\nEx Output:\nSammy was trying to figure how many layers of clothes she would need 3 or 4.The _ would keep her warm.\n\n\nEx Input:\nContext Word: hotel.\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "Jimmy wanted to learn how to learn about the hotel market so he took a class but the _ is empty.\n\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. 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 fine 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 : '$': Dollar Sign, \"''\": Single Quotes, ',': Comma Symbol, '-LRB-': Left Parantheses, '-RRB-': Right Parantheses, '.': Period, ':': Colon, 'ADD': Email Address, 'AFX': Affix, 'CC': Coordinating conjunction, 'CD': Cardinal Number, 'DT': Determiner, 'EX': Existential there, 'FW': Foreign Word, 'GW': Go with, 'HYPH': Hyphen symbol, 'IN': Preposition or a subordinating conjunction, 'JJ': Adjective, 'JJR': A comparative Adjective, 'JJS': A Superlative Adjective, 'LS': List item Marker, 'MD': Modal, 'NFP': Superfluous punctuation, 'NN': Singular Noun, 'NNP': Singular Proper Noun, 'NNPS': Prural Proper Noun, 'NNS': Prural Noun, 'PDT': Pre-determiner, 'POS': Possessive Ending, 'PRP': Personal pronoun, 'PRP$': Possessive Pronoun, 'RB': Adverb, 'RBR': Comparative Adverb, 'RBS': Superlative Adverb, 'RP': Particle, 'SYM': Symbol, 'TO': To , 'UH': Interjection, 'VB': Base form Verb, 'VBD': Verb in Past tense, 'VBG': Verb in present participle, 'VBN': Verb in past participle, 'VBP': Verb in non-3rd person singular present, 'VBZ': Verb in 3rd person singular present, 'WDT': Wh-determiner, 'WP': Wh-pronoun, 'WP$' Possessive Wh-pronoun, 'WRB': Wh-adverb, 'XX': Unknown, '``': Double backticks.\n\nSentence: instead of suggesting a specific rate increase - 10 or 15 % , I think we should acknowledge that a \" modest \" increase may be necessary and may in fact be desirable - but that the specific amount of increase should {{ be }} reasoned and subject to well thought out evidence and hearings , not just determined by whim . \nWord: be\n"
},
{
"from": "gpt",
"value": "VB"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair neither agree nor contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\n\nSentence 1: A man smiles while holding a rope on a boat. Sentence 2: a man smiles while holding a rope"
},
{
"from": "gpt",
"value": "the man was driving his new yacht"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you're given the beginning and the ending of a three-part story. Your job is to complete the short story by writing a middle sentence that seamlessly connects the first and last sentence. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the middle sentence, and use names (e.g. Jack, Barbara,...) instead of pronouns (e.g. he / she) wherever possible.\nProblem:Beginning: Jessica wanted to get her ears pierced, but her parents said no. Ending: She would never try something like that again!\nSolution:"
},
{
"from": "gpt",
"value": "Jessica asked her friends to pierce her ear."
}
] |
[
{
"from": "human",
"value": "You will be given a sentence. Check whether the sentence is grammatically correct and is meaningful. If the sentence is grammatically correct, then answer with '1', otherwise answer with '0'.\n\nInput: Consider Input: The bartender gave John some good beers.\n\nOutput: 1\n\n\nInput: Consider Input: Carmen bought a dress at Bloomingdale's.\n\nOutput: 1\n\n\nInput: Consider Input: This book cost $10.\n\n"
},
{
"from": "gpt",
"value": "Output: 1\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: insult and non-insult. Insult is any lanugage or act that is disrespectful or scornfully abusive.\n\nComment: 4. x=y=z=0."
},
{
"from": "gpt",
"value": "Non-insult"
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.