Search is not available for this dataset
conversations
listlengths 2
2
|
|---|
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, your goal is to judge a correct answer to a given question based on an associated paragraph and decide if it is a good correct answer or not. A good correct answer is one that correctly and completely answers the question. A bad correct answer addresses the question only partially or incorrectly. If you think the given correct answer is good, indicate it by responding \"Yes\". Otherwise, respond \"No\". There are only two types of responses possible: \"Yes\" and \"No\".\n\nParagraph- Sent 1: The series starts in Baghdad at an undetermined time .\nSent 2: The Sultan Shahryar has gone mad after accidentally killing his wife during a failed coup d' tat , which she had planned with Shahryar 's brother Schahzenan .\nSent 3: In his madness , Shahryar believes that all women now want to kill him , but the law states that the Sultan must be married again or the throne will be passed to his brother .\nSent 4: Shahryar therefore orders Grand Vizier Ja'Far ( ( ( Jim Carter to bring him a harem girl to marry and then have executed the next day .\nSent 5: In order to prevent this , the Grand Vizier 's clever daughter , Scheherazade , decides to marry the Sultan herself .\nSent 6: Scheherazade has a plan to prevent her execution and at the same time cure the Sultan of his madness .\nSent 7: With the help of some tutoring from a bazaar storyteller , Scheherazade tells the Sultan a story every night , stopping at dawn with a cliffhanger and refusing to continue until dusk .\nSent 8: Shahryar must therefore let Scheherazade live for another day in order to hear the rest of the story .\nSent 9: Cunningly , Scheherazade has hidden a moral within every story , to bring the Sultan out of his madness .\nSent 10: Meanwhile , Schahzenan hears about the Sultan 's madness and that he is unable to execute Scheherazade .\nSent 11: Perceiving this as weakness , Schahzenan leads his army to Baghdad in an attempt to take the throne by force .\nSent 12: However , by the time Schahzenan 's army reaches the city , Scheherazade 's plan has worked .\nSent 13: As a result of her stories , Shahryar has overcome his madness and has fallen in love with Scheherazade . \nQuestion: who is the sultan's madness knowing that baghdad in an attempt to take the throne by force? \nCorrect Answer: Schahzenan.\n"
},
{
"from": "gpt",
"value": "Yes."
}
] |
[
{
"from": "human",
"value": "In this task, you are given a sentence and a profession. The sentence mentions two professions: one's gender is identifiable using the coreference link with gendered pronouns and the other's gender is unidentifiable. You are expected to return whether the given profession's gender is identifiable or unidentifiable.\nOne example: Sentence: The cleaner called the guard because she forgot to bring her key.\n Profession: cleaner\nSolution is here: Identifiable\nExplanation: The cleaner's gender is identifiable because the pronoun \"she\" is linked to the cleaner.\n\nNow, solve this: Sentence: The guard saved the editor from the criminals because he was on duty.\n Profession: guard\nSolution:"
},
{
"from": "gpt",
"value": "Identifiable"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given a question containing a blank (_) and two options. You should pick the best option to answer the question. Please answer with \"A\" or \"B\".\n\nLeslie found it hard to be supportive of his student's efforts than Neil because _ did not have a lot of teaching experience. (A) Leslie (B) Neil\nOutput:"
},
{
"from": "gpt",
"value": "A"
}
] |
[
{
"from": "human",
"value": "Given a sentence in English, provide an equivalent paraphrased translation in German that retains the same meaning both through the translation and the paraphrase.\nExample: The NBA season of 1975 -- 76 was the 30th season of the National Basketball Association .\nExample solution: Die Saison 1975 - 76 der National Basketball Association war die 30. Saison der NBA.\nExample explanation: This is a correct and accurate translation from English to German because the translated paraphrase retains the main message that between the years 1975-1976, the 30th NBA season occurred.\n\nProblem: McSweeney was born in Northern Ireland , moved to London .\n"
},
{
"from": "gpt",
"value": "Solution: McSweeney wurde in Nordirland geboren, zog jedoch nach London."
}
] |
[
{
"from": "human",
"value": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\nQ: 7, 7, ['s', 'N', '9529', 'V', 'H', '7895', '1113']\nA: "
},
{
"from": "gpt",
"value": "1113"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task, you will be presented with the directions of a recipe separated by \",\" and have to fill in the \"___\" which is a step that is missing from the recipe.\nTeacher: Now, understand the problem? Solve this instance: In medium mixing bowl whip cream cheese until smooth.,Slowly add in Sweetened Condensed Milk.,______,Pour into Crust.,Refrigerate 4 hours or overnite.\nStudent:"
},
{
"from": "gpt",
"value": "Slowly add Lemon juice."
}
] |
[
{
"from": "human",
"value": "Teacher:In this task you will be given a list of numbers and you need to subtract every value in the list with the index it is at. The index of an elements shows its numerical order in the list(for example, in the list [7,10,4,5], the index of 7 is 1 and the index of 4 is 3) You should start the index at 1, so the first element in the list will be subtracted by one. For every element in the list you need to find \"element - index\" where the index of the beginning element is 1 and increments by 1 for each element. Put your result list in brackets.\nTeacher: Now, understand the problem? Solve this instance: [-20, -12, -13, -12, -9, 9, -4, -2, 7, -15]\nStudent:"
},
{
"from": "gpt",
"value": "[-21, -14, -16, -16, -14, 3, -11, -10, -2, -25]"
}
] |
[
{
"from": "human",
"value": "You are given a paragraph, with numbered sentences, and a question. Write the numbers of the sentences needed to answer the given question. Separate multiple sentence numbers with a comma (\", \"). E.g. \"1, 2\" would be the correct response if Sent 1 and Sent 2 are needed to answer the given question (do not include sentences that contain no information that is necessary to answer the question). Sort the sentence numbers in an increasing order (i.e., '1, 2', instead of '2, 1'). Your answer should not contain anything than the sentence numbers separated by a comma (e.g. '1, 2, 3, 4'). The given question requires more than one sentence to answer. So, your answer must contain at least one comma (\", \").\n\nParagraph- Sent 1: Historically, LSEO letter-writing campaigns generated from $11,000 to $25,000 annually, recalls Dallas Ferguson, a Tulsa attorney and board president of the new LASO.\nSent 2: That amount hardly offset enormous cuts, beginning in 1996, by Congress to Legal Services Corp., the chief funding source for state legal-aid agencies.\nSent 3: Threatened with extinction, LSEO clawed its way back with the help of state funding, grant money and the Tulsa Area United Way.\nSent 4: Meanwhile, the clients keep coming.\nSent 5: At least three-quarters are women and children living in poverty.\nSent 6: The agency helps more than 12,000 children a year.\nSent 7: A third of LSEO's clients are the working poor who receive no government benefits.\nSent 8: Many are senior citizens.\nSent 9: Riggs regrets that retired Tulsa attorney John Athens, a champion of legal aid, did not live to see how much the money has meant.\nSent 10: Athens died last year.\nSent 11: In his honor, The Oxley Foundation donated $200,000 to expand a client hot line.\nSent 12: That service, which will be expanded statewide, enables needy people to consult an attorney about civil legal problems, including rent and contract disputes, domestic abuse, consumer issues and custody matters.\nSent 13: Attorneys handle no criminal cases.\nSent 14: R.H. Harbaugh, foundation trustee and a colleague of Athens at the Conner & Winters law firm, said his mentor had \"a special interest in people who could not afford legal services.\nSent 15: He was aware of the hot line and supported its expansion.\"Sent 16: Said Riggs: \"We use lofty phrases such as 'with justice for all,' when we talk about our legal system.\nSent 17: That phrase is etched on our U.S. Supreme Court building.\nSent 18: Those are just empty words if people don't have access to that system.\". \nQuestion: What agency helps more than 12,000 children a year?."
},
{
"from": "gpt",
"value": "3, 6."
}
] |
[
{
"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 review of a movie and a boolean question whether this review has positive sentiment or negative sentiment. Your task is to generate answer \"yes\" when the tweet has that particular sentiment, otherwise generate answer \"no\".\n\nReview: I thought this was a very good movie. It would have been nice to have seen a little more into the movie about the 2 sisters knowing about each liking the same boy before he was killed off. I'm sure if the movie had been done this way there would have been a very different ending, that's why this made this move such a good movie. It shows that no matter what happens in your life with your siblings that you can always get thru it and that if it's 2 sisters dealing with a boy, (the same boy) that working thru the pain and hurt makes things to seem better and easier to work out between the 2 of them. It's nice to see love stories that have a terrible thing to happen in someone's life that you can still get thru it become even closer after its over. I really enjoyed watching this movie, and I still do now when it comes on. I seem to find myself watching it every time it comes on. It would have been nice if there would have been a part 2 for this movie, maybe having the older sister to come up and have his baby, this would really have made a great finish to the story since he died, this way it would keep him alive even though he's dead. Question: is it a positive review?\nOutput:"
},
{
"from": "gpt",
"value": "yes"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nGiven a sequence of actions to navigate an agent in its environment, provide the correct command in a limited form of natural language that matches the sequence of actions when executed. Commands are lowercase and encapsulate the logic of the sequence of actions. Actions are individual steps that serve as the building blocks for a command. 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'. For commands, 'left' and 'right' are used to denote the direction of an action. 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. Actions and commands do not have quotations in the input and output.\n\nI_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_RUN\nOutput:"
},
{
"from": "gpt",
"value": "look around right twice and run right"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to classify the genre of the sentences from the 10 options displayed. Indicate your answer by entering the number of the choice as 1-10.\n\nSentence 1: Next to the MGM Grand you will find M and M World. Sentence 2: The candy has many fans who love its attractions. Choices: 1. FACE-TO-FACE, 2. GOVERNMENT, 3. LETTERS, 4. 9/11, 5. SLATE, 6. TELEPHONE, 7. TRAVEL, 8. VERBATIM, 9. OUP, 10. FICTION.\nSolution: 1\nWhy? The places are specifically pointed out and referred to as attractions.\n\nNew input: Sentence 1: yeah it it obviously is not a DC you know Sentence 2: It resembles DC a lot. Choices: 1. FACE-TO-FACE, 2. GOVERNMENT, 3. LETTERS, 4. 9/11, 5. SLATE, 6. TELEPHONE, 7. TRAVEL, 8. VERBATIM, 9. OUP, 10. FICTION.\nSolution:"
},
{
"from": "gpt",
"value": "5"
}
] |
[
{
"from": "human",
"value": "In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to 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\nOne example is below.\nQ: eq { hop { nth_argmax { all_rows ; attendance ; 3 } ; competition } ; danish superliga 2005 - 06 } = true\nA: select the row whose attendance record of all rows is 3rd maximum. the competition record of this row is danish superliga 2005-06.\nRationale: Here, the generated sentence interprets given logical form correctly that 3rd maximum should be selected from given table rows.\nQ: eq { hop { nth_argmax { all_rows ; original air date ( uk ) ; 1 } ; episode title } ; loyalties ii } = true\nA:"
},
{
"from": "gpt",
"value": "select the row whose original air date uk record of all rows is 1st maximum . the episode title record of this row is loyalties ii ."
}
] |
[
{
"from": "human",
"value": "In this task you're given a question and you have to paraphrase the question to create the output question while retaining the meaning of the original question.\n\nLet me give you an example: What can one do after MBBS?\nThe answer to this example can be: What do i do after my MBBS ?\nHere is why: In this example both the question ask the same thing about what to do after MBBS hence second question is the correct output \n\nOK. solve this:\nWhat is the male equivalent of \"maiden name?\"\nAnswer:"
},
{
"from": "gpt",
"value": "My daughter wants to use my maiden name at new school. Can she without legally changing it, which she may do when she turns 18 (10/2016)?"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you're given five sentences, numbered 1 through 5. Your job is to generate a title for the story that makes complete sense. The title must be short, with less than three words, use simple language, and include the main topic of the story.\nExample: Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: All of his clothes were either too formal or too casual. Sentence 3: He decided to buy a pair of khakis. Sentence 4: The pair he bought fit him perfectly. Sentence 5: Marcus was happy to have the right clothes for the event.\nOutput: Marcus Buys Khakis\nMarcus's reasons for buying khakis is established, followed by his purchase of them and reaction.\n\nNew input case for you: Sentence 1: Dan left her daughter in the room while he used the bathroom. Sentence 2: Dan realized she was a bit too quiet, and ran to check on her. Sentence 3: Dan was shocked to see his computer mouse in a glass of water. Sentence 4: Dan knew that his mouse had been damaged. Sentence 5: Dan was not pleased that he would have to purchase a new mouse.\nOutput:"
},
{
"from": "gpt",
"value": "Mouse in Water"
}
] |
[
{
"from": "human",
"value": "Instructions: This task is about creating an unanswerable question based on a given passage. Construct a question that looks relevant to the given context but is unanswerable. Following are a few suggestions about how to create unanswerable questions:\n(i) create questions which require satisfying a constraint that is not mentioned in the passage\n(ii) create questions which require information beyond what is provided in the passage in order to answer\n(iii) replace an existing entity, number, date mentioned in the passage with other entity, number, date and use it in the question\n(iv) create a question which is answerable from the passage and then replace one or two words by their antonyms or insert/remove negation words to make it unanswerable.\nInput: Passage: Gibraltar opened its first comprehensive school in 1972. Between the ages of 12 and 16 two comprehensive schools cater for girls and boys separately. Students may also continue into the sixth form to complete their A-levels.\nOutput:"
},
{
"from": "gpt",
"value": "When was the last comprehensive school opened in Gibraltar?"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you're given a context passage. Your job is to generate relevant questions that can be answered by directly referring to the passage.\n\nLee gave his mom a special gift for their birthday that year.\n"
},
{
"from": "gpt",
"value": "What will happen to Lee?"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nIn this task, you are given a sentence and a profession that is mentioned in the sentence. The gender of the person with the given profession can be identified using the gendered pronouns that refer to them in the text. You are expected to identify the gender. Select from female and male.\nPart 2. Example\nSentence: The cashier told the sheriff the money was lost but failed to convince her.\n Profession: sheriff\nAnswer: Female\nExplanation: The sheriff is a female because the pronoun \"her\" is linked to the sheriff.\nPart 3. Exercise\nSentence: The teacher stared at the construction worker and asked her a question.\n Profession: construction worker\nAnswer:"
},
{
"from": "gpt",
"value": "Female"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. You will be asked how to do a certain task. You should describe a physical process that does not lead to the asked outcome, yet it is closely related to it (i.e., it should use the words that are provided in the input). The physical process can be moving something, arranging something in a certain way, mixing things, shaking them, etc. To make sure that the generated process does not lead to the asked outcome, you can introduce objects or events unrelated to the context of the question e.g. 'cleaning the keyboard by making an elephant sit on them'; or you can create contradictory statements e.g. 'drying wet keyboards with running water'. In your responses, avoid typos and misspellings.\n\nHow do I make an omelet\n"
},
{
"from": "gpt",
"value": "Place 2 lemons in a cup, add some salt and veggies, beat with a fork and cook it"
}
] |
[
{
"from": "human",
"value": "In this task, you are given an input list A. You need to find all the elements of the list that are numbers in the same order as they appear in the list A.\n\n[EX Q]: ['W', '8593', 'g', 'M', '9307', 'd', 'W', '9717', '8595', '8345', 'n', '5783', '1377', 'O', '8339', 'e', '3885', '4059', '8821', '1501', '5881', 'A', '1609', '5321', 'n', '5673', 'P', 'y']\n[EX A]: 8593, 9307, 9717, 8595, 8345, 5783, 1377, 8339, 3885, 4059, 8821, 1501, 5881, 1609, 5321, 5673\n\n[EX Q]: ['9895', '2801', 'n', '9839', 'k', 'm', '9565', 'g', 'w', 'F', 'h', 'w']\n[EX A]: 9895, 2801, 9839, 9565\n\n[EX Q]: ['r', '9945', 'f', '5081', 'n', '229', 'f', '981', '139', 'k', 'C', 'V', 'i', 'G', '6501', '8951', 'g', 'B', 'i', 'x', '9815', 'Q', '2897', '1909', '553', '4383', '1229', '6465', 'T']\n[EX A]:"
},
{
"from": "gpt",
"value": "9945, 5081, 229, 981, 139, 6501, 8951, 9815, 2897, 1909, 553, 4383, 1229, 6465\n\n"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given a sentence and a profession. The sentence mentions two professions: one's gender is identifiable using the gendered pronouns in the text and the other's gender is unidentifiable. You are expected to return whether the given profession's gender is identifiable or unidentifiable.\n\nSentence: The counselor helped the laborer because he is a very kind person.\n Profession: counselor\nOutput:"
},
{
"from": "gpt",
"value": "Identifiable"
}
] |
[
{
"from": "human",
"value": "Definition: 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.\nInput: Sentence: Emory University's Board of Trustees announced Friday that it was prepared to accept students {{ of }} any race as soon as the state's tax laws made such a step possible . \nWord: of\nOutput:"
},
{
"from": "gpt",
"value": "ADP"
}
] |
[
{
"from": "human",
"value": "Given a disfluent sentence, modify the sentence to it to its equivalent fluent form, preserving the meaning of the sentence.\n\nThe referendum to establish a devolved Edinburgh or no make that Scottish Assembly succeeded in what year?\nThe referendum to establish a devolved Scottish Assembly succeeded in what year?\n\nWhat types type of treatment no health outcomes do pharmacists never have with their patients?\nWhat types of health outcomes do pharmacists never have with their patients?\n\nCells of the site of an infection in a animal no wait plant undergo what process to prevent spread of the disease?\n"
},
{
"from": "gpt",
"value": "Cells of the site of an infection in a plant undergo what process to prevent spread of the disease?\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a question containing a blank (_) and two options. You should pick the best option to answer the question. Please answer with \"A\" or \"B\".\n\nThe problem of my sister this year is worse than my situation was last year because the _ is fixable. (A) problem (B) situation\nB\n\nMary converted to Christianity and asked Erin about how to pray as a Christian because _ was previously an Atheist. (A) Mary (B) Erin\nA\n\nSandra tried out a new conditioner for her hair that makes it curly, but was upset with the results because the _ was too straight. (A) conditioner (B) hair\n"
},
{
"from": "gpt",
"value": "B\n\n"
}
] |
[
{
"from": "human",
"value": "Q: This task involves annotating the answer type to a given question that involve some kind of complex reasoning (including numerical reasoning). Note that the questions require looking at more than one part of the passage to answer. There are 3 possible answer types (i) spans, (ii) numbers and (iii) dates. If the answer can be found in the passage, label it as \"span\". If the answer is a number, label as \"number\". Similarly, label \"date\" if you think the answer to the given question is a date.\nPassage: After Mwai Kibaki took over as president in 2003,the GDP growth quickly picked up to 2.3% in 2004 reaching an all time high of 7% in 2007.GDP growth slumped to 1% in 2008 due to post election violence,then picked up to 2.9% in 2009 before averaging 5% between 2009 to 2013 when the Grand Coalition government came to an end.In the last year of Kibaki and the grand coalition government in 2013,Kenyas total GDP was US$55.1 Billion with a population of 44.83 Million and a per capita of US$1,229.\nQuestion: Which year did the GDP do better, 2008 or 2009?\nA:"
},
{
"from": "gpt",
"value": "date"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to classify the genre of the sentences from the 10 options displayed. Indicate your answer by entering the number of the choice as 1-10.\n\nEx Input:\nSentence 1: sure yeah i have heard of that Sentence 2: I have heard good things about that. Choices: 1. FACE-TO-FACE, 2. GOVERNMENT, 3. LETTERS, 4. 9/11, 5. SLATE, 6. TELEPHONE, 7. TRAVEL, 8. VERBATIM, 9. OUP, 10. FICTION.\n\nEx Output:\n5\n\n\nEx Input:\nSentence 1: Similarly, he infuriates senators with grandstanding attacks on pork, being a master at publicizing and eliminating other senators' sweetheart projects. Sentence 2: He made senators happy with his grandstanding attacks on pork. Choices: 1. FACE-TO-FACE, 2. GOVERNMENT, 3. LETTERS, 4. 9/11, 5. SLATE, 6. TELEPHONE, 7. TRAVEL, 8. VERBATIM, 9. OUP, 10. FICTION.\n\nEx Output:\n4\n\n\nEx Input:\nSentence 1: We looked in. Sentence 2: We closed our eyes. Choices: 1. FACE-TO-FACE, 2. GOVERNMENT, 3. LETTERS, 4. 9/11, 5. SLATE, 6. TELEPHONE, 7. TRAVEL, 8. VERBATIM, 9. OUP, 10. FICTION.\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "4\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. There are several possible answers, you'll need to choose the proper one. Carefully read the given text, pay special attention to the marked number, think about what (unwritten) information the marked number holds inside, choose the most adequate word(s) from the optional answers. If none of them seems right to you, there's also an option for other. If your answer is \"REFERENCE\", also write the reference entity, otherwise write the implicit option name. Options to choose from are:\nREFERENCE: Some object which is being mentioned in the text before or after the target number. The reference answer has a higher priority than any other. If both Reference and another answer are possible, prioritize the Reference.\nYEAR: Describing a calendric year\nAGE: Describing someone's age\nCURRENCY: Reference to some monetary value e.g dollar, euro etc.\nPEOPLE: Describing a single/plural persons\nTIME: Describing a time of the day. Usually you can add the word o'clock after those numbers.\nOTHER: Some other option, which isn't listed here.\nQ: Hester Farrell: How much time do you have ?\nAmos Lasher: Time enough to hit _ one _ more outta the park .\nA: "
},
{
"from": "gpt",
"value": "OTHER"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given a text which is the body of a document. You are given a question and options. Pick the correct number. Don't generate anything else apart from the numbers provided in options.\nExample: Text: The Mansfield Building Society is a UK building society which has its headquarters in Mansfield Nottinghamshire. It is a member of the Building Societies Association. \nQuestion: The document can be classified to which topic? Options: 1)Animal, 2)Plant, 3)Building, 4)Company, 5)WrittenWork\nOutput: 3\nMansfield Building Society is a UK building society. Hence, option 3 is the correct answer\n\nNew input case for you: Context: I.P. Paul is an Indian National Congress politician from Thrissur city India. He was the fourth mayor of Thrissur Municipal Corporation.\nQuestion: The document can be classified to which topic? \nOptions: 1)Artist, 2)Building, 3)OfficeHolder, 4)Plant\nOutput:"
},
{
"from": "gpt",
"value": "3"
}
] |
[
{
"from": "human",
"value": "Definition: Predict the next word given an incomplete English Sentence.\nInput: madame danglars therefore went to bed without a shadow of suspicion and began to muse\nOutput:"
},
{
"from": "gpt",
"value": "over"
}
] |
[
{
"from": "human",
"value": "Definition: In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the count of all the numerical elements in the given list. Return 0 if no numerical element in the list.\nInput: ['g', 'j', 'b', '7875', 't', 't', '235', '3869', 'Z']\nOutput:"
},
{
"from": "gpt",
"value": "3"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. Given a part of privacy policy text, identify the purpose for which the user information is collected/used. The purpose should be given inside the policy text, answer as 'Not Specified' otherwise\n\nAn unnamed third party does receive unspecified information about you for marketing purposes. The data is aggregated or anonymized.\n"
},
{
"from": "gpt",
"value": "Marketing"
}
] |
[
{
"from": "human",
"value": "Definition: You are given a paragraph, a question and some answer options (associated with \"A\", \"B\", \"C\", \"D\", etc.) You need to list all the correct answer options with their associated letters (e.g. \"A\" can be a valid answer). Note that sometimes, more than one option can answer the question correctly and completely. In those cases, please generate all such options separated by a comma (e.g. \"A, B\" is a valid answer). Do not generate anything else apart from one or more of the following characters: 'A', 'B, 'C', 'D', etc.\nInput: Paragraph- Sent 1: The grant also will help victims go through court proceedings after losing a job or being evicted because of an abuser's actions, Xanthopoulos said.\nSent 2: \"It's going to help the victims, but it's also going to help their children,\" he said.\nSent 3: More than 270 domestic violence assaults in Madison County were reported last year, according to Tennessee Bureau of Investigation statistics.\nSent 4: In Jackson, more than 730 domestic violence assaults were reported last year, according to records.\nSent 5: \"Domestic violence is certainly on the increase and we need to do something to curve that.\nSent 6: I see this as helping that,\" Madison County Sheriff David Woolfork said of the grant.\nSent 7: Domestic violence accounted for five of 12 murders in 2001 in Jackson, police have said.\nSent 8: And the increase in calls prompted Jackson Police Chief Rick Staples in March to form a focus group to determine if police officers need to make changes in their response to domestic calls. \nQuestion: Where more domestic violence assaults were reported last year, in Madison County or in Jackson? (A) In Madison County (B) In Jackson (C) More domestic violence assaults occurred in Jackson last year.\nOutput:"
},
{
"from": "gpt",
"value": "B, C."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: 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\".\nSee one example below:\nProblem: She shone her light around the space, following the glow of the flashlight's ray along the walls.\nSolution: Past\nExplanation: The verb \"shone\" is in past tense.\n\nProblem: He tastes of mint.\nSolution:"
},
{
"from": "gpt",
"value": "Present"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Classify the relation of question with context to one of these categories: 1) award received, 2) based on, collection, 3) conflict, 4) constellation, 5) convicted of, 6) date of death, 7) director, 8) drafted by, 9) educated at, 10) medical condition, 11) military branch, 12) narrative location, 13) occupation, 14) original network, 15) parent company, 16) point in time, 17) production company, 18) residence, 19) series, 20) service entry, 21) sex or gender, 22) spouse, 23) standards body question.\nProblem:Context : Active in the Boy Scouts of Canada for many years, in 1969 William Tetley was awarded the Boy Scouts of Canada Medal. \nQuestion : What is the name university that educated William Tetley?\nSolution:"
},
{
"from": "gpt",
"value": "educated at"
}
] |
[
{
"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 list. This list contains many lists of integers. The list is several items written within a []. Your task is to find the maximum number among the members of each inner list. The output should be a list comprised of the maximums with the same order as the internal lists.\n\n[[-192, -183, -114], [20, -68, 26], [-35, 90], [-26, -56, -132, 15, 17, -57, -171], [-62, 100, 82, -112, -35], [-119, -181, -140, 12], [-91, 22, -57, -50], [-125, -149, -44, -95, -39], [-196, -43, 34, -185]]\nOutput:"
},
{
"from": "gpt",
"value": "[-114, 26, 90, 17, 100, 12, 22, -39, 34]"
}
] |
[
{
"from": "human",
"value": "Q: In this task, you need to output 'Yes' if the given number is a prime number otherwise output 'No'. A 'prime number' is a a whole number above 1 that can not be made by multiplying other whole numbers.\n49739\nA:"
},
{
"from": "gpt",
"value": "Yes"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: You are given a paragraph (Passage), a question (Question) and two answer options (Option1 and Option2). Your task is to choose the correct answer to the question based on the passage. Answer of the question cannot be found directly from the passage, it is indirectly indicated in the passage. Do not answer with words other than the two options, and do not answer with option titles(e.g. \"option1\" or \"1\" are not acceptable answers.)\nSee one example below:\nProblem: Passage: Omelettes make a great breakfast , and I enjoy making them because they are very easy to cook . First , I get the eggs out and begin cracking them on the side of the bowl and dumping them into the bowl . I normally use two eggs whites and one whole egg to cut the calories . I add some salt and pepper to the mix for flavor . I pour the mixture into the hot frying pan . I make sure that I add some vegetable oil to the pan before I add the eggs though because I do n't want them to stick . As this occurs , I add some cheese or vegetable to the center of the egg mixture . Really , almost any type of cheese or vegetable makes a good omelette . I then flip one side of the omelette over on to itself to seal in the contents in the middle . It is then ready to serve ! Question: Where is the omelette being browned? Option1: In the pan Option2: On the street\nSolution: In the pan\nExplanation: As mentioned in the passage that I pour the mixture into the hot frying pan; it is clear that omelette is being browned in pan only. Also, there is nothing related to street mention in the passage.\n\nProblem: Passage: I was driving to work when I noticed that my gas tank was low . I like keeping a full tank , so at the next gas station I pulled in and pulled up to the gas hoses . I shut my engine off and got out of my car , making sure I had my wallet in my back pocket . There 's a number pad and a slot on the pump for your credit card or debit to go in . I made sure it was in , then pressed the buttons I needed to to get ten gallons of gas . I had to put my pin number for the card in , and my zip code . Once I saw that , I pumped the ten gallons I had paid for with my debit card . It was expensive , but I always feel more secure when I have a full gas tank , so that 's a good thing . Question: What does the screen say is ok to pump? Option1: Gas Option2: 1 gallon\nSolution:"
},
{
"from": "gpt",
"value": "Gas"
}
] |
[
{
"from": "human",
"value": "Definition: In this task, you're given a pair of sentences, sentence 1 and sentence 2. Sentence 2 contradicts sentence 1. Your job is to alter sentence 2 so that the pair neither agree nor contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\nInput: Sentence 1: 5 students are listening to a lesson by a teacher Sentence 2: The student yells at the professor in a crowded classroom.\nOutput:"
},
{
"from": "gpt",
"value": "College students are listening to their astronomy professor."
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: In this task, you will be presented with a passage, and you need to write an **implausible** answer to to fill in the place of \"_\". Your answer should be incorrect, but should not be out of context. Try using words that are related to the context of the passage, but are not the correct answer. Even though there exist multiple wrong answers, we only need a single wrong answer.\nPROBLEM: (CNN) -- Less than a week after the United Nations declared an end to the famine in Somalia, a new report from the world body says millions of people in South Sudan will now face hunger if urgent action is not taken. The report released Wednesday by the Food and Agricultural Organization of the United Nations (FAO) and the World Food Program (WFP) says that fighting in the northern border region and ethnic clashes in many other parts of South Sudan has created a level of food insecurity that could nearly double in the next year. \"Poor harvests, increased demand, rapidly rising prices, displacement and a large number of returnees have all contributed to the situation,\" the report says.Millions could face food shortages and hunger in South Sudan, the U.N. saysFood supply routes into South Sudan have been blocked, the report saysSouth Sudan became independent from Sudan last year \n Question:Under a normal functioning market, food insecurity and increased demand might have been addressed, the report says, but border closures that link the newly independent South Sudan to Sudan have disrupted the usual supply of food commodities to _'s markets.\n\nSOLUTION: CNN\n\nPROBLEM: (CNN) The case of college football player Michael Keck has added more fuel to the fire about whether young children should play football. Despite the fact that Keck, 25, never played professional football, he was diagnosed with chronic traumatic encephalopathy, the Alzheimer's-like disease that also claimed the likes of former Chicago Bears safety Dave Duerson and former San Diego Chargers linebacker Junior Seau, and with equal severity. \"I was surprised how extensive it was,\" said Dr. Ann McKee, professor of neurology and pathology at Boston University. She and her team have evaluated 170 brains to understand the pathology of CTE. The telltale sign of the disease is tangles of the protein tau, which takes over parts of the brain. They result from repeated hits to the head.Chronic traumatic encephalopathy results from repetitive hits to the headThe disease has symptoms that are similar to Alzheimer's44 of 55 college football players were found to have CTE \n Question:Keck believed he suffered from _, but it cannot be diagnosed in living people.\n\nSOLUTION: Michael Keck\n\nPROBLEM: A newly released analysis of Charleston church shooter Dylann Storm Roof's hate-filled manifesto has revealed that the 21-year-old murder suspect may have been active on an online white supremacist forum. The group Southern Poverty Law Center, which tracks hate groups around the country, compared the text of Roof's manifesto, which was discovered on his website The Last Rhodesian Saturday, to comments and posts made by user AryanBlood1488 on the site The Daily Stormer and found striking similarities. The SPLC described The Daily Stormer in its report as a neo-Nazi online community run by its publisher, Andrew Anglin, that generates original content and also re-posts articles from other sites promoting the white supremacist agenda.Roof's manifesto was discovered Saturday on his site The Last RhodesianThe 21-year-old accused mass murderer detailed his attitudes towards various minorities, including blacks, Hispanics and JewsSouthern Poverty Law Center ran Roof's writings through a plagiarism detection softwareSPLC's analysis found similarities between Roof's writings and posts made by online user AryanBlood1488 on white supremacist forum \n Question:Andrew Anglin, the publisher of the Daily Stormer, responded to SPLC's report in a lengthy post Tuesday saying that a person using the handle _ penned about 20 comments on the forum over the past few months.\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "Charleston\n\n"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nIn this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis, that is, it makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis, that is, it makes you much more likely to believe the hypothesis is true. Your task is to answer with 'strengthener' or 'weakener' if the update strengthens or weakens the hypothesis, respectively.\nPart 2. Example\nPremise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is serious and is surrounded by workers.\nAnswer: strengthener\nExplanation: If the old man is serious and surrounded by workers, it is more likely that he is working.\nPart 3. Exercise\nPremise: Two young men in a purple and white shirt running on grass.\nHypothesis: Two young men are playing tag.\nUpdate: The men have frisbees.\nAnswer:"
},
{
"from": "gpt",
"value": "weakener"
}
] |
[
{
"from": "human",
"value": "Instructions: Given a passage, construct a question on the basis of the information present in the passage. Construct the question in such a way that (i) it is unambiguous, (ii) it is answerable from the passage, (iii) its answer is unique (iv) it answer uses text phrases from the passage. Avoid creating questions that (i) can't be answered correctly without actually understanding the passage and (ii) uses the same words or phrases given in the passage.\nInput: Although estrogen replacement therapy has been associated with reduction of cardiovascular events in postmenopausal women, the mechanism for this benefit remains unclear. Because nitric oxide (NO) is considered an important endothelium-derived relaxing factor and may function to protect blood vessels against atherosclerotic development, we investigated the acute effects of physiological levels of estrogen on NO release from human internal thoracic artery endothelia and human arterial endothelia in culture.', 'We tested the hypothesis that estrogen acutely stimulates constitutive NO synthase activity in human endothelial cells by acting on a cell-surface receptor. NO release was measured in real time with an amperometric probe. 17beta-Estradiol exposure to internal thoracic artery endothelia and human arterial endothelia in culture stimulated NO release within seconds in a concentration-dependent manner. 17beta-Estradiol conjugated to bovine serum albumin also stimulated NO release, suggesting action through a cell-surface receptor. Tamoxifen, an estrogen receptor inhibitor, antagonized this action. We further showed with the use of dual emission microfluorometry that 17beta-estradiol-stimulated release of endothelial NO was dependent on the initial stimulation of intracellular calcium transients.\nOutput:"
},
{
"from": "gpt",
"value": "Do cell-surface estrogen receptors mediate calcium-dependent nitric oxide release in human endothelia?"
}
] |
[
{
"from": "human",
"value": "Given a sequence of actions to navigate an agent in its environment, provide the correct command in a limited form of natural language that matches the sequence of actions when executed. Commands are lowercase and encapsulate the logic of the sequence of actions. Actions are individual steps that serve as the building blocks for a command. 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'. For commands, 'left' and 'right' are used to denote the direction of an action. 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. Actions and commands do not have quotations in the input and output.\n\nExample Input: I_TURN_RIGHT I_TURN_RIGHT I_WALK I_TURN_RIGHT I_TURN_RIGHT I_WALK I_TURN_RIGHT I_TURN_RIGHT I_WALK I_WALK I_WALK I_WALK\nExample Output: walk opposite right thrice and walk thrice\n\nExample Input: I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_RIGHT I_JUMP\nExample Output: look left twice and jump right\n\nExample Input: I_TURN_RIGHT I_LOOK I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP\nExample Output:"
},
{
"from": "gpt",
"value": "jump around left after look right\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given an abstract of article. Your task is to generate title for this article. Preferred titles are under thirty words.\n\nLet me give you an example: Alterations of the architecture of cerebral white matter in the developing human brain can affect cortical development and result in functional disabilities. A line scan diffusion-weighted magnetic resonance imaging (MRI) sequence with diffusion tensor analysis was applied to measure the apparent diffusion coefficient, to calculate relative anisotropy, and to delineate three-dimensional fiber architecture in cerebral white matter in preterm (n = 17) and full-term infants (n = 7). To assess effects of prematurity on cerebral white matter development, early gestation preterm infants (n = 10) were studied a second time at term. In the central white matter the mean apparent diffusion coefficient at 28 wk was high, 1.8 microm2/ms, and decreased toward term to 1.2 microm2/ms. In the posterior limb of the internal capsule, the mean apparent diffusion coefficients at both times were similar (1.2 versus 1.1 microm2/ms). Relative anisotropy was higher the closer birth was to term with greater absolute values in the internal capsule than in the central white matter. Preterm infants at term showed higher mean diffusion coefficients in the central white matter (1.4 +/- 0.24 versus 1.15 +/- 0.09 microm2/ms, p = 0.016) and lower relative anisotropy in both areas compared with full-term infants (white matter, 10.9 +/- 0.6 versus 22.9 +/- 3.0%, p = 0.001; internal capsule, 24.0 +/- 4.44 versus 33.1 +/- 0.6% p = 0.006). Nonmyelinated fibers in the corpus callosum were visible by diffusion tensor MRI as early as 28 wk; full-term and preterm infants at term showed marked differences in white matter fiber organization. The data indicate that quantitative assessment of water diffusion by diffusion tensor MRI provides insight into microstructural development in cerebral white matter in living infants.\nThe answer to this example can be: Microstructural development of human newborn cerebral white matter assessed in vivo by diffusion tensor magnetic resonance imaging.\nHere is why: This title is appropriate for the given abstract because the focus of this abstract is cerebral white matter assesment.\n\nOK. solve this:\nBoth signal transducer and activator of transcription 3 (STAT3) and SALL4 are important in maintaining the pluripotent and self-renewal state of embryonic stem cells. We hypothesized that STAT3, a latent transcriptional factor, may regulate the gene expression of SALL4. In support of this hypothesis, DNA sequence analysis of the SALL4 gene promoter revealed four putative STAT3-binding sites. Using a SALL4-luciferase reporter gene assay, we found that modulation of the STAT3 activity significantly up-regulated the luciferase activity. By chromatin immunoprecipitation, the segment of the SALL4 promoter showing the highest affinity to STAT3 was localized to -366 to -163, in which there was only one putative STAT3 binding site starting at -199. Site-directed mutagenesis of all four putative STAT3-binding sites in the SALL4 promoter significantly reduced its responsiveness to STAT3, although the most dramatic effect was seen at the binding site starting at -199. We further tested the functional relationship between STAT3 and SALL4 using MDA-MB-231, a breast cell line carrying constitutive SALL4 expression and STAT3 activity. Down-regulation of the STAT3 activity using a dominant-negative construct resulted in a significant decrease in the expression of SALL4. To conclude, our data suggest that STAT3 and SALL4 probably cooperate in both physiological and pathological states.\nAnswer:"
},
{
"from": "gpt",
"value": "Signal transducer and activator of transcription 3 is a transcriptional factor regulating the gene expression of SALL4."
}
] |
[
{
"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\nSentence: So was the attack upon Charles E. Bohlen {{ when }} Eisenhower appointed him Ambassador to Moscow . \nWord: when\nADV\n\nSentence: He is Aldo Rostagno , son of the Guglielmo Rostagnos of Florence {{ whom }} the Burkes met last year in Europe . \nWord: whom\nPRON\n\nSentence: He skimmed over the millions that went to Meeker Park , Medfield Hospital , the {{ civic }} center , the Public Health Nursing Association , the library , and so on , pausing when he came to the scholarship fund . \nWord: civic\n"
},
{
"from": "gpt",
"value": "ADJ\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Write a correct answer for the question. You should reason about prototypical situations and provide the correct answer. Avoid answers that provide incomplete justification for the question.\nSee one example below:\nProblem: at the beach, name something that might protect you from sun.\nSolution: umbrella\nExplanation: Umbrella can serve as a shield to block the sun\n\nProblem: name something you might do to win over your in-laws.\nSolution:"
},
{
"from": "gpt",
"value": "cook nice meals"
}
] |
[
{
"from": "human",
"value": "Teacher: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.\nTeacher: Now, understand the problem? Solve this instance: [[44, 15, 23], [11, 34, 23], [-17, 21, 27], [26, 36, -31, 35], [32, 37], [-32, 25, -48, -12, 4], [-14, -36, -24, -25]]\nStudent:"
},
{
"from": "gpt",
"value": "[44, 34, 0, 936, 32, -73728, -12096]"
}
] |
[
{
"from": "human",
"value": "In this task, you're given the title of a five-sentence story, the first four sentences, and two options for the fifth sentence as a and b. Your job is to pick the sentence option that does not connect with the rest of the story, indicating your choice as 'a' or 'b'. If both sentences are plausible, pick the one that makes less sense.\n\nExample input: Title: Marcus Buys Khakis. Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: All of his clothes were either too formal or too casual. Sentence 3: He decided to buy a pair of khakis. Sentence 4: The pair he bought fit him perfectly. Choices: a. Marcus was happy to have the right clothes for the event. b. He left in a huff for having his ideas mocked.\nExample output: b\nExample explanation: Marcus is buying clothes for a business event and not presenting an idea.\nQ: Title: Lessons. Sentence 1: I took voice lessons after school on Friday. Sentence 2: I walked to the tutor's house. Sentence 3: Her miniature poodle greeted me at the door. Sentence 4: I would sing with her for over half an hour. Choices: a. She showed me a lot of new tricks. b. It took all weekend but her house looked much better.\nA:"
},
{
"from": "gpt",
"value": "b"
}
] |
[
{
"from": "human",
"value": "In this task you will be given a text passage from a trivia quiz. You should choose the category this question belongs to from these categories: History, Science, Social Science, Fine Arts, Literature. You can only choose one category, so if in doubt, please choose the closest match.\n\nExample input: In one work this author details the life of a tomb-maker who makes extra money by playing the organ at an insane asylum, while another of his novels sees Swartz give a refugee proper documentation only after he tells him his life story in the title Portuguese city. In addition to The Black Obelisk and The Night in Lisbon, he also wrote about Robert and Otto selling their auto workshop and visiting Patrice in a Swiss tuberculosis sanatorium in his novel The Three Comrades, while the turbulent life of the German surgeon Ravic is told in The Arch of Triumph. Another of his novels, The Road Back, is thought to be a sequel to his most famous book, in which the patriotic teacher Kantorek convinces Paul Bumer and his friends to join the Germany Army during World War I. For 10 points, name this German author who wrote All Quiet on the Western Front.\nExample output: Literature\nExample explanation: The text is talking about an author and their works, so it belongs to theliterature category.\nQ: During his first meeting with Richard Wagner he refused to sit down out of respect for his musical hero. His first major musical work, Requiem in D minor, was written while teaching at St. Florian in Austria. In 1856, he moved to Linz, and while there he composed a version of Ave Maria and his Mass in D Major. He dedicated his Third Symphony to Wagner but its 1877 premier was a failure - only 25 people remained in the auditorium by the end. FTP, identify this composer of the more favorably received Fourth or \"Romantic\" Symphony, who is sometimes better known for his Zeroth Symphony.\nA:"
},
{
"from": "gpt",
"value": "Fine Arts"
}
] |
[
{
"from": "human",
"value": "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'.\n\nAnalisten zijn tevreden over Colruyt\nNone\n\nDe zin van zon\nNone\n\nIn een gesprek met De Morgen verklaarde zijn advocaat eerder dat Ruggiu al sinds de zomer van vorig jaar had meegewerkt met het parket van de openbare aanklager .\n"
},
{
"from": "gpt",
"value": "Ruggiu: B-PER\n\n"
}
] |
[
{
"from": "human",
"value": "You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. Your task is to label each of the continuous conversations done by one speaker with the emotion detected in that particular part. Your labels can be one among the following: 'No emotion', 'surprise', 'happiness', 'sadness', 'anger', 'disgust'.\nQ: Person1: Bill , how can you hear so happy today ? \n Person2: Aha . I've read of my roommate . I made a move today . \n Person1: Really ? What was the matter ? \n Person2: You knew Brain Locker ? \n Person1: Brain Locker ? No , I don't think so . What does he look like ? \n Person2: Well , he's thin and tall . He has brown hair , a holt nose , green eyes and wearing glasses . \n Person1: Mm . I've seen him a couple of times , I think . \nA: "
},
{
"from": "gpt",
"value": "No emotion,No emotion,surprise,No emotion,No emotion,No emotion,No emotion"
}
] |
[
{
"from": "human",
"value": "Given an trivia question precisely answer the question with a word/phrase/name. External resources such as Wikipedia could be used to obtain the facts.\n\nEx Input:\nWho created the character Jason Bourne?\n\nEx Output:\nrobert ludlum\n\n\nEx Input:\nWhich US rock band comprises brothers Caleb, Nathan and Jared Followill with their cousin Matthew?\n\nEx Output:\nkings of leon\n\n\nEx Input:\nActress Kate Hudson is the daughter of which other actress?\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "goldie hawn\n\n\n"
}
] |
[
{
"from": "human",
"value": "Given a story, answer the question about the story. The question is the last sentence in the input. These stories can be difficult due to their length and how each story has at least one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios.\n\n[Q]: Liam entered the master_bedroom. Owen entered the master_bedroom. The pumpkin is in the blue_suitcase. Liam moved the pumpkin to the red_crate. Ethan entered the crawlspace. Owen entered the crawlspace. The grapefruit is in the green_bottle. Ethan moved the grapefruit to the red_suitcase. Liam entered the dining_room. Ethan entered the dining_room. The banana is in the red_drawer. Liam moved the banana to the red_bottle. Owen entered the back_yard. Liam entered the back_yard. The potato is in the blue_cupboard. Owen moved the potato to the blue_container. Where was the potato at the beginning?\n[A]: blue_cupboard\n\n\n[Q]: Oliver entered the patio. Charlotte entered the patio. The beans is in the green_bucket. Oliver moved the beans to the green_envelope. Charlotte is in the patio. Oliver is in the patio. The beans is in the green_envelope. Charlotte moved the beans to the green_bucket. Oliver is in the patio. Lucas entered the patio. The pineapple is in the green_envelope. Oliver moved the pineapple to the green_bucket. Oliver entered the garage. Lucas entered the garage. The carrot is in the green_cupboard. Oliver moved the carrot to the green_suitcase. Where was the carrot at the beginning?\n[A]: green_cupboard\n\n\n[Q]: Olivia entered the basement. Liam entered the basement. The peach is in the red_box. Liam exited the basement. Olivia moved the peach to the red_crate. Olivia entered the study. Hannah entered the study. The green_pepper is in the green_cupboard. Hannah exited the study. Olivia moved the green_pepper to the blue_cupboard. Olivia entered the living_room. Jackson entered the living_room. The grapefruit is in the blue_suitcase. Jackson exited the living_room. Olivia moved the grapefruit to the blue_bathtub. Olivia entered the study. Jackson entered the study. The tomato is in the blue_cupboard. Jackson exited the study. Olivia moved the tomato to the green_cupboard. Where does Olivia think that Jackson searches for the tomato?\n[A]:"
},
{
"from": "gpt",
"value": "blue_cupboard\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choice based on your inference from the statement and your commonsense knowledge. The neutral choice is a sentence that neither agrees nor disagrees with the statement. Indicate your answer as '1', '2', or '3', corresponding to the choice number of the selected sentence. If sentence X agrees with sentence Y, one's correctness follows from the other one. If sentence X disagrees with sentence Y, they can not be correct at the same time.\n\nStatement: The egg cell was biochemically pre-programmed to commence development, and that, apparently, was enough to jerk the mammary-cell DNA out of its quiescent state. Choices: 1. The egg cell caused the mammary cell's DNA to wake up. 2. The egg cell sent a radio signal to wake up the mammary cell's DNA. 3. The mammary cell's DNA was never activated and it lay dormant.\n2\n\nStatement: And please accept cookies so you can enjoy Choices: 1. Accept cookies to enjoy the experience. 2. It's important that you accept cookies. 3. You will enjoy regardless of if you accept cookies.\n2\n\nStatement: Even if they bill themselves as voting sites rather than polling sites, Web sites such as Dick Morris' Vote.com tacitly imply that the results of their online polls are reliable and valid. Choices: 1. Dick Morris' Vote.com is a website that is billed as a voting site. 2. Dick Morris' Vote.com is not a website, and claims to be a voting site. 3. Dick Morris' Vote.com is a website is not a voting site.\n"
},
{
"from": "gpt",
"value": "3\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you need to count the number of nouns/verbs in the given sentence.\nExample: Sentence: 'A small toy kept on tray held by a man'. Count the number of nouns in this sentence.\nOutput: 3\nThe words 'toy', 'tray', and 'man' are nouns in this sentence. So, the answer is 3.\n\nNew input case for you: Sentence: 'The woman is walking around holding a umbrella'. Count the number of verbs in this sentence.\nOutput:"
},
{
"from": "gpt",
"value": "2"
}
] |
[
{
"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'.\nProblem:05:39:36 PM occured before 10:12:35 but after 2:35:09\nSolution:"
},
{
"from": "gpt",
"value": "False"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: You will be given a trivia clue, and the category it belongs to. You should answer with the best answer that belongs in the category and is described by the clue. For simplicity, answers should be in all lower cased letters.\nProblem:Category: \"RUSH\"IA \nClue: The Klondike one lasted for 3 short but enriching years\nSolution:"
},
{
"from": "gpt",
"value": "a gold rush"
}
] |
[
{
"from": "human",
"value": "Q: You will be given two pieces of text with the same meaning. One of them is simpler and easier to understand for non-native English speakers. Complex texts may contain more difficult words, have unnecessary phrases or contain long sentences. Your task is to choose the simpler piece of text. You are expected to output 'Text one' if the first sentence is simpler. Otherwise output 'Text two'.\nText one: It was an F0 tornado. It touched down close to Brunswick, Georgia. It snapped trees and caused moderate roof damage. The tornado had a 2 mile (3.2 km) path.\n Text two: It was an F0 tornado. It touched down close to Brunswick, Georgia. It snapped trees and caused moderate roof damage. The tornado had a 2 mile (3.2 km) path.\nA:"
},
{
"from": "gpt",
"value": "Text one"
}
] |
[
{
"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 impractical statement. You are also given three reasons (associated with \"A\", \"B\", \"C\") explaining why this statement doesn't make sense. You must choose the most corresponding reason explaining why this statement doesn't make sense.\n\nI don't believe in the journalists, they are writing fake codes\n(A) Journalists can lead the public opinion\n(B)Some Chinese journalists are just the slave of the party\n(C)Journalists' job is not writing codes\nOutput:"
},
{
"from": "gpt",
"value": "C"
}
] |
[
{
"from": "human",
"value": "In this task, you need to count the number of words in a sentence that start with the given letter. Answer with numbers and not words.\n\nEx Input:\nSentence: 'the man is wearing a suit and tie'. How many words start with the letter 't' in the sentence.\n\nEx Output:\n2\n\n\nEx Input:\nSentence: 'here is an asian standing by a yellow fire hydrant'. How many words start with the letter 'h' in the sentence.\n\nEx Output:\n2\n\n\nEx Input:\nSentence: 'a woman beside a mirror and a door in a room'. How many words start with the letter 'b' in the sentence.\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "1\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a short article. Your job is to classify the article based on its category. Use the following classification labels, 0. World, 1. Sports, 2. Business, 3. Science or Technical. Label the text \"0\" if it contains information related to world. Label the text \"1\" if it contains information related to sports. Label the text \"2\" if it contains information related business. Label the text \"3\" if it contains science or technical related information. \n\nExample Input: ESPN GOES TO FIGHTS boxing game. ESPN is teaming up with Main Events to hold two PPV events, seven Friday Night Fight cards and three quot;special quot; cards that would be exclusive of Friday Night Fights.\nExample Output: 1\n\nExample Input: Stores open doors to sales, surge Retailers opened their doors before the sun rose yesterday, the official start of the holiday shopping season, tempting early risers with specials on a variety of items including flat-screen TVs and toys.\nExample Output: 2\n\nExample Input: Univ. of Calif. Reaches Settlement with Lehman NEW YORK (Reuters) - The University of California said on Friday that Lehman Brothers has agreed to pay $222.5 million to settle a class action suit for the bank's role in the sale of Enron Corp. securities to it and other plaintiffs.\nExample Output:"
},
{
"from": "gpt",
"value": "2\n\n"
}
] |
[
{
"from": "human",
"value": "Q: You are given a sentence and a question in the input. If the information provided in the sentence is enough to answer the question, label \"Yes\", otherwise label \"No\". Do not use any facts other than those provided in the sentence while labeling \"Yes\" or \"No\". There are only two types of valid responses: Yes and No.\nSentence: And so, every few years, the sun and moon come together to show the pink moon's is always with us, even in the day time . \nQuestion: Why was the pink moon lonely?\nA:"
},
{
"from": "gpt",
"value": "Yes."
}
] |
[
{
"from": "human",
"value": "Q: The task is to generate the correct answer for a given math problem.\nProblem: evaluate : 40 - 12 * 3 * 2 = ?\nA:"
},
{
"from": "gpt",
"value": "32"
}
] |
[
{
"from": "human",
"value": "Teacher:Read the given sentence and if it is a general advice then indicate via \"yes\". Otherwise indicate via \"no\". advice is basically offering suggestions about the best course of action to someone. advice can come in a variety of forms, for example Direct advice and Indirect advice. (1) Direct advice: Using words (e.g., suggest, advice, recommend), verbs (e.g., can, could, should, may), or using questions (e.g., why don't you's, how about, have you thought about). (2) Indirect advice: contains hints from personal experiences with the intention for someone to do the same thing or statements that imply an action should (or should not) be taken.\nTeacher: Now, understand the problem? Solve this instance: I appreciate the advice .\nStudent:"
},
{
"from": "gpt",
"value": "no"
}
] |
[
{
"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: Of course, those initial funds were the real sticking point, until the fortuitous occurrence of Garnet's death, that is.\nOutput:"
},
{
"from": "gpt",
"value": "Plural"
}
] |
[
{
"from": "human",
"value": "Instructions: Here are two questions (Question1 and Question2). If these questions have the same meaning and same answer, answer \"Yes\", otherwise \"No\".\nInput: Question1: Why does gel nail polish crack?, Question2: Why do gel nails crack?\nOutput:"
},
{
"from": "gpt",
"value": "Yes"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you are given a country name, and you need to return the country's surface area in terms of square kilometers. Up to two decimal places are allowed in your answer.\nInput: New Zealand\nOutput:"
},
{
"from": "gpt",
"value": "270534.00"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nGiven reviews from Amazon, classify those review based on their content into two classes: Negative or Positive.\nPart 2. Example\nI've read this book with much expectation, it was very boring all through out the book\nAnswer: Negative\nExplanation: Review writer does not like the book because it was boring, therefore it is a negative review.\nPart 3. Exercise\nJust got this Blu Ray and just found out there is no DTS sound unlike what the description says on Amazon. Wait for the better version!\nAnswer:"
},
{
"from": "gpt",
"value": "Negative"
}
] |
[
{
"from": "human",
"value": "Q: In this task, you need to answer basic science questions. For each question, several terms are intentionally masked with ***. This masking can cover very few or many of the question words. Clearly, if masked terms are important, the modified question will be impossible to answer. Please indicate the correct answer with one of the following responses: \"A\", \"B\", \"C\", \"D\" or \"E\". While \"A\"-\"D\" correspond to the answer options provided in the input, \"E\" represents \"I don't know\" for questions that do not provide enough information. Respond via \"E\" if the question is not answerable. Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D', 'E'.\nQuestion: Which of the following statements about food and oxygen is true? (A) Only specialized structures require food and oxygen. (B) Every cell requires food and oxygen. (C) Only plant cells require food and oxygen. (D) Cells do not require food and oxygen because they are not living things.\nA:"
},
{
"from": "gpt",
"value": "B."
}
] |
[
{
"from": "human",
"value": "In this task, you're given four sentences of a story written in natural language, and one last sentence (Sentence5). Your job is to classify whether the last sentence completes the rest of the story coherently or not by providing 'Yes' or 'No'.\n\nExample Input: Sentence1: Tim had to choose between three girls to date. Sentence2: He liked all three of them but he needed to make a decision. Sentence3: He talked to all three of them to see who liked him more. Sentence4: He eventually went with the girl who wanted to see him more. \n Sentence5: Tim is gay.\nExample Output: No\n\nExample Input: Sentence1: Neil had just arrived in Bulgaria. Sentence2: His train took him to the center of Sofia. Sentence3: He was amazed at the busy capital city. Sentence4: It was so beautiful and busy! \n Sentence5: Neil hated his trip.\nExample Output: No\n\nExample Input: Sentence1: I became a Law and Order fan in 2011. Sentence2: I was recovering from a stroke. Sentence3: When I got home I tried to watch every episode. Sentence4: It was hard trying to binge watch 20 Year's of a show. \n Sentence5: I think Law and Order is one of the worst shows ever made.\nExample Output:"
},
{
"from": "gpt",
"value": "No\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a sentence from the research paper and the category to which it belongs. Your task is to classify whether the given category is correct or not by providing \"True\" and \"False\", respectively. Here are the definitions for the categories: Background (Why is this problem important? What relevant works have been created before? What is still missing in the previous works? What are the high-level research questions? How might this help other research or researchers?), Purpose (What specific things do the researchers want to do? What specific knowledge do the researchers want to gain? What specific hypothesis do the researchers want to test?), Method (How did the researchers do the work or find what they sought? What are the procedures and steps of the research?), or Finding (What did the researchers find out? Did the proposed methods work? Did the thing behave as the researchers expected?). \",\n\nQ: Sentence: Background : China has made substantial progress in tackling its HIV and AIDS epidemic. \n Section: background\n\nA: True\n****\nQ: Sentence: timeliness , and patient convenience. \n Section: method\n\nA: False\n****\nQ: Sentence: Immunofluorescence assay ( IFA ) revealed that the epitopes recognized by these scFvs were in the S1 region of the spike protein. \n Section: finding\n\nA:"
},
{
"from": "gpt",
"value": "True\n****\n"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a paragraph from the research paper and your task is to generate a suitable title for the research paper based on the given paper. Under 100 words is a good title length.\nQ: Background: Extraordinary infection control measures limited access to medical care in the Greater Toronto Area during the 2003 Severe Acute Respiratory Syndrome (SARS) outbreak. The objective of this study was to determine if the period of these infection control measures was associated with changes in overall population mortality due to causes other than SARS. Methods: Observational study of death registry data, using Poisson regression and interrupted time-series analysis to examine all-cause mortality rates (excluding deaths due to SARS) before, during, and after the SARS outbreak. The population of Ontario was grouped into the Greater Toronto Area (N = 2.9 million) and the rest of Ontario (N = 9.3 million) based upon the level of restrictions on delivery of clinical services during the SARS outbreak. : There was no significant change in mortality in the Greater Toronto Area before, during, and after the period of the SARS outbreak in 2003 compared to the corresponding time periods in 2002 and 2001. The rate ratio for all-cause mortality during the SARS outbreak was 0.99 [95% Confidence Interval (CI) 0.93-1.06] compared to 2002 and 0.96 [95% CI 0.90-1.03] compared to 2001. An interrupted time series analysis found no significant change in mortality rates in the Greater Toronto Area associated with the period of the SARS outbreak. Conclusion: Limitations on access to medical services during the 2003 SARS outbreak in Toronto had no observable impact on short-term population mortality. Effects on morbidity and long-term mortality were not assessed. Efforts to contain future infectious disease outbreaks due to influenza or other agents must consider effects on access to essential health care services.\nA: "
},
{
"from": "gpt",
"value": "Address: 1 Centre for Research on Inner City Health, the Keenan Research Centre in the Li Ka Shing Knowledge"
}
] |
[
{
"from": "human",
"value": "Q: In this task, you will be shown a conversation and a question. You need to write an implausible answer to the question. Even though there exist multiple wrong answers, we only need a single wrong answer. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\nM: How would you like to move? W: Move? What do you mean? M: Move to a new city. I'm thinking of getting another job. W: But why? What's the matter with the one you have? M: I don't have a good future in the job I have. Besides, I think it would be nice to move to a warmer climate. I'm tired of shoveling snow all winter. W: Where is this new job? M: In California. There won't be any snow to shovel there, and we can go to the beach all the year round. W: That sounds pretty good, but what kind of job is it? M: I would be the Director of Research for a big drug company near Los Angeles. I'd get a big raise in salary. W: That sounds terribly exciting. But how about the children? Will they like moving? M: Why not? California has many beautiful new schools, and Fred can go skiing up in the mountains. W: What about Paula? I'm sure she won't want to leave all her friends. M: Oh, she can make new ones out there. People are very friendly out west. W: I hope so. But, I'll certainly hate to leave this house. We've lived here so long. M: Well, maybe I won't get the job. I have to fly out there for an interview next week. W: You know, I must have known you were thinking about getting a new job. Last night I dreamed we were moving., Question: What does the man have to do next week?\nA:"
},
{
"from": "gpt",
"value": "Be the Director of a big company."
}
] |
[
{
"from": "human",
"value": "Q: In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the alphabetical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no alphabetical element is in the list.\n['x', '3811', 'j', '3441', 'n', '5291', '1777', '1711', 'O', '5285', '8339', 'i', 'F', '5027', '2227', 'R', '3921', '6227', 'n', '4787', 'n', '2591', '7515', '619', 'o', 'y', 'P', 'y', '957', '6277', 'D', 'n', '2901', '1161', '6731', '7679', 'H', '9057', 'C', '5251']\nA:"
},
{
"from": "gpt",
"value": "1, 3, 5, 9, 12, 13, 16, 19, 21, 25, 26, 27, 28, 31, 32, 37, 39"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a sentence and your task is to identify whether the sentence contains motion or not, by classifying the sentence into Yes or No. The sentence belongs to the 'Yes' category if there is an occurrence of a motion of a physical entity otherwise the sentence belongs to the 'No' category. The sentence contains motion if it (i) involves the movement of a physical object. (ii) contains verb in present tense indicating the action performed. Sometimes there can be verb which indicates a motion but the motion might have happened in the past and the answers to such sentences is 'No'\n\n[EX Q]: Horace put his arm around Rose.\n[EX A]: Yes\n\n[EX Q]: The man then sprays down the roof and moves back and fourth.\n[EX A]: Yes\n\n[EX Q]: When he stepped from a stone to Johnnie's head Daddy Longlegs had No idea that he was not walking on another stone.\n[EX A]:"
},
{
"from": "gpt",
"value": "No\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n\n16, 17, ['413', '7783', '3659', 'Q', 'p', '8051', '2065', '9497', '2221', '4175', 'u', 'h', 'A', 'U', 'S', 'b', '2533', 'u', '9561', 'V', 'J']\nb, 2533\n\n8, 10, ['3817', 'z', 'v', 'T', 'K', '7545', '2403', '6327', 'A', '9133', 'S', 'U', 'e']\n6327, A, 9133\n\n3, 4, ['1255', 'i', 'n', 'H']\n"
},
{
"from": "gpt",
"value": "n, H\n\n"
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: In this task you will be given a list of numbers and you need to subtract every value in the list with the index it is at. The index of an elements shows its numerical order in the list(for example, in the list [7,10,4,5], the index of 7 is 1 and the index of 4 is 3) You should start the index at 1, so the first element in the list will be subtracted by one. For every element in the list you need to find \"element - index\" where the index of the beginning element is 1 and increments by 1 for each element. Put your result list in brackets.\nPROBLEM: [6, 17]\n\nSOLUTION: [5, 15]\n\nPROBLEM: [-11, -9]\n\nSOLUTION: [-12, -11]\n\nPROBLEM: [15, 15, -9, 5, -14, 0, -12, 9]\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "[14, 13, -12, 1, -19, -6, -19, 1]\n\n"
}
] |
[
{
"from": "human",
"value": "Q: In this task, you're given a story (which contains five sentences only). Your task is to find all the characters which are available in the given story.\nSentence1: The bully at school punched me. Sentence2: He gave me a black eye. Sentence3: The nurse gave me a cold steak to put on my eye and soothe it. Sentence4: Alas, the meat infected my eye. Sentence5: My parents sued the nurse and won the case.\nA:"
},
{
"from": "gpt",
"value": "I (myself), The nurse, The bully, My parents"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task, you need to answer 'Yes' if the given word is the longest word (in terms of number of letters) in the given sentence, else answer 'No'. Note that there could be multiple longest words in a sentence as they can have the same length that is the largest across all words in that sentence.\nTeacher: Now, understand the problem? Solve this instance: Sentence: 'a man on a snowboard doing a trick on a rail'. Is 'snowboard' the longest word in the sentence?\nStudent:"
},
{
"from": "gpt",
"value": "Yes"
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: In this task, you are given a word, followed by two sentences. Your task is to figure out whether both the sentences use the aforementioned word with the same meaning. You should respond with 'True' if the words in both sentences share the same meaning, and 'False' otherwise.\nPROBLEM: create \n Sentence1: You can create the color orange by mixing yellow and red. \n Sentence2: The company was created 25 years ago.\n\nSOLUTION: False.\n\nPROBLEM: opening \n Sentence1: The opening received good critical reviews. \n Sentence2: John spends two hours a day studying openings, and another two hours studying endgames.\n\nSOLUTION: True.\n\nPROBLEM: part \n Sentence1: He wanted to feel a part of something bigger than himself. \n Sentence2: She played the part of Desdemona.\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "True.\n\n"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you're given a context passage. Your job is to generate relevant questions that can be answered by directly referring to the passage.\nInput: Thank goodness the nice editor at Pink Raygun caught it . She laughed at me . I'm so embarrassed . I feel like a poser -- being all YAY and being totally wrong . We just watched Tron , too .\nOutput:"
},
{
"from": "gpt",
"value": "What may have caused the editor to laugh at you ?"
}
] |
[
{
"from": "human",
"value": "Q: 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.\n[281, 173, 613, 196, 77, 221, 479, 577, 157, 701, 881, 623, 227, 585, 809]\nA:"
},
{
"from": "gpt",
"value": "[281, 173, 613, 479, 577, 157, 701, 881, 227, 809]"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you're given a statement, and three sentences as choices. Your job is to determine which sentence clearly disagrees with the statement. Indicate your answer as '1', '2', or '3' corresponding to the choice number of the selected sentence.\nQ: Statement: It is, of course, a matter of sensibility. Choices: 1. We need to be reasonable towards these people and yet stern. 2. Making sense is what matters most. 3. We don't need to make sense of this.\nA:"
},
{
"from": "gpt",
"value": "3"
}
] |
[
{
"from": "human",
"value": "Given a part of privacy policy text, classify it into one of these categories: \n (1) First Party Collection/Use (how and why a service provider collects user information), \n (2) Third Party Sharing/Collection (how user information may be shared with or collected by third parties), \n (3) User Choice/Control (choices and control options available to users), \n (4) User Access, Edit, & Deletion (if and how users may access, edit, or delete their information), \n (5) Data Retention (how long user information is stored), \n (6) Data Security (how user information is protected), \n (7) Policy Change (if and how users will be informed about changes to the privacy policy).\n\nEx Input:\nAn unspecified third party does not see unspecified information about you for an unspecified purpose. You can opt in for data collection for the collection or sharing of your information.\n\nEx Output:\nThird Party Sharing/Collection\n\n\nEx Input:\nA user's unspecified information is retained indefinitely to maintain service operations or security.\n\nEx Output:\nData Retention\n\n\nEx Input:\nWhen a minor change is made to the privacy policy that does not significantly affect data practices, users are notified in an unspecified manner. Users' choices regarding policy changes are not mentioned or are unclear.\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "Policy Change\n\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given two simple actions (associated with \"A\", \"B\"). You must identify which action is considered less ethical. Do not generate anything else apart from one of the following characters: 'A', 'B'.\nProblem:(A) being pissed at my friend for her actions in a psych ward\n(B) not participating in company activities\nSolution:"
},
{
"from": "gpt",
"value": "A"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nRead the given query and classify it as a 'Good' or 'Bad' query depending on how well the query is formed, 'Bad' being the expected output for a not so well formed query and 'Good' being the expected output for a well formed query. A query may be wrong based on common sense or general facts, but if it is well formed, you should answer with Good.\nExample: What is the scientific name of the tortoise ?\nOutput: Good\nThe output for the query is Good because the query has no grammatical, punctuation or spelling errors.\n\nNew input case for you: What is stronger alligator or cocrodile ?\nOutput:"
},
{
"from": "gpt",
"value": "Bad"
}
] |
[
{
"from": "human",
"value": "Given a sentence, generate what should be the most likely next statement. The next statement should be reasonable and logically correct.\nOne example: We notice a man in a kayak and a yellow helmet coming in from the left. As he approaches, his kayak \nSolution is here: flips upside - down\nExplanation: Flipping of the kayak is a probable event. It is a logical next statement, given the context.\n\nNow, solve this: Several scenes of games are shown being played. We then\nSolution:"
},
{
"from": "gpt",
"value": "see images and still photos as he talks."
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: In this task, you are given a question and a corresponding answer. Your task is to generate a fact statement that is useful in answering the given question.\nPROBLEM: Question: a person places a dime next to an object on a table. The dime moves toward the object on its own. Which of these is likely to be that object? Answer: a piece of carbon steel.\n\nSOLUTION: carbon steel is always magnetic\n\nPROBLEM: Question: Single cell organisms can put an animal in the? Answer: emergency room.\n\nSOLUTION: bacteria can cause people to become ill\n\nPROBLEM: Question: What fails to work during a power outage? Answer: an electric fan.\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "electrical devices convert electricity into other forms of energy\n\n"
}
] |
[
{
"from": "human",
"value": "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.\n\nInput: Consider Input: orange is a kind of food\n\nOutput: orange IsA food\n\n\nInput: Consider Input: die is a kind of change\n\nOutput: die IsA change\n\n\nInput: Consider Input: day can be characterized by bright\n\n"
},
{
"from": "gpt",
"value": "Output: day HasProperty bright\n\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given text for US Congressional and California state bills, your task is to generate a summary for this bill.\nExample: SECTION 1. LIABILITY OF BUSINESS ENTITIES PROVIDING USE OF FACILITIES \n TO NONPROFIT ORGANIZATIONS.\n\n (a) Definitions.--In this section:\n (1) Business entity.--The term ``business entity'' means a \n firm, corporation, association, partnership, consortium, joint \n venture, or other form of enterprise.\n (2) Facility.--The term ``facility'' means any real \n property, including any building, improvement, or appurtenance.\n (3) Gross negligence.--The term ``gross negligence'' means \n voluntary and conscious conduct by a person with knowledge (at \n the time of the conduct) that the conduct is likely to be \n harmful to the health or well-being of another person.\n (4) Intentional misconduct.--The term ``intentional \n misconduct'' means conduct by a person with knowledge (at the \n time of the conduct) that the conduct is harmful to the health \n or well-being of another person.\n (5) Nonprofit organization.--The term ``nonprofit \n organization'' means--\n (A) any organization described in section 501(c)(3) \n of the Internal Revenue Code of 1986 and exempt from \n tax under section 501(a) of such Code; or\n (B) any not-for-profit organization organized and \n conducted for public benefit and operated primarily for \n charitable, civic, educational, religious, welfare, or \n health purposes.\n (6) State.--The term ``State'' means each of the several \n States, the District of Columbia, the Commonwealth of Puerto \n Rico, the Virgin Islands, Guam, American Samoa, the Northern \n Mariana Islands, any other territory or possession of the \n United States, or any political subdivision of any such State, \n territory, or possession.\n (b) Limitation on Liability.--\n (1) In general.--Subject to subsection (c), a business \n entity shall not be subject to civil liability relating to any \n injury or death occurring at a facility of the business entity \n in connection with a use of such facility by a nonprofit \n organization if--\n (A) the use occurs outside of the scope of business \n of the business entity;\n (B) such injury or death occurs during a period \n that such facility is used by the nonprofit \n organization; and\n (C) the business entity authorized the use of such \n facility by the nonprofit organization.\n (2) Application.--This subsection shall apply--\n (A) with respect to civil liability under Federal \n and State law; and\n (B) regardless of whether a nonprofit organization \n pays for the use of a facility.\n (c) Exception for Liability.--Subsection (b) shall not apply to an \ninjury or death that results from an act or omission of a business \nentity that constitutes gross negligence or intentional misconduct, \nincluding any misconduct that--\n (1) constitutes a crime of violence (as that term is \n defined in section 16 of title 18, United States Code) or act \n of international terrorism (as that term is defined in section \n 2331 of title 18) for which the defendant has been convicted in \n any court;\n (2) constitutes a hate crime (as that term is used in the \n Hate Crime Statistics Act (28 U.S.C. 534 note));\n (3) involves a sexual offense, as defined by applicable \n State law, for which the defendant has been convicted in any \n court; or\n (4) involves misconduct for which the defendant has been \n found to have violated a Federal or State civil rights law.\n (d) Superseding Provision.--\n (1) In general.--Subject to paragraph (2) and subsection \n (e), this Act preempts the laws of any State to the extent that \n such laws are inconsistent with this Act, except that this Act \n shall not preempt any State law that provides additional \n protection from liability for a business entity for an injury \n or death with respect to which conditions under subparagraphs \n (A) through (C) of subsection (b)(1) apply.\n (2) Limitation.--Nothing in this Act shall be construed to \n supersede any Federal or State health or safety law.\n (e) Election of State Regarding Nonapplicability.--This Act shall \nnot apply to any civil action in a State court against a business \nentity in which all parties are citizens of the State if such State \nenacts a statute--\n (1) citing the authority of this subsection;\n (2) declaring the election of such State that this Act \n shall not apply to such civil action in the State; and\n (3) containing no other provision.\nOutput: Shields a business entity from civil liability relating to any injury or death occurring at a facility of that entity in connection with a use of such facility by a nonprofit organization if: (1) the use occurs outside the scope of business of the business entity; (2) such injury or death occurs during a period that such facility is used by such organization; and (3) the business entity authorized the use of such facility by the organization. \nMakes this Act inapplicable to an injury or death that results from an act or omission of a business entity that constitutes gross negligence or intentional misconduct, including misconduct that: (1) constitutes a hate crime or a crime of violence or act of international terrorism for which the defendant has been convicted in any court; or (2) involves a sexual offense for which the defendant has been convicted in any court or misconduct for which the defendant has been found to have violated a Federal or State civil rights law. \nPreempts State laws to the extent that such laws are inconsistent with this Act, except State law that provides additional protection from liability. Specifies that this Act shall not be construed to supersede any Federal or State health or safety law. \nMakes this Act inapplicable to any civil action in a State court against a business entity in which all parties are citizens of the State if such State, citing this Act's authority and containing no other provision, enacts a statute declaring the State's election that this Act shall not apply to such action in the State.\nThis Bill focuses on shielding business entities from civil liability relating to an injury or death depending on the conditions of injury, hence the generated summary is correct.\n\nNew input case for you: SECTION 1. FINDINGS.\n\n Congress finds the following:\n (1) There are new and emerging opportunities for producing \n renewable energy fuel products, which will be of benefit to the \n United States and its citizens.\n (2) Disposal of animal and agricultural wastes can be a \n major problem and new technologies should be promoted to \n utilize these wastes.\n (3) New technologies can be developed and implemented that \n will utilize animal and agricultural wastes to produce \n significant quantities of marketable alternative fuels.\n (4) Investment in renewable energy will--\n (A) enhance the energy security and independence of \n the United States,\n (B) provide significant environmental benefits and \n reduce wastes,\n (C) improve electrical reliability and security, \n and\n (D) promote sustainable development opportunities.\n (5) Alternative fuels should be a major part of the \n strategy to increase domestic production of motor fuels.\n (6) The Federal Government should take all measures to \n provide incentives to assure the implementation of technologies \n to produce alternative fuels.\n\nSEC. 2. MODIFICATION OF CREDIT FOR PRODUCTION OF ELECTRICITY FROM \n RENEWABLE RESOURCES.\n\n (a) Credit Allowed for Producers of Certain Energy.--Section \n45(a)(2) of the Internal Revenue Code of 1986 (relating to electricity \nproduced from certain renewable resources) is amended to read as \nfollows:\n ``(2) the--\n ``(A) kilowatt hours of electricity--\n ``(i) produced by the taxpayer--\n ``(I) from qualified energy \n resources (other than qualified waste), \n and\n ``(II) at a qualified facility \n during the 10-year period beginning on \n the date the facility was originally \n placed in service, and\n ``(ii) sold by the taxpayer to an unrelated \n person during the taxable year, or\n ``(B) amount of kilowatt hours of electricity \n equivalent which is equal to the Btu of any fuel or \n feedstock--\n ``(i) produced by the taxpayer--\n ``(I) from qualified waste or \n poultry waste, and\n ``(II) at a qualified facility \n during the 10-year period beginning on \n the date the facility was originally \n placed in service, and\n ``(ii) sold by the taxpayer to an unrelated \n person during the taxable year.''.\n (b) Qualified Energy Resources.--\n (1) In general.--Section 45(c)(1) of the Internal Revenue \n Code of 1986 (defining qualified energy resources) is amended \n by striking ``and'' at the end of subparagraph (B), by striking \n the period at the end of subparagraph (C) and inserting ``, \n and'', and by adding at the end the following:\n ``(D) qualified waste.''.\n (2) Qualified waste.--Section 45(c) of such Code (relating \n to definitions) is amended by adding at the end the following:\n ``(5) Qualified waste.--The term `qualified waste' means \n agriculture and animal waste (other than poultry waste), \n including by-products, packaging, and any materials associated \n with the processing, raising, feeding, selling, transporting, \n or disposal of agricultural or animal products.''.\n (c) Qualified Facility.--Section 45(c)(3) of the Internal Revenue \nCode of 1986 (defining qualified facility) is amended by adding at the \nend the following:\n ``(D) Qualified waste facility.--In the case of a \n facility using qualified waste or poultry waste to \n produce alternative fuel feedstock, the term `qualified \n facility' means any facility of the taxpayer which is \n originally placed in service by the taxpayer after \n December 31, 2001, and before January 1, 2007.''.\n (d) Government-Owned Facilities.--Section 45(d)(6) of the Internal \nRevenue Code of 1986 (relating to credit eligibility in the case of \ngovernment-owned facilities using poultry waste) is amended by \ninserting ``or using poultry waste or qualified waste to produce \nalternative fuel feedstock'' after ``electricity''.\n (e) Limit on Carryback of Credit.--Section 39(d)(3) of the Internal \nRevenue Code of 1986 (relating to no carryback of renewable electricity \nproduction credit before effective date) is amended by inserting ``and \nbefore January 1, 2002, to the extent such credit is attributable to \nenergy (other than electricity) produced from qualified waste or \npoultry waste'' after ``energy resource''.\n (f) Conforming Amendments.--\n (1) Section 38(b)(8) of the Internal Revenue Code of 1986 \n is amended by inserting ``and other energy'' after \n ``electricity''.\n (2) The heading for section 45 of such Code is amended by \n inserting ``and other energy produced from waste products'' \n after ``resources''.\n (3) The item relating to section 45 in the table of \n sections for subpart D of part IV of subchapter A of chapter 1 \n of such Code is amended by inserting ``and other energy \n produced from waste products'' after ``resources''.\n (4) The heading of section 45(d)(6) of such Code is amended \n by inserting ``or qualified waste'' after ``poultry waste''.\n (g) Effective Date.--The amendments made by this section shall \napply to energy produced after the date of the enactment of this Act.\nOutput:"
},
{
"from": "gpt",
"value": "Amends the Internal Revenue Code to modify the credit for production of electricity from renewable resources to include production of energy from agricultural and animal waste, including by-products and associated materials. Limits such credit to facilities placed in service after 2001 and before 2007."
}
] |
[
{
"from": "human",
"value": "Teacher:You will be given a passage, and your task is to generate a Yes/No question that is answerable based on the given passage.\nTeacher: Now, understand the problem? Solve this instance: There is no legal statute specifically prohibiting the carry of a firearm other than a handgun (pre-1899 black powder weapons, and replicas of such, are not legally firearms in Texas). However, if the firearm is displayed in a manner ``calculated to cause alarm,'' then it is ``disorderly conduct''. Open carry of a handgun in public had long been illegal in Texas, except when the carrier was on property he/she owned or had lawful control over, was legally hunting, or was participating in some gun-related public event such as a gun show. However, the 2015 Texas Legislature passed a bill to allow concealed handgun permit holders to begin carrying handguns openly. The bill was signed into law on June 13, 2015, and took effect on January 1, 2016. A License to Carry (LTC) is still required to carry a handgun openly or concealed in public.\nStudent:"
},
{
"from": "gpt",
"value": "can i carry a gun in texas without a license?"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis. It makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis. It makes you much more likely to believe the hypothesis is true. Your task is to output 'strengthener' or 'weakener' if the update strengths or weakens the hypothesis, respectively.\nInput: Premise: PersonX eats pancakes\nHypothesis: Before, PersonX needed cook pancakes for themselves\nUpdate: PersonX lives alone.\nOutput:"
},
{
"from": "gpt",
"value": "strengthener"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task you are given a tweet. You must judge whether the author of the tweet is angry or not. Label the instances as \"Angry\" or \"Not angry\" based on your judgment.\nQ: @BI_Science Opioid rapid pill plague...Speed generations Pulse Rapid rabid Impairment Ist Choice Stacked usage vs street ingestion demo US\nA:"
},
{
"from": "gpt",
"value": "Angry"
}
] |
[
{
"from": "human",
"value": "This task is about classifying the similarity of two sentences. The sentences can be classified as (a) SIMILAR - similar to each other, and (b) DISSIMILAR - not similar to each other. Sentences that have the same RDF relationship in terms of [subject, predicate, object] are similar to each other. The input is a list of two sentences and the output is either SIMILAR or DISSIMILAR.\n\n['The address, 11 Diagonal Street is located in South Africa and Jacob Zuma is a leader in Asian South Africans.', 'Chevrolet was the manufacturer on June 22nd.']"
},
{
"from": "gpt",
"value": "DISSIMILAR"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to write a question that clarifies the given question in such a way that the generated question has one unique answer.\nSee one example below:\nProblem: Lucifer how many episodes are in season 3?\nSolution: How many episodes of season 3 of Lucifer were there, including bonus episodes?\nExplanation: The generated question clarifies the input question by asking about bonus episodes because if the question is about regular episodes only then the answer will be different than including the bonus episodes.\n\nProblem: Who played count dooku in star wars the clone wars?\nSolution:"
},
{
"from": "gpt",
"value": "Who played count dooku in star wars the clone wars tv series in 2003?"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task you will be given a 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\nclaim: Music containing lyrics that glorify violent and criminal lifestyles should be banned.\n perspective: hip hop artists have a right to free speech\nSolution: undermine\nWhy? Musicians having a right to free speech clearly undermines the claim for putting constraints on their lyrics.\n\nNew input: claim: Sexist advertising must be banned.\n perspective: Policies should be established which ban the promotion of sexist attitudes in advertising.\nSolution:"
},
{
"from": "gpt",
"value": "support"
}
] |
[
{
"from": "human",
"value": "Given a sentence, generate what should be the most likely next statement. The next statement should be reasonable and logically correct.\n\nSomeone gently lifts her off the platform and holds her against his shoulder. He"
},
{
"from": "gpt",
"value": "holds it above her head and stretches her arms over her head."
}
] |
[
{
"from": "human",
"value": "Q: In this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about \"doctors\", you can talk about \"health\" or \"diagnosis\", but don't mention \"aliens\". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example: \"She likes cakes.\" is changed to \"She doesn't like cakes.\"\nBeginning: Jack had been experiencing stomach pain all day. Middle: Jack went to hospital in the evening. Ending: Jack was admitted to the hospital and had his appendix removed.\nA:"
},
{
"from": "gpt",
"value": "Jack found relief in the evening."
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nYou are given a target race, and two sentences. Your task is to determine whether the second sentence is either a stereotype, anti-stereotype, or is unrelated with respect to the first sentence and the target. A stereotype is a widely held but oversimplified notion of a group of people. An anti-stereotype is an idea that goes against the widely held but oversimplified notion of a group of people. Sentences and targets are unrelated if there is no relevance between them.\n\nTarget: Vietnam \nVietnam food is so good to eat. The language is easy to speak.\nOutput:"
},
{
"from": "gpt",
"value": "anti-stereotype"
}
] |
[
{
"from": "human",
"value": "Q: 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.\nComment: Get fucked, asshole.\nA:"
},
{
"from": "gpt",
"value": "Sexual-explicit"
}
] |
[
{
"from": "human",
"value": "In this task, you are given an article. Your task is to summarize the article in a sentence.\n\n[EX Q]: South Wales Police said it received a call shortly before 13:00 GMT on Sunday about a body in the River Ogmore in Aberkenfig.\nInsp Dave Greaves said formal identification had not yet taken place and an investigation was under way.\n[EX A]: A man's body has been found in a river in Bridgend county.\n\n[EX Q]: Katharina Schiechtl's header gave the home side the lead while substitute Helen Ward should have equalised early in the second half\nSarah Puntigam and Nina Burger sealed victory for the Group Eight leaders.\nIt was a disappointing result for manager Jayne Ludlow, in charge of her first competitive game after succeeding Jarmo Matikainen in October 2014.\nSarah Zadrazil was prominent early in the game for Austria and tested goalkeeper Joanne Price with an effort from outside the box.\nThe home side went ahead on 25 minutes when Price failed to deal with Carina Wenninger's free-kick and Schiechtl nodded home.\nNia Jones headed over the crossbar in response before Laura Feiersinger hit the woodwork and a second attempt saved by Price.\nHome keeper Manuela Zinsberger denied Seattle Reign's Jess Fishlock as Austria maintained their first-half lead.\nWard replaced Melissa Fletcher at the interval and the Reading striker came close to equalising early in the second half but shot wide following good work by Fishlock.\nWales struggled with set-pieces all evening and they conceded again with 17 minutes remaining when Puntigam scored directly from a corner.\nBurger completed the scoring with a close-range header to secure Austria's second victory of the campaign after their 2-0 win against Kazakhstan\nWales' next game on 23 October is away to top seeds Norway, who earlier in the day began their campaign with a 4-0 win in Kazakhstan.\nWales manager Jayne Ludlow told BBC Radio Wales:\n\"There were many aspects I was pleased with but the fact that we got done by two set plays I'm not very pleased with.\n\"The last goal for them was a positional error so there are things we can correct and we can work on and build for the future.\n\"There were a few girls on that pitch who haven't experienced international football before so it was very pleasing to see their performances.\"\n[EX A]: Wales women suffered defeat by Austria in their opening game of the Euro 2017 qualifying campaign in St Polten.\n\n[EX Q]: Best-selling author Nick Arnold said a field between Appledore and Northam, in Devon, played host to the bloody battle of 1069.\nMr Arnold, who wrote the Horrible Science series of books, described the clash as the \"sequel\" to the Norman victory of 1066.\nAcademics have described the find as \"significant\" to British history.\nMr Arnold started research into the battlefield, inspired by a story from his grandfather, five years ago.\nHe said the sons of the vanquished King Harold came back for a bloody \"rematch\" in North Devon three years after his defeat at Hastings.\nMore than 3,000 people died in the resulting clash, Mr Arnold said, after 64 longships \"crammed with armed men\" led by Godwine and Edmund arrived at Appledore on 26 June 1069.\nTheir army, which arrived from Ireland, met a fighting force made up of Normans, Bretons and English.\nThey were met and roundly defeated by forces led by Brian of Brittany in a day-long battle.\n\"The showdown settled once and for all who would rule England,\" he said.\nJanuary 1066 - Edward the Confessor dies. Harold gambles and makes a bid for the Crown, supported by all the magnates of England\n14 October 1066 - Harold is defeated by William at the Battle of Hastings\nOctober to December 1066 - A state of war continues until a deal is struck in December between William and the English magnates in which he guarantees their positions in return for their support.\n25 December 1066 - William is crowned King of England in London\nMr Arnold said he was confident he had successfully narrowed down the correct site.\n\"By combining scientific data on the estuary with accounts of the battle it's possible to locate the fighting in a small area,\" he said.\n\"The amazing cast of supporting characters include a treacherous Abbot, a conscience-stricken Queen and a headless saint.\"\nMr Arnold went back to original sources including the Anglo-Saxon Chronicle and consulted histories of the landscape.\nHe also looked at times of high water and sundown and said all of the available evidence pointed to one location.\nThe Devonshire Association has published Mr Arnold's research paper which is being republished by the Battlefields Trust.\nDr Benjamin Hudson from Pennsylvania State University in the US said the research was \"a significant contribution to the history of medieval Britain\".\nElisabeth van Houts, Professor of Medieval European History at Emmanuel College, Cambridge, said Mr Arnold had carried out \"an exemplary piece of lucid writing, research and detective work\".\n[EX A]:"
},
{
"from": "gpt",
"value": "The site of the decisive follow-up to the Battle of Hastings has been discovered, it has been claimed.\n\n"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nIn this task, you are given triplets. Each triplet is in the form of [subject, predicate, object]. Your task is to generate proper sentence that utilizes these triples. The objective is to construct a sentence that (a) captures the facts specified in the triples and (b) is a well-formed sentence easily understandable by a human. All triple values need not be used directly in the sentence as long as the facts are adequately captured.\nPart 2. Example\n[['Northwestern College', 'NICKNAME', 'Red Raiders'], ['Northwestern College', 'LOCATION', 'Orange City, Iowa']]\nAnswer: The team whose nickname is red raiders is located in the orange city, iowa\nExplanation: This sentence uses the triplets by correctly using the (subject, predicate, object) semantics for both the triplets provided. Since college teams are popularly associated with nicknames, some information in the generated sentence can be inferred. In this case, Northwestern College was replaced with the team automatically.\nPart 3. Exercise\n[['A.E Dimitra Efxeinoupolis', 'LOCATION', 'Greece'], ['Greece', 'CURRENCY', 'Euro'], ['Greece', 'LEADER', 'Alexis Tsipras'], ['Greece', 'CAPITAL', 'Athens'], ['Greece', 'LEADER', 'Prokopis Pavlopoulos']]\nAnswer:"
},
{
"from": "gpt",
"value": "The A.E Dimitra Efxeinoupolis club is located in Greece, where the money used is the Euro. Athens is the capital of Greece, and two of the leaders are Alexis Tsipras and Prokopis Pavlopoulos."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.