Search is not available for this dataset
conversations
listlengths 2
2
|
|---|
[
{
"from": "human",
"value": "In 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.\nOne example is below.\nQ: I sting a mosquito\n(A) A human is a mammal\n(B)A human is omnivorous\n(C)A human doesn't have stings\nA: C\nRationale: The third option explains why a human can't sting a mosquito correctly. So, the third option is the best choice.\nQ: Jack jumps up the cliff\n(A) one can jump up the cliff given enough strength\n(B)the cliff is too steep and Jack likes jumping\n(C)the height of the cliff is much more than the limit of one's strength\nA:"
},
{
"from": "gpt",
"value": "C"
}
] |
[
{
"from": "human",
"value": "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.\nQ: A synopsis of the book published in 1910 states: This is a romance of the Virginia tobacco fields and has for its central figure Christopher Blake. He is the descendant of a rich and aristocratic family, and through reduced fortunes is obligated to work as a laborer on the estate which for generations has been owned by his forbears. Upon the death of his father, when he is only ten years old, he suddenly finds home and fortune snatched from him, and with a blind mother and two sisters to support he begins a life of toil. He foregoes education and drudges unceasingly that his mother may be kept in ignorance of her change of fortune and that his twin sister may not have to work. After fifteen years of this existence his nature becomes hardened and his heart is filled with hatred for Mr. Fletcher, the past manager of the estate, who is now its possessor. Fletcher, who is a vulgar and ugly tempered man, has gained his possessions by cheating and dishonesty, and Christopher's one though from childhood has been a desire for revenge. He finds his opportunity in leading to ruin Fletcher's grandson, Will, a weak young fellow, who is idolized by his grandfather. Christopher leads him into dissipation and teaches him to despise his grandfather till finally in a moment of drunken frenzy he kills him. Then Christopher realizes the enormity of his sin, aids Will to escape, and takes the punishment. He goes to prison to serve out a five years' sentence, but after three years have passed is pardoned out through the efforts of Maria Wyndham, Fletcher's granddaughter, whom he has loved for years. Maria, who has returned his affection and is now the heir to the estate, is only too glad to restore it to its rightful owner, and the lovers, and their many years of unhappiness, are at least united.\nA: "
},
{
"from": "gpt",
"value": "Why is Christopher forced to work as a laborer?"
}
] |
[
{
"from": "human",
"value": "From the given sentence, extract the phrase (often noun or verb) that carries the given relationship. The generated phrase should be present in the sentence.\nExample: Given Relationship: 'make', Sentence: 'Jenny made the announcement that her baby was an alien.'\nExample solution: made\nExample explanation: The output relationship - made, is a correct verb form of the given relationship - make, and it is also used in the given sentence\n\nProblem: Given Relationship: 'support', Sentence: 'Both Syria and Hamas are supported by Iran .'\n"
},
{
"from": "gpt",
"value": "Solution: supported"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given an input list A. You need to find all the elements of the list that are alphabets in the same order as they appear in the list A. Do not change their case/capitalization.\nProblem:['6657', 'f']\nSolution:"
},
{
"from": "gpt",
"value": "f"
}
] |
[
{
"from": "human",
"value": "In this task, you are given inputs i, j, and A, where i and j are integers and A is a list. You need to find all elements of A from the ith element to the jth element, reverse the order in which they occur, and then concatenate them to output the resultant string. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j. Perform the operations in order, i.e., do not concatenate the elements and then reverse the string.\n\nExample input: 1, 3, ['238', 'h', '92', 'U', '2799']\nExample output: 92h238\nExample explanation: Here, concatenating all the elements between the 1st element and 3rd element in reverse order gives '92h238'.\nQ: 2, 2, ['u', '2523']\nA:"
},
{
"from": "gpt",
"value": "2523"
}
] |
[
{
"from": "human",
"value": "Definition: In this task, you are given inputs i and A, where i is an integer and A is a list. You need to list all the elements of A preceding the last i elements. i will always have a value less than the length of A.\nInput: 10, ['3079', 't', 'Q', 'c', 'i', 'B', 'V', '3809', '1585', '1981', '8479', 'd', 'Y', 's', '6337', '4897', '2581', 'E', 'b', 'T', 'o']\nOutput:"
},
{
"from": "gpt",
"value": "3079, t, Q, c, i, B, V, 3809, 1585, 1981, 8479"
}
] |
[
{
"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: Lose the dismal cover illustrations and return to having a lead review or cover essay. Sentence 2: It is highly recommended that when submitting a cover essay, one should include a dismal cover illustration. 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: no it's not you think of your chances of getting the death penalty after cre uh committing a crime are really pretty slim right now and you can probably spend uh a lot of time Sentence 2: You probably won't get the death penalty. 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: But my friends call me Tuppence.\" Sentence 2: Tuppence is what my friends call me. 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": "9\n\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. Languages typically provide more than one grammatical construction to express certain types of messages. Your task is to generate a senetence with the same meaning as given sentence, but with different grammatical construction.\n\nAlice owed him the money\n"
},
{
"from": "gpt",
"value": "Alice owed the money to him"
}
] |
[
{
"from": "human",
"value": "In this task you are given a sentence. You must judge whether subject of the main clause is singular or plural. Label the instances as \"Singular\" or \"Plural\" based on your judgment.\n\nEx Input:\nThe green LED on the bottom right of the screen turned red.\n\nEx Output:\nSingular\n\n\nEx Input:\nThe blades crashed and the room shook.\n\nEx Output:\nPlural\n\n\nEx Input:\nNothin' changes, baby. \"\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "Plural\n\n\n"
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: For the given English description, write an SQL command such that it accomplishes every step. An SQL query works by selecting data from a table where certain conditions apply. A table contains columns where every row in that table must have a value for each column. Every table has a primary key that uniquely identifies each row, usually an id. To choose which columns are returned you specify that after the \"SELECT\" statement. Next, you use a \"FROM\" statement to specify what tables you want to select the data from. When you specify a table you can rename it with the \"AS\" statement. You can reference that table by whatever name follows the \"AS\" statement. If you want to select data from multiple tables you need to use the \"JOIN\" statement. This will join the tables together by pairing a row in one table with every row in the other table (Cartesian Product). To limit the number of rows returned you should use the \"ON\" statement. This will only return rows where the condition specified after the statement is true, this is usually an equals operator with primary keys. You can also use the \"WHERE\" statement to specify that only rows with column values statisfying a certain condition, should be returned. The \"GROUP BY\" statement will group rows together that have equal column values for whatever columns follows the statement. The \"HAVING\" statement will return groups that statisfy whatever condition follows the statement. Any column(s) being returned from grouped rows must either be an aggregate function, (AVG, MAX, COUNT, SUM, ...) of a column, or the column(s) that the data was grouped by. To sort the returned data you can use the \"ORDER BY\" command which will order the data by whatever aggregate function or column follows the statement. The \"DESC\" statement will sort in descending order and the \"ASC\" statement will sort in ascending order. Finally, you can use the \"LIMIT\" statement to return a certain number of rows. When \"*\" is used in an SQL statement every column is returned. For example, SELECT * FROM table WHERE attribute = 1, will select every column from rows with the attribute column equal to 1.\nPROBLEM: Did M0 's writer , director , cinematographer , editor , producer , and art director direct and executive produce M1\n\nSOLUTION: SELECT count(*) WHERE {\n?x0 ns:film.cinematographer.film M0 .\n?x0 ns:film.director.film M0 .\n?x0 ns:film.director.film M1 .\n?x0 ns:film.editor.film M0 .\n?x0 ns:film.film_art_director.films_art_directed M0 .\n?x0 ns:film.producer.films_executive_produced M1 .\n?x0 ns:film.producer.film|ns:film.production_company.films M0 .\n?x0 ns:film.writer.film M0\n}\n\nPROBLEM: Did M3 's editor and writer edit and produce M0 , M1 , and M2\n\nSOLUTION: SELECT count(*) WHERE {\n?x0 ns:film.editor.film M0 .\n?x0 ns:film.editor.film M1 .\n?x0 ns:film.editor.film M2 .\n?x0 ns:film.editor.film M3 .\n?x0 ns:film.producer.film|ns:film.production_company.films M0 .\n?x0 ns:film.producer.film|ns:film.production_company.films M1 .\n?x0 ns:film.producer.film|ns:film.production_company.films M2 .\n?x0 ns:film.writer.film M3\n}\n\nPROBLEM: Did M0 influence M1 , marry M5 , M6 , and M7 , and influence M2 , M3 , and M4\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "SELECT count(*) WHERE {\nFILTER ( M0 != M5 ) .\nFILTER ( M0 != M6 ) .\nFILTER ( M0 != M7 ) .\nM0 ns:influence.influence_node.influenced M1 .\nM0 ns:influence.influence_node.influenced M2 .\nM0 ns:influence.influence_node.influenced M3 .\nM0 ns:influence.influence_node.influenced M4 .\nM0 ns:people.person.spouse_s/ns:people.marriage.spouse|ns:fictional_universe.fictional_character.married_to/ns:fictional_universe.marriage_of_fictional_characters.spouses M5 .\nM0 ns:people.person.spouse_s/ns:people.marriage.spouse|ns:fictional_universe.fictional_character.married_to/ns:fictional_universe.marriage_of_fictional_characters.spouses M6 .\nM0 ns:people.person.spouse_s/ns:people.marriage.spouse|ns:fictional_universe.fictional_character.married_to/ns:fictional_universe.marriage_of_fictional_characters.spouses M7\n}\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a context passage, an answer, and a question. Your task is to classify whether the question for this answer is correct or not, based on the given context with commonsense reasoning about social situations. If its correct ,return \"True\" else \"False\".\nQ: Context: sasha was a patient person so she spent an hour waiting. \n Answer: as calm \n Question: How would Sasha feel afterwards?\nA: "
},
{
"from": "gpt",
"value": "True"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, based on the given context word, you are asked to create a pair of sentences each containing a blank (_). The sentence pair should look similar and should be about two different persons (PersonX and PersonY). Additionally, the two sentences must be different in terms of trigger words (e.g., \"sympathetic\" and \"stern\") which express contrasting attributes about the two persons. The answer to the first and the second sentence must be PersonX and PersonY, respectively. PersonX and PersonY should not be equally likely to fill the blank. For each sentence, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people (e.g., Donald Trump, Putin, etc.) in your sentences. Avoid repeating the same style or phrase in twin sentences e.g., a contrasting sentence can always be created using simple negation i.e. by adding not, never, etc. Instead, try to increase diversity. Both twin sentences must contain at least 15 and at most 30 words. Twin sentences must have at least 70% overlapping words. You must utilize the given context word while writing the twin sentences. Each of the twin sentences must contain only one blank. Make sure that PersonX and PersonY have the same gender. In each sentence, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY.\nQ: Context Word: vitamins.\nA:"
},
{
"from": "gpt",
"value": "Sentence 1: PersonX gave them vitamins everyday, and PersonY took them, because _ was a good parent. \nSentence 2: PersonX gave them vitamins everyday, and PersonY took them, because _ was a good child."
}
] |
[
{
"from": "human",
"value": "In this task, based on the given context word, you are asked to create a pair of sentences each containing a blank (_). The sentence pair should look similar and should be about two different persons (PersonX and PersonY). Additionally, the two sentences must be different in terms of trigger words (e.g., \"sympathetic\" and \"stern\") which express contrasting attributes about the two persons. The answer to the first and the second sentence must be PersonX and PersonY, respectively. PersonX and PersonY should not be equally likely to fill the blank. For each sentence, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people (e.g., Donald Trump, Putin, etc.) in your sentences. Avoid repeating the same style or phrase in twin sentences e.g., a contrasting sentence can always be created using simple negation i.e. by adding not, never, etc. Instead, try to increase diversity. Both twin sentences must contain at least 15 and at most 30 words. Twin sentences must have at least 70% overlapping words. You must utilize the given context word while writing the twin sentences. Each of the twin sentences must contain only one blank. Make sure that PersonX and PersonY have the same gender. In each sentence, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY.\nExample: Context word: upset.\nExample solution: Sentence 1: PersonX yelled at PersonY because _ was so upset about the news. \nSentence 2: PersonX comforted at PersonY because _ was so upset about the news.\nExample explanation: As expected, two sentences contain mentions of PersonX and PersonY and they're quite similar. Their difference is in terms of trigger words (\"yelled\" and \"comforted\"), whcih result in them having different answers. As required by the instructions, the answer to sentence 1 and sentence 2 are PersonX and PersonY, respectively.\n\nProblem: Context Word: Hawaii.\n"
},
{
"from": "gpt",
"value": "Solution: Sentence 1: PersonX was very excited to be flying to Hawaii with PersonY who has flown many times before, but _ was feeling anxious. \nSentence 2: PersonX was very excited to be flying to Hawaii with PersonY who has flown many times before, but _ was feeling calm."
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nGiven a paragraph from a Wikipedia article about some topic, and a question related to the topic, determine whether the question is answerable from the paragraph. If the question is answerable, answer \"True\", otherwise, answer \"False\".\n\nMuammar Gaddafi was born in a tent near Qasr Abu Hadi, a rural area outside the town of Sirte in the deserts of western Libya. His family came from a small, relatively un-influential tribal group called the Qadhadhfa, who were Arabized Berber in heritage. His father, Mohammad Abdul Salam bin Hamed bin Mohammad, was known as Abu Meniar (died 1985), and his mother was named Aisha (died 1978); Abu Meniar earned a meager subsistence as a goat and camel herder. Nomadic Bedouins, they were illiterate and kept no birth records. As such, Gaddafi's date of birth is not known with certainty, and sources have set it in 1942 or in the spring of 1943, although biographers Blundy and Lycett noted that it could have been pre-1940. His parents' only surviving son, he had three older sisters. Gaddafi's upbringing in Bedouin culture influenced his personal tastes for the rest of his life. He repeatedly expressed a preference for the desert over the city and retreated to the desert to meditate. Question: Who died first, Abu Meniar or Aisha?\nOutput:"
},
{
"from": "gpt",
"value": "True"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a context tweet and an answer. Your job is to generate a question for the given answer based on the given tweet paragraph. Note that your question should be answerable based on the given tweet, and the answer to your question should be the given answer.\nQ: Context: Sam Amick @sam_amickMore from the Draymond v. NBA front: his agent, B.J. Armstrong, isn't happy with the league's stance or its style , 7:14:02 AM Answer: b.j. armstrong\nA: "
},
{
"from": "gpt",
"value": "what is the name of draymond's agent?"
}
] |
[
{
"from": "human",
"value": "You are given a password and you need to generate the number of steps required to convert the given password to a strong password. A password is considered strong if (a) it has at least 6 characters and at most 20 characters; (b) it contains at least one lowercase letter and one uppercase letter, and at least one digit; (c) it does not contain three repeating characters in a row. In one step you can: (1) Insert one character to password, (2) delete one character from password, or (3) replace one character of password with another character.\n\npassword = iLZO5DWLNslX9pjr3hXMAIOs"
},
{
"from": "gpt",
"value": "4"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. 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.\n\nheat skillet on stovetop.,add olive oil, onions, garlic, cook until softened.,add corn and rosemary and stir.,______,add heavy cream, bring to a boil and cook until reduced by 1/3.,remove from heat.,stir in feta and butter until creamy.,season with fresh ground pepper, serve.\n"
},
{
"from": "gpt",
"value": "add stock and simmer until corn is tender, 5 minutes."
}
] |
[
{
"from": "human",
"value": "Classify the given tweet into the three categories: (1) 'Hate Speech', (2) 'Offensive' and (3) 'Neither'. 'Hate Speech' is kind of a threating statement or sometimes include call for violence while 'offensive' statement just offensds someone. 'Neither' is when it doesn't fall into Hate Speech or Offensive category.\nExample: \"@MarkRoundtreeJr: LMFAOOOO I HATE BLACK PEOPLE https://t.co/RNvD2nLCDR\" This is why there's black people and niggers\nExample solution: Hate Speech\nExample explanation: The writer mentions emotions like hating so it is clearly a hate speech.\n\nProblem: \"@ozzie_garza: @white_thunduh I'm so sure bitch\" frfr tf\n"
},
{
"from": "gpt",
"value": "Solution: Offensive"
}
] |
[
{
"from": "human",
"value": "Q: The task is to write a full sentence or two using all of the information given. The sentence(s) will be a brief review of a restaurant. Use all of the information provided.\nname[xname], rating[3 out of 5], location[riverside], familyFriendly[yes], near[xnear]\nA:"
},
{
"from": "gpt",
"value": "Near xnear, by the river, is xname. Its customer rating is 3 out of 5 but it is child friendly."
}
] |
[
{
"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 fine labels that represent a category of words with similar grammatical properties. The list of part-of-speech tags i.e tagset of this corpus is : '$': Dollar Sign, \"''\": Single Quotes, ',': Comma Symbol, '-LRB-': Left Parantheses, '-RRB-': Right Parantheses, '.': Period, ':': Colon, 'ADD': Email Address, 'AFX': Affix, 'CC': Coordinating conjunction, 'CD': Cardinal Number, 'DT': Determiner, 'EX': Existential there, 'FW': Foreign Word, 'GW': Go with, 'HYPH': Hyphen symbol, 'IN': Preposition or a subordinating conjunction, 'JJ': Adjective, 'JJR': A comparative Adjective, 'JJS': A Superlative Adjective, 'LS': List item Marker, 'MD': Modal, 'NFP': Superfluous punctuation, 'NN': Singular Noun, 'NNP': Singular Proper Noun, 'NNPS': Prural Proper Noun, 'NNS': Prural Noun, 'PDT': Pre-determiner, 'POS': Possessive Ending, 'PRP': Personal pronoun, 'PRP$': Possessive Pronoun, 'RB': Adverb, 'RBR': Comparative Adverb, 'RBS': Superlative Adverb, 'RP': Particle, 'SYM': Symbol, 'TO': To , 'UH': Interjection, 'VB': Base form Verb, 'VBD': Verb in Past tense, 'VBG': Verb in present participle, 'VBN': Verb in past participle, 'VBP': Verb in non-3rd person singular present, 'VBZ': Verb in 3rd person singular present, 'WDT': Wh-determiner, 'WP': Wh-pronoun, 'WP$' Possessive Wh-pronoun, 'WRB': Wh-adverb, 'XX': Unknown, '``': Double backticks.\n--------\nQuestion: Sentence: I suppose that it 's damn lucky for the {{ GOP }} that she is populated with gullible idiots . \nWord: GOP\n\nAnswer: NNP\n\n\nQuestion: Sentence: Now it is time to take the next steps and achieve even {{ greater }} progress in our public education system . \nWord: greater\n\nAnswer: JJR\n\n\nQuestion: Sentence: That private wealth can easily be funneled into aid for the Palestinians and for Lebanese {{ Shiites }} . \nWord: Shiites\n\nAnswer:"
},
{
"from": "gpt",
"value": "NNPS\n\n\n"
}
] |
[
{
"from": "human",
"value": "You are given a sentence in Italian. Your job is to translate the Italian sentence into English.\nQ: 6.000 lingue diverse, parlate da sei miliardi e mezzo di persone, diverse per colore, proporzioni, altezza.\nA: "
},
{
"from": "gpt",
"value": "6,000 different languages spoken by six and a half billion people, all different colors, shapes, sizes."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to classify the command into one of these seven categories: (1) majority, (2) unique, (3) superlative, (4) count, (5) comparative, (6) aggregation, and (7) ordinal. \n Here are the defications of each category: \n 1. majority: Describing the majority values (most or all) over one column, with the scope of all table rows or a subset of rows \n 2. unique: Describing one unique row, regarding one column, with the scope of all table rows or a subset of rows \n 3. Superlative: Describing the maximum or minimum value in a column, with the scope of all table rows or a subset of rows \n 4. Ordinal: Describing the n-th maximum or minimum value in a column, with the scope of all table rows or a subset of rows \n 5. Comparative: Comparing two rows in the table, regarding their values in one column \n 6. Count: counting some rows in the table based on the values in one column, with the scope of all table rows or a subset of rows \n 7. Aggregation: Describing the sum or average value over a column, with the scope of all table rows or a subset of rows. \n Here are the definitions of logical operators for understanding of command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\nProblem:and { only { filter_eq { all_rows ; gp - gs ; 14 } } ; eq { hop { filter_eq { all_rows ; gp - gs ; 14 } ; season } ; 2009 } }\nSolution:"
},
{
"from": "gpt",
"value": "unique"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given a command in a limited form of natural language, provide the correct sequence of actions that executes the command to thus navigate an agent in its environment. A command can be broken down into many different actions. Actions are uppercase and are individual steps that serve as the building blocks for a command. For commands, 'left' and 'right' are used to denote the direction of an action. The word 'opposite' turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. Actions and commands do not have quotations in the input and output.\nSee one example below:\nProblem: jump left\nSolution: I_TURN_LEFT I_JUMP\nExplanation: The agent must first turn left and then jump in order to jump to the left.\n\nProblem: walk around right thrice and jump opposite right twice\nSolution:"
},
{
"from": "gpt",
"value": "I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_TURN_RIGHT I_JUMP"
}
] |
[
{
"from": "human",
"value": "Teacher:Here are two questions (Question1 and Question2). If these questions have the same meaning and same answer, answer \"Yes\", otherwise \"No\".\nTeacher: Now, understand the problem? Solve this instance: Question1: Should I tell my friend I'm in love with him?, Question2: I'm in love with my best friend, should I tell him I love him?\nStudent:"
},
{
"from": "gpt",
"value": "Yes"
}
] |
[
{
"from": "human",
"value": "In 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.\n\n[Q]: Sentence: The secretary contacted the driver and asked him for a ride home.\n Profession: driver\n[A]: Male\n\n\n[Q]: Sentence: The teacher provided requirements to the developer and asked him if those would be possible to implement.\n Profession: developer\n[A]: Male\n\n\n[Q]: Sentence: The driver hit the clerk and refused to say sorry to her.\n Profession: clerk\n[A]:"
},
{
"from": "gpt",
"value": "Female\n\n\n"
}
] |
[
{
"from": "human",
"value": "Teacher: 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.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nSentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had not been in the store.\nSolution: Tom had been shopping for fruit to give Jon.\nReason: The given sentence is a good alteration. If the changed sentence was something like: \"Tom had been sleeping in his house in that time\", it'd contradict the first sentence. But this given sentence neither agrees with the first sentence, nor contradicts it.\n\nNow, solve this instance: Sentence 1: The girl loves her pink dress. Sentence 2: The girl hates dresses.\nStudent:"
},
{
"from": "gpt",
"value": "She got the dress from her parents for her birthday."
}
] |
[
{
"from": "human",
"value": "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.\nQ: Sentence1: Randy was out jogging one morning. Sentence2: Then suddenly, the world began to look different. Sentence3: He realized he had lost a contact lens. Sentence4: He went back to check and see if he could find it. Sentence5: Sadly, though, Randy's lens was gone for good.\nA: "
},
{
"from": "gpt",
"value": "Randy"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you will be shown a conversation and a question. You need to answer the question and choose the correct option based on the conversation. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\n\nM: Hey, Louise, where can I get some lunch around here? W: There are several places. What would you like to eat? M: I'd really like a cheeseburger and some French fries. W: Well, there's a coffee shop on the next corner. It serves good food. M: OK. I'll try it. Can I get you something? W: No, I think I'll come with you. I'm longing for a nice salad. M: Do you often have lunch at this coffee shop? W: No, I usually bring my lunch from home and eat at my desk., Question: Where does Louise suggest the man eat? (A) At a coffee shop. (B) At his house. (C) In her office.\n"
},
{
"from": "gpt",
"value": "(A) At a coffee shop."
}
] |
[
{
"from": "human",
"value": "In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: insult and non-insult. Insult is any lanugage or act that is disrespectful or scornfully abusive.\n\nLet me give you an example: Comment: your posts shows you are stupid period\nThe answer to this example can be: Insult\nHere is why: This comment is insult because it is scornful and disrespectful.\n\nOK. solve this:\nComment: There are plenty of immigrants from South America in Barcelona. They're not murdering people. Stop apologising for what is a global problem.\nAnswer:"
},
{
"from": "gpt",
"value": "Non-insult"
}
] |
[
{
"from": "human",
"value": "In this task, You are given an amazon food product review and its summary. Your task is to Generate \"True\" if given review and its summary match, otherwise generate \"False\".\nOne example: I have bought several of the Vitality canned dog food products and have found them all to be of good quality. The product looks more like a stew than a processed meat and it smells better. My Labrador is finicky and she appreciates this product better than most. \n Summary: Good Quality Dog Food\nSolution is here: True\nExplanation: The customer talked about dog food which was good. So, it's a correct Summary. So, the correct answer is true.\n\nNow, solve this: Everything you'd want from a Hot Chocolate...creamy, milky, tasty, makes you happy :) I can't wait to try the other flavors! \n Summary: delicious!\nSolution:"
},
{
"from": "gpt",
"value": "False"
}
] |
[
{
"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--------\nQuestion: 8, 11, ['3643', 'L', 'P', '4607', '2549', '153', 'U', 'F', 'c', 'w', '2029']\n\nAnswer: F, c, w, 2029\n\n\nQuestion: 11, 15, ['K', '5593', '6601', 'U', '9919', 'd', '9073', '5635', 'k', '479', '2617', '7471', '657', '309', '9691', '5963']\n\nAnswer: 2617, 7471, 657, 309, 9691\n\n\nQuestion: 4, 25, ['6215', '4629', 'd', 'y', '7109', '163', 'F', 'f', 'f', '2655', '1797', '5759', 'E', 'Y', 'f', 'E', 'S', '8639', 'h', 'r', '5197', '365', '8903', '4649', '8437']\n\nAnswer:"
},
{
"from": "gpt",
"value": "y, 7109, 163, F, f, f, 2655, 1797, 5759, E, Y, f, E, S, 8639, h, r, 5197, 365, 8903, 4649, 8437\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task you will be given a list of numbers. You should remove any number that is not an integer (whole number). If every number is not an whole number then an empty list (\"[]\") should be returned. Otherwise, answer with the list of whole numbers separated by comma inside brackets.\n\nExample Input: [-78.158, 76, -38.708, -37, -30.975, 20.752, -48, 14]\nExample Output: [76, -37, -48, 14]\n\nExample Input: [-68, 67, -17.412, 6.05, -53, -27, -0.289, 2.383]\nExample Output: [-68, 67, -53, -27]\n\nExample Input: [-9, -69]\nExample Output:"
},
{
"from": "gpt",
"value": "[-9, -69]\n\n"
}
] |
[
{
"from": "human",
"value": "instruction:\nIn this task, you're given a statement, the genre to which that statement belongs, and a label indicating if the statement should be agreed with (entailment), disagreed with (contradiction), or neither (neutral). Your job is to write a sentence that describes the genre that follows the tone with respect to the statement, as indicated by the label. If sentence X agrees with sentence Y, the can be concluded from one another. If sentence X disagrees with sentence Y, they can not be correct at the same time. The sentence must also belong to the genre specified.\nquestion:\nStatement: and i said you haven't heard about tornados how about bugs you know\nLabel: neutral.\nGenre: telephone.\nanswer:\nHave you heard about bugs or insects or cats or dogs?\n\n\nquestion:\nStatement: I am confident that fiscal year 2001 will be just as productive.\nLabel: neutral.\nGenre: government.\nanswer:\nFiscal year 2001 is guaranteed to be very productive.\n\n\nquestion:\nStatement: Handled in this way, the rates might turn out to be 17a and 23a.\nLabel: contradiction.\nGenre: government.\nanswer:\n"
},
{
"from": "gpt",
"value": "The rates will turn out to be 17a no matter what the circumstance.\n\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: You are given a sentence in Portuguese. Your job is to translate the Portuguese sentence into English.\nProblem:E quanto ao futuro?\nSolution:"
},
{
"from": "gpt",
"value": "What about the future?"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nGiven 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'.\nExample: 03:40:40 PM doesn't occur between 5:35:38 and 07:58:59 AM\nOutput: False\nThe output of 'False' is correct as the input statement is false, since 03:40:40 PM occurs after 07:58:89 AM and not between 5:35:38(AM) and 07:58:59 AM\n\nNew input case for you: 2:13:02 PM occurs between 05:24:40 PM and 09:28:18\nOutput:"
},
{
"from": "gpt",
"value": "True"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task you are given a list of integers and you need to find the absolute value of the difference between each two consecutive values. The output should be a list of the absolute value of the differences of each two consecutive values.\nTeacher: Now, understand the problem? Solve this instance: [30, 26, 80]\nStudent:"
},
{
"from": "gpt",
"value": "[4, 54]"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn this task, a passage will be given and the goal is to identify an event from the passage. An event is defined as a single word representing something that happened, is happening, or may happen. An event can be factual or hypothetical, positive or negative, certain or uncertain. While most events are based on verbs, an event can also be based on a noun (ex. storm, snow, rainfall) or a copula verb (is, was, been, etc.). The event must not be a pronoun or an adjective. For noun events with multiple words, use the last word in the phrase as event.\nExample: Passage: I submitted the hit. The hit was approved, and then I was paid.\nOutput: approved\nThere are three events in this passage (i) submission event (\"submitted\") (ii) the approval event (\"approved\"), and (iii) the payment event (\"paid\"). You can use any one of them as an output.\n\nNew input case for you: Passage: \"In these Games, we will carry out 1,200 urine tests and around 50 blood tests. We also carried out 86 pre-competition tests.\"\nOutput:"
},
{
"from": "gpt",
"value": "carry"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a pair of sentences, sentence 1 and sentence 2, that neither agree with nor contradict each other. Your job is to alter sentence 2 so that the pair clearly contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\n\nSentence 1: A group of men are playing ball together. Sentence 2: The men are playing basketball"
},
{
"from": "gpt",
"value": "The men play ball"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a context, a question, and three options. Your task is to find the correct answer to the question using the given context and options. Also, you may need to use commonsense reasoning about social situations to answer the questions. Classify your answers into 'A', 'B', and 'C'.\n\n[EX Q]: Context: Jordan is offered help on the project by their coworkers. Jordan has it under control and thanks them. \n Question: How would you describe Jordan? \n Options: (A) grateful for the offer but they don't need help (B) thankful for the offer but they can handle it (C) independent\n[EX A]: C\n\n[EX Q]: Context: Skylar loved all sports and loved going to the local bar to play pool. \n Question: How would you describe Skylar? \n Options: (A) their friend likes baseball (B) competitive (C) not competitive\n[EX A]: B\n\n[EX Q]: Context: Aubrey took Cameron's home and bulldozed it after winning the eminent domain case. \n Question: How would Cameron feel as a result? \n Options: (A) strong now (B) angry at being forced out of their home (C) skilled now\n[EX A]:"
},
{
"from": "gpt",
"value": "B\n\n"
}
] |
[
{
"from": "human",
"value": "You need to create a question containing a blank (_), based on the given context word. Your question must contain two persons --PersonX and PersonY. The expected answer to your question must be PersonX. PersonX and PersonY should not be equally likely to fill the blank. There should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people (e.g., Donald Trump, Putin, etc.) in your question. Avoid repeating the same style, pattern, or phrases in each question, try to increase diversity by varying sentence structure, blank placement, etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Person X and Person Y have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY.\nExample: Context word: upset.\nExample solution: PersonX yelled at PersonY because _ was so upset about the news.\nExample explanation: As expected, PersonX and PersonY are mentioned only once in the question. It contains only one blank. Also, the expected answer to this question is PersonX. So, it's a valid question.\n\nProblem: Context Word: cell phone.\n"
},
{
"from": "gpt",
"value": "Solution: PersonX got a new cell phone and showed it to PersonY because _ was happy about the new phone."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to collate all the alphabetical elements at the start of the list followed by all the numerical elements of the list. Maintain the order in which the alphabetical elements appear in the given input list, and do the same for the numerical elements.\nQ: ['6869', '4745', 'G', '7385', '559', '1395', '6017', 'e', '2629', '7743', 'Y', '9599']\nA:"
},
{
"from": "gpt",
"value": "G, e, Y, 6869, 4745, 7385, 559, 1395, 6017, 2629, 7743, 9599"
}
] |
[
{
"from": "human",
"value": "In this task, you are given inputs i and A, where i is an integer and A is a list. You need to list all the elements of A preceding the last i elements. i will always have a value less than the length of A.\nOne example is below.\nQ: 3, ['a', '34', 'f', '931', '7', '3432', '13245', '762']\nA: a, 34, f, 931, 7\nRationale: Here, all the elements except the last 3 from the list are 'a', '34', 'f', '931', and '7'.\nQ: 7, ['K', '2115', '2561', 'L', 'a', 'c', '7813', '6431', '7817', '2289', 'D', '6645', '9869', 'j', '8733', 'G', '4895', 't', '7465', 'x']\nA:"
},
{
"from": "gpt",
"value": "K, 2115, 2561, L, a, c, 7813, 6431, 7817, 2289, D, 6645, 9869"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you will be given sentences in which you have to recognize the name of the body cells. A cell is a mass of cytoplasm that is bound externally by a cell membrane. Usually microscopic in size, cells are the smallest structural units of living matter and compose all living things. Although there might be several correct answers, you need to write one of them.\nInput: Particularly Egr1 ( Fig . 6B ) and Egr2 ( Fig . 6C ) mRNA levels were almost identical when comparing neurons treated with BDNF alone and neurons with BDNF and ephrin - A5 together .\nOutput:"
},
{
"from": "gpt",
"value": "neurons"
}
] |
[
{
"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\nSentence: Indeed , the antiviral activity found in the serum and in the urine of infected piglets displayed the same main biological and antigenic properties as the IFN induced in influenza-infected pig leukocytes. \n Section: background"
},
{
"from": "gpt",
"value": "True"
}
] |
[
{
"from": "human",
"value": "Given a negotiation between two participants, answer 'Yes' if both participants agree to the deal, otherwise answer 'No'.\n\nTHEM: hello, may i have the hats and books and you can have the balls? YOU: i want one book to go with the balls THEM: okay deal, 1 book 3 balls for you, 1 book 2 hats for me."
},
{
"from": "gpt",
"value": "Yes"
}
] |
[
{
"from": "human",
"value": "Given a prompt and two completions from a language model, select the completion that is the most fluent with respect to continuing the prompt. Fluency is defined by coherency and ease of understanding, not necessarily grammatical correctness. Generate either Completion A or Completion B.\n\n[EX Q]: Prompt: Vic fuckin my old bitch nunu she acting like she didn't fuck \nCompletion A: niggas for real till I saw her dress like this niggas dress like a mary-knoll-wearing-the-g \nCompletion B: Robinson Climate Houston Oaks Pasadena/Arroyo C 15 interest featuring director Horacio Ceza, 21 epistame, socialists of grocery bank\n[EX A]: Completion A\n\n[EX Q]: Prompt: Bitch, I fucking hope you do. You'll be a dead \nCompletion A: -end job.Derek L. Bennett, M.D., M.-F.C., and Mary J. E. Brown, \nCompletion B: ringer for her in years to come. That's one more thing you won't be able to hide. You know it.\" \"O\n[EX A]: Completion B\n\n[EX Q]: Prompt: Real bitchxs dey lust em hatein niggas disgust em i see \nCompletion A: them nigga The reason why they hate dem is cause they can't relate ta them. Like, 'Cause all of a sudden these guys \nCompletion B: . She livin a life. She has friends niggas. Not gonna worry em, she ain't gonna give em a brea\n[EX A]:"
},
{
"from": "gpt",
"value": "Completion B\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given a post that is a real-life anecdote of a complex ethical situation and a question asks if AUTHOR, NOBODY, EVERYBODY, or OTHER is wrong in the situation. Answer the question and classify your answers into yes or no.\nQ: Is OTHER wrong in the post ? POST : Sorry for grammar mistakes im on mobile and English isnt my first language\n\nSo my Friend is 13 years old he wapes and smokes and wont go to school \n\nSo basically i try to explain to my Friend that he has to go to school and actualy come to classes \nor else he wont be able to get a good carrier\nBut he always just say no and that im an asshole\nAm i the asshole ???\nA:"
},
{
"from": "gpt",
"value": "yes"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. 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.\n\nSir Victor: Surrender , rogues . I have these outnumbered _ one _ to five .\nDuke Igthorn: Modest as ever , Victor .\nSir Victor: Sigmund ?\nToadwart: Yes , it 's Sigmund . Sigmund ?\n"
},
{
"from": "gpt",
"value": "PEOPLE"
}
] |
[
{
"from": "human",
"value": "Instructions: 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 (\", \").\nInput: Paragraph- Sent 1: As a husband, father and tenant of a Grand Rapids public housing complex, Aubrey Robertson puts security at the top of his home priority list.\nSent 2: Because of that, Robertson is all for a zero-tolerance drug law in force at Creston Plaza apartments on Grand Rapids' Northeast Side.\nSent 3: That includes cases in which families may be evicted for the drug use of a single family member, even off the premises.\nSent 4: Robertson sees it as a tool to keep his complex as clean and safe as possible.\nSent 5: \"If there's one person (using drugs), that is a start,\" said Robertson, 52, a native of Jamaica.\nSent 6: He has lived the past four years at Creston Plaza with his wife, Tammy, and his daughter, Precious, 3.\nSent 7: In recent months, Robertson was pleased to see casual drug use at the complex diminish with the installation of security cameras.\nSent 8: \"If there is a start, then there will be some other problem.\nSent 9: I totally agree (if there is a drug link), get them out.\"Sent 10: Critics say the law -- argued Tuesday before the U.S. Supreme Court -- tramples on individual rights and harms the very people public housing authorities are supposed to help.\nSent 11: \"It's basically one strike and you're out, and I think they went beyond what Congress intended,\" said Michael Chielens, executive director of Western Michigan Legal Services.\nSent 12: \"Someone who had no knowledge or involvement in a criminal act is being punished.\nSent 13: That's kind of a basic due process notion that we have had in our legal tradition for a long time.\"Sent 14: The case was brought by four Oakland, Calif., senior citizens, including 63-year-old great-grandmother Pearlie Rucker.\nSent 15: They received eviction notices because of the drug use of relatives or caregivers.\nSent 16: Rucker was ordered out because her mentally disabled daughter was caught with cocaine three blocks from the apartment she shared with her mother and other family members, court records show.\nSent 17: An appeals court blocked enforcement of the law.\nSent 18: At issue is whether housing directors are being more aggressive than Congress intended. \nQuestion: Why does the tenant of the Creston Plaza complex think the law is a valid one?.\nOutput:"
},
{
"from": "gpt",
"value": "1, 2, 4, 5, 6, 7, 8, 9."
}
] |
[
{
"from": "human",
"value": "Given a sentence in Dutch, generate a new Dutch sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\nExample: Je kunt een mandje gebruiken om de prullenbak te vervangen.\nExample solution: Je kunt een mand gebruiken om afval weg te gooien.\nExample explanation: This is a good change in the input, because it is semantically similar to the input as both are talking about using a basket to through trash/garbage and the output sentence follows the commonsense knowledge.\n\nProblem: De paradox van naar school gaan is het vertrouwen in de regels van de samenleving.\n"
},
{
"from": "gpt",
"value": "Solution: De stijl van naar school gaan is om de regels van de samenleving bij te wonen."
}
] |
[
{
"from": "human",
"value": "Based on the given context, craft a common-sense question, especially those that are LONG, INTERESTING, and COMPLEX. The goal is to write questions that are easy for humans and hard for AI machines! To create such questions, here are some suggestions: A. What may (or may not) be the plausible reason for an event? B. What may (or may not) happen before (or after, or during) an event? C. What may (or may not) be a plausible fact about someone (or something)? D. What may (or may not) happen if an event happens (or did not happen)? You can also create other types of questions. DO NOT make your question answerable without looking at the context, or question of which the correct answer can be directly extracted from the context. DO NOT ask a question that requires very specialized knowledge that is not common sense. DO NOT ask too simple or too short questions. Your question must be related to the context and answerable with common sense. Try to add more variations and complexity to the questions.\n\n[EX Q]: Context: My mum went to her place after buka puasa and she slept while Aunty Sim was doing facial on mum face . Mum fell asleep so once aunty sim done with her face she left mum to sleep somemore and made chocolate muffins . It took her 15 minutes to make and mix and 20 minute to bake . So fast and easy and damn yummy !.\n[EX A]: Why did they go to the Aunt 's house ?\n\n[EX Q]: Context: Bake in the preheated oven for 35 minutes , or until a toothpick inserted into the center of the cake comes out clean . Cool for 10 minutes on a cooling rack , then unmold cake . Cool completely before serving . Store in an airtight container once cooled .\n[EX A]: What type of cuisine is the narrator teaching ?\n\n[EX Q]: Context: I just love this picture , i think i might make it greyscale , blow it up and frame it . It will go great with my cabin theme and i think it will make a really interesting piece ! All in all , the weekend was fun , relaxing and memorable . Unfortunately , it all had to come to an end , and not a very good one !.\n[EX A]:"
},
{
"from": "gpt",
"value": "What type of theme is the narrator going for ?\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task you will be given a list of integers. For every element in the list, if the element is even you should divide by two, if the element is odd you should multiply by three then add one. The output should be a list of integers that is the result of applying that logic to the input list.\nProblem:[35, 172, 197, 132, 124]\nSolution:"
},
{
"from": "gpt",
"value": "[106, 86, 592, 66, 62]"
}
] |
[
{
"from": "human",
"value": "Definition: In this task, you are given one english sentence. The major part of the sentences talk about health-related topics, but some of the them describe an organization and its activities. Your job is to translate the given sentences into German.\nInput: Nosocomial infection\nOutput:"
},
{
"from": "gpt",
"value": "Nosokomiale Infektion"
}
] |
[
{
"from": "human",
"value": "You need to create a question containing a blank (_), based on the given context word. Your question must contain two persons --PersonX and PersonY. The expected answer to your question must be PersonX. PersonX and PersonY should not be equally likely to fill the blank. There should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people (e.g., Donald Trump, Putin, etc.) in your question. Avoid repeating the same style, pattern, or phrases in each question, try to increase diversity by varying sentence structure, blank placement, etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Person X and Person Y have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY.\nOne example: Context word: upset.\nSolution is here: PersonX yelled at PersonY because _ was so upset about the news.\nExplanation: As expected, PersonX and PersonY are mentioned only once in the question. It contains only one blank. Also, the expected answer to this question is PersonX. So, it's a valid question.\n\nNow, solve this: Context Word: trout.\nSolution:"
},
{
"from": "gpt",
"value": "Trout was something that PersonX loved to eat but not PersonY, so _ ordered the trout almondine for their entree."
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nIn this task, you need to answer the given multiple-choice question on the physics. Classify your answers into 'a', 'b', 'c', 'd', and 'e'.\nPart 2. Example\nProblem: walking at 5 / 6 th of its usual speed a cab is 15 mnts late . find its usual time to cover the journey ? \nOptions: a ) 25 m , b ) 45 m , c ) 32 m , d ) 75 m , e ) 62 m\nAnswer: d\nExplanation: New speed = 5 / 6 th of usual speed new time = 6 / 5 th of usual time 6 / 5 ut - ut = 15 m ut / 5 = 15 m ut = 75 m answer is d\nPart 3. Exercise\nProblem: donovan and michael are racing around a circular 600 - meter track . if donovan runs each lap in 45 seconds and michael runs each lap in 40 seconds , how many laps will michael have to complete in order to pass donovan , assuming they start at the same time ? \nOptions: a ) 8 , b ) 7 , c ) 9 , d ) 6 , e ) 5\nAnswer:"
},
{
"from": "gpt",
"value": "c"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you're given a context, a sentence, and a character. The sentence describes an action or job of the given character. Also, the context provides more information about the sentence or the character. Your task is to return one of the emotions which are expressed by the Character in the given sentence. For that you can use the Context; however, Context is not provided in all the inputs. Also, in some inputs, there can be zero emotion; for that return 'None'.\nSee one example below:\nProblem: Context: A cook was carrying an armful of oranged in the kitchen. \n Sentence: He dropped one on the floor by accident. \n Character: Cook\nSolution: annoyed\nExplanation: The cook dropped one orange on the floor, so, he must feel annoyed at that time.\n\nProblem: Context: Beth had been throwing up for 3 days from the flu. She argued with her mother when she insisted going to the ER. \n Sentence: She finally admitted she needed help. \n Character: Beth\nSolution:"
},
{
"from": "gpt",
"value": "nervous"
}
] |
[
{
"from": "human",
"value": "In this task, you must classify if a given review is positive/negative, indicating your answer as P or N.\n\nExample input: plot : two teen couples go to a church party , drink and then drive .\nthey get into an accident .\none of the guys dies , but his girlfriend continues to see him in her life , and has nightmares .\nwhat 's the deal ?\nwatch the movie and \" sorta \" find out . . .\ncritique : a mind - fuck movie for the teen generation that touches on a very cool idea , but presents it in a very bad package .\nwhich is what makes this review an even harder one to write , since i generally applaud films which attempt to break the mold , mess with your head and such ( lost highway & memento ) , but there are good and bad ways of making all types of films , and these folks just did n't snag this one correctly\n.\nthey seem to have taken this pretty neat concept , but executed it terribly .\nso what are the problems with the movie ?\nwell , its main problem is that it 's simply too jumbled\n.\nit starts off \" normal \" but then downshifts into this \" fantasy \" world in which you , as an audience member ,\nhave no idea what 's going on\n.\nthere are dreams , there are characters coming back from the dead , there are others who look like the dead , there are strange apparitions , there are disappearances , there are a looooot of chase scenes , there are tons of weird things that happen , and most of it is simply not explained .\nnow i personally do n't mind trying to unravel a film every now and then , but when all it does is give me the same clue over and over again , i get kind of fed up after a while , which is this film 's biggest problem .\nit 's obviously got this big secret to hide , but it seems to want to hide it completely until its final five minutes .\nand do they make things entertaining , thrilling or even engaging , in the meantime ?\nnot really .\nthe sad part is that the arrow and i both dig on flicks like this , so we actually figured most of it out by the half - way point , so all of the strangeness after that did start to make a little bit of sense , but it still did n't the make the film all that more entertaining .\ni guess the bottom line with movies like this is that you should always make sure that the audience is \" into it \" even before they are given the secret password to enter your world of understanding .\ni mean , showing melissa sagemiller running away from visions for about 20 minutes throughout the movie is just plain lazy ! !\nokay , we get it .\n. .\nthere are people chasing her and we do n't know who they are .\ndo we really need to see it over and over again ?\nhow about giving us different scenes offering further insight into all of the strangeness going down in the movie ?\napparently , the studio took this film away from its director and chopped it up themselves , and it shows .\nthere might 've been a pretty decent teen mind - fuck movie in here somewhere , but i guess \" the suits \" decided that turning it into a music video with little edge , would make more sense .\nthe actors are pretty good for the most part , although wes bentley just seemed to be playing the exact same character that he did in american beauty , only in a new neighborhood .\nbut my biggest kudos go out to sagemiller , who holds her own throughout the entire film , and actually has you feeling her character 's unraveling .\noverall , the film does n't stick\nbecause it does n't entertain , it 's confusing , it rarely excites and\nit feels pretty redundant for most of its runtime , despite a pretty cool ending and explanation to all of the craziness that came before it .\noh ,\nand by the way , this is not a horror or teen slasher flick . . .\nit 's just packaged to look that way because someone is apparently assuming that the genre is still hot with the kids .\nit also wrapped production two years ago and has been sitting on the shelves ever since .\nwhatever . .\n. skip it !\nwhere 's joblo coming from ?\na nightmare of elm street 3 ( 7/10 ) - blair witch 2 ( 7/10 ) - the crow ( 9/10 ) - the crow : salvation ( 4/10 )\n- lost highway ( 10/10 ) - memento ( 10/10 ) - the others ( 9/10 ) - stir of echoes ( 8/10 )\nExample output: N\nExample explanation: The phrases used in the review convey a negative sentiment (e.g. \"presents it in a very bad package\").\nQ: dreamworks pictures presents a jinks/ cohen company production kevin spacey annette bening \" american beauty \" thora birch allison janney peter gallagher mena suvari wes bentley and chris cooper co - producers stan wlodkowski alan ball music by thomas newman costume designer julie weiss\nfilm editor tariq anway chris greenbury production designer naomi shohan director of photography conrad\nl . hall , a .\ns .\nc .\nproduced by bruce cohen & dan jinks written by alan ball directed by sam mendes\n\" both my wife and daughter think i 'm this gigantic loser .\nand they 're right .\ni have lost something .\ni did n't always feel this sedated .\n\" with that piece of dialogue , we are fully introduced to lester burnham ( kevin spacey ) , a 42 year old man trapped within his own life .\nlester works for an advertising agency .\nhis growing dissatisfaction with his job is only one of the mid - life crisis he is suffering .\nestranged from both his wife and his daughter , lester starts to crack under the stress .\nhis life becomes nothing more than a series of mastubatory fantasies , and sullen apathy .\ncarolyn burnham ( annette bening ) , is the prototypical career woman/ homemaker .\nshe carefully tends her rose garden , decorates her home with the best furnishings .\nbut inside she is desperate .\nunsuccessful at her profession as a real estate agent , she drives herself into states of denial and self loathing that only feed her growing resentment towards her family .\nthe third member of this anti - family is jane burnham ( thora birch ) , lester and carolyn 's daughter .\na young girl going through the typical stages of adolescence , but having to also come to terms with her families growing dysfunction .\nthis funny ( and frightening ) slice of life is refreshingly simple .\nnot one character is given less than is needed to identify him or her .\nsome of the most telling characters are those that serve to highlight other characters .\nmost notably is barbara fitts ( allison janney ) , the almost catatonic wife of retired marine colonel fitts .\nshe has almost no dialogue , and seems to be either recovering from a stroke or suffering from one .\ncolonel fitts ( chris cooper ) is an angry and frightened man .\nhis rage directed almost singularly at his son , ricky ( wes bentley ) who has just moved with his family to the same neighborhood as the burnham 's .\nin fact they are the next door neighbors .\nanymore detail into the personalities of these marvelously diverse characters would deprive one of the many pleasures and surprises to be had in \" american beauty \" .\nalan ball , who was the co - executive producer of the hit tv series \" cybil \" and creator of the new sitcom\n\" oh grow up \" , has fashioned one of the most insightful and expertly tuned screenplays to have hit the screen in the past ten years . not one character in this film rings falsely .\nand the depth of personality in each , is achingly honest and insightful .\nthe plot detailing the last year in the life of a man as he tries to find his own self worth is so resoundingly cliched and at the same time original as to bring to mind such marvelous film work as \" the graduate \" or \" lolita \" .\nkevin spacey turns in one of this years most pragmatic performances .\nhis lester burnham is an everyman caught up in the middle of a life that is spiraling into old age .\nfinally unable to deal with the lost soul that he has become , lester tries to return to his youth .\nhe quits his job ( actually blackmailing his employer for one year 's salary ) , starts smoking pot , fantasizes about his daughter 's girlfriend angela ( mena suvari , in a marvelous performance here ) , starts working out , and finally takes a job at the local fast food outlet .\nmr .\nspacey 's performance is so remarkably subtle and ingenuous , that we can be certain that come oscar ? time ,\nwe can be assured to see him name among the five nominees .\nannette bening also turns in what may be the best performance of her career .\ncarolyn burnham is a woman who has become so insecure as to be caught up in maintaining the facade of normalcy . unable to cope with her growing disillusionment , she forces herself to maintain her demeanor , driving her further and further into desperation , adultery and possibly murder .\nms .\nbening makes the character of carolyn so compelling as to be identifiable to almost anyone .\nthe slow and methodical turn from happy home maker to charnel house martha stewart is too frightening to express in words .\nthora birch holds her own against the talents cast with her .\njane burnham is both an innocent girl caught up in what is a dysfunctional family , and a rebellious child ready to abandon them at any moment .\nher growing distrust and isolation from her family is something that many parents should view as a warning .\nshe is the prototypical trophy child .\nwhen carolyn praises her daughter after a performance by her cheerleading team ( \" i 'm so proud of you , honey .\nyou did n't screw up once ! \" ) , the bitterness and resentment are palpable .\nthora birch is a young actress to watch\n. praise must also go to chris cooper who brings yet another angry father role to life with depth and resonance .\ncolonel finn is a man in complete denial .\nhis military upbringing masking a desire he is too repulsed to even comprehend .\nwes bentley as ricky finn is fine as the enigma .\nthe boy next door who may be more foe than friend .\na deceitful and calculating young man , whose voyeuristic proclivities mask a deeper and more profound understanding of life than any of the adults around him .\nmr .\nbentley 's performance is the one troublesome note in the film .\nthat is simply because the character is such a grand and complete liar , that one almost faults the performance for it .\ndirector sam mendes handles all of the particulars of the cast and the settings with a sure and composed style that is neither intrusive nor subtle .\nscenes of carolyn walking through the rain , carry an ominous fission that calls attention to the emotions of the character .\nthe subtle cinematography by conrad hall is wonderful , capturing the season in all of it 's harsh beauty\n( fall has never looked so inviting , yet depressing ) .\nevery nuance of \" american beauty \" begs it 's audience to think and examine .\nit is a film that will be discussed and debated for years to come .\nand well it should , as\nit is simply one of this years best .\nA:"
},
{
"from": "gpt",
"value": "P"
}
] |
[
{
"from": "human",
"value": "You are given an open-domain question from an open movie database. Your task is to provide an answer to that question. Try to only include the answer. Do not put it in a sentence.\n\nLet me give you an example: what kind of film is Best Seller?\nThe answer to this example can be: crime\nHere is why: The answer is correct because crime genre movie is among best seller.\n\nOK. solve this:\nwhat movies was David A.R. White an actor in?\nAnswer:"
},
{
"from": "gpt",
"value": "God's Not Dead, Jerusalem Countdown, Bells of Innocence, Mercy Streets, The Moment After"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a context sentence containing a blank (_). You are expected to fill the blank with one word to make the sentence convey a cultural stereotype. A stereotype is an over-generalized belief about a particular group of people. Your answer must not contain more than one word.\nQ: Context: The entrepreneur is _ because he wants to make as much money as possible.\nA: "
},
{
"from": "gpt",
"value": "greedy"
}
] |
[
{
"from": "human",
"value": "Given a sentence, fill out the missing word with a 'no' or a number (between zero and ten). You should write the numbers with english alphabet, like: four instead of 4.\n\nInput: Consider Input: Cellulose contains nothing that is considered hazardous, and carries ____ hazardous warning messages.\n\nOutput: no\n\n\nInput: Consider Input: Human malaria is caused by ____ species of Plasmodium . .\n\nOutput: four\n\n\nInput: Consider Input: Most plants develop into small bushes with up to ____ basal stems.\n\n"
},
{
"from": "gpt",
"value": "Output: six\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a second sentence. Your task is to generate the first sentence on the same topic but incoherent and inconsistent with the second sentence.\n\nHowever , Sarno manages to shoot and cripple the already wounded Parker and Longbaugh , and then calls for an ambulance ."
},
{
"from": "gpt",
"value": "All of Sarno 's men are killed in the ensuing firefight ."
}
] |
[
{
"from": "human",
"value": "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.\n\nInput: Consider Input: You will do great :)\n\nOutput: no\n\n\nInput: Consider Input: Oh hell no .\n\nOutput: no\n\n\nInput: Consider Input: Tell them you quit to focus on school .\n\n"
},
{
"from": "gpt",
"value": "Output: yes\n\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given a hateful post in English from online platforms. You are expected to classify the target being harassed in the post as individual or generic, i.e., single person or a group of people. Note that the URLs in the text have been replaced with [Link].\nQ: Post: and the rest are staying, raping our daughters and welfare system and creating a caliphate. They will never return as they were never refugees as we all knew when they streamed in, as they are still doing. Really hope peace returns to all of Syria. Great to see. [Link]\nA:"
},
{
"from": "gpt",
"value": "Generic"
}
] |
[
{
"from": "human",
"value": "Q: In this task, positions of two consecutive words have been swapped. You need to output the position of the swaped words. e.g. in the sentence 'Seattle has nice a weather', the word 'a' and 'nice' have been swapped. These words are at 3rd and 4th position respectively. So, the output should be (3, 4). Note that the index of first word is 1.\na group women of play a game of soccer\nA:"
},
{
"from": "gpt",
"value": "(3, 4)"
}
] |
[
{
"from": "human",
"value": "In this task, you are given inputs k, i, and A, where k and i are integers and A is a list. You need to find every ith element of A starting from the kth element. The process stops when the position of the next ith element exceeds the length of the list.\nOne example: 2, 3, ['a', '34', 'f', '931', '7', '3432', '13245', '762']\nSolution is here: 34, 7, 762\nExplanation: Here, starting from 2nd element every 3rd element from the list are '34', '7', and '762'.\n\nNow, solve this: 1, 2, ['4833', 'D', 'j', 'M', 'O', 'p', 'l']\nSolution:"
},
{
"from": "gpt",
"value": "4833, j, O, l"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task, you are given a context paragraph, a question based on that and corresponding answer of a question. Your task is to generate supporting fact/knowledge from context paragraph which helps in answering a given question.\nTeacher: Now, understand the problem? Solve this instance: The relations between Switzerland and the European Union (EU) are framed by a series of bilateral treaties whereby the Swiss Confederation has adopted various provisions of European Union law in order to participate in the Union's single market. All but one (the microstate Liechtenstein) of Switzerland's neighbouring countries are EU member states. Question: Which non-EU microstate is a neighbour of the country which held an immigration referendum in February 2014? Answer: Liechtenstein\nStudent:"
},
{
"from": "gpt",
"value": " All but one the microstate Liechtenstein of Switzerlands neighbouring countries are EU member states."
}
] |
[
{
"from": "human",
"value": "In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the numerical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no numerical element is in the list.\nQ: ['2419', '6413', 'T', '7123', 'L', '8769', '6913', '2223', 'E', 'U', 'y', 'O', 'O', 'z', '4923', 's', '7787', 'X', 'v', '4697', 'L', 'N', '9063', 't', 'I', 'T', '2159', 'X', 'k', 'L', 'A', '9743', 'X', '953', '9123', '1739', '221']\nA: "
},
{
"from": "gpt",
"value": "1, 2, 4, 6, 7, 8, 15, 17, 20, 23, 27, 32, 34, 35, 36, 37"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a review from Amazon's food products. Your task is to generate a short summary of the given review in the input. Note that you don't need to write a complete sentence as a summary.\nQ: This batch was horrible. Since most regular coffee were out of stock, I tried this one. It tastes and smells awful. Do not buy this flavor.\nA: "
},
{
"from": "gpt",
"value": "Awful smell and taste."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given a question. Your task is to generate an answer that is relevant to the question.\nProblem:Would you like to get together sometime?\nSolution:"
},
{
"from": "gpt",
"value": "I can meet for breakfast any day this week."
}
] |
[
{
"from": "human",
"value": "In this task, you will be shown a short story with a beginning, two potential middles, and an ending. Your job is to choose the middle statement that makes the story coherent / plausible by writing \"1\" or \"2\" in the output. If both sentences are plausible, pick the one that makes most sense.\n\nExample Input: Beginning: My brother came home dirty from his football game. Middle 1: He put it in the closet. Middle 2: He put it in the washing machine. Ending: On his next game he had a clean uniform.\nExample Output: 2\n\nExample Input: Beginning: Jake sprained his ankle while playing soccer. Middle 1: Jake realized their ankle was broken. Middle 2: Jake thought his ankle was broken. Ending: Jake sighed in relief.\nExample Output: 2\n\nExample Input: Beginning: Sam bought a lottery ticket. Middle 1: Sam saved all his father's money. Middle 2: Sam blew all his money. Ending: Sam was heart broken.\nExample Output:"
},
{
"from": "gpt",
"value": "2\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given an ambiguous question/query (which can be answered in more than one way) and a clarification statement to understand the query more precisely. Your task to classify that if the given clarification accurately clarifies the given query or not and based on that provide 'Yes' or 'No'.\n\nQ: Query: figs \n Clarification: are you looking for a flowering ivy\n\nA: No\n****\nQ: Query: Tell me more about indiana state fairgrounds. \n Clarification: do you want to know about the tennessee titans\n\nA: No\n****\nQ: Query: Tell me about the pacific northwest laboratory. \n Clarification: do you want to watch funny penguin videos\n\nA:"
},
{
"from": "gpt",
"value": "No\n****\n"
}
] |
[
{
"from": "human",
"value": "In this task, you're given four sentences of a story written in natural language. The given story is not complete and your job is to complete the story by selecting one of the end sentence choices from (A) and (B), such that the story does not sound complete and coherent, i.e., select an incorrect end sentence.\n\nExample input: Sentence1: Rick grew up in a troubled household. Sentence2: He never found good support in family, and turned to gangs. Sentence3: It wasn't long before Rick got shot in a robbery. Sentence4: The incident caused him to turn a new leaf. \n (A) He is happy now. (B) He joined a gang.\nExample output: B\nExample explanation: As mentioned in fourth sentence, the incident turned a new leaf to Rick's life; so, he must be happy now. Also, he was previously in gang, so, this incident cannot make him to join a gang. So, B is incorrect.\nQ: Sentence1: Sally was on her work break. Sentence2: She went to get tacos from the taco stand outside. Sentence3: She realized she had forgotten her wallet at home. Sentence4: A nice man noticed what happened and offered to pay. \n (A) Sally was grateful for his kindness. (B) Sally cried the rest of her break.\nA:"
},
{
"from": "gpt",
"value": "B"
}
] |
[
{
"from": "human",
"value": "You are given an original reference as well as a system reference. Your task is to judge the quality of the system reference. If the utterance is grammatically correct and fluent output 1, else output 0.\n\nExample input: System Reference: there is a chinese restaurant on x called x.\nOriginal Reference: x is a chinese restaurant in x.\nExample output: 1\nExample explanation: The system reference is grammatically correct and fluent.\nQ: System Reference: x is a chinese restaurant in the city centre and riverside area near x.\nOriginal Reference: x is a chinese restaurant in the city centre and riverside areas near x.\nA:"
},
{
"from": "gpt",
"value": "1"
}
] |
[
{
"from": "human",
"value": "Given a scientific question, generate an incorrect answer to the given question. The incorrect answer should be a plausible alternative to the correct answer. The answer should be some other item belonging to the same category as the correct answer but should be incorrect.\n\nExample Input: What is one function of the nervous system in humans?\nExample Output: controlling emotion\n\nExample Input: Which region is just posterior to the mouth?\nExample Output: the esophagus\n\nExample Input: What bond is a force of attraction between ions and atoms?\nExample Output:"
},
{
"from": "gpt",
"value": "carbon bond\n\n"
}
] |
[
{
"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'\nOne example: The man then paints a side table black with lights shining off of the black painted wood.\nSolution is here: Yes\nExplanation: Here the man is in motion as he is painting a side table black table.\n\nNow, solve this: When he stepped from a stone to Johnnie's head Daddy Longlegs had No idea that he was not walking on another stone.\nSolution:"
},
{
"from": "gpt",
"value": "No"
}
] |
[
{
"from": "human",
"value": "Teacher:The task is to write a full sentence or two using all of the information given. The sentence(s) will be a brief review of a restaurant. Use all of the information provided.\nTeacher: Now, understand the problem? Solve this instance: name[xname], recommend[yes], cuisine[New American], decor[bad], qual[good], location[Manhattan], price[expensive]\nStudent:"
},
{
"from": "gpt",
"value": "xname is the best restaurant because it is pricey with bad decor pal, but it offers good food though. It is in Manhattan. xname is a New American place."
}
] |
[
{
"from": "human",
"value": "Instructions: You are given a short text as a title. Your task is to generate a poem as output that is related to the given title and should feel like written by kids. The output should be a run-on sentence (two or more complete sentences connected without any punctuation). The poem should not be too long or too complex, because it should feel like it is written by younger person without high level of literature education.\nInput: RED\nOutput:"
},
{
"from": "gpt",
"value": "red of an apple red be in a tree red be not the same of the blue ocean breeze"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task, you need to reverse the order of words in the given sentence.\nTeacher: Now, understand the problem? Solve this instance: Sentence: a man riding some skis down a snowy trail\nStudent:"
},
{
"from": "gpt",
"value": "trail snowy a down skis some riding man a"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given a short passage that may convey stereotype, anti-stereotype, or is unrelated. A stereotype is an over-generalized belief about a particular group of people. An anti-stereotype is an idea that goes against a common stereotype. The passage is unrelated if it does not convey a stereotype or anti-stereotype. You are expected to classify the passage into three classes: stereotype, anti-stereotype, and unrelated.\nProblem:Passage: My favorite college course was taught by a chemist. Her presentations were hilarious; she had a great sense of humor.\nSolution:"
},
{
"from": "gpt",
"value": "Anti-stereotype"
}
] |
[
{
"from": "human",
"value": "You will be given a context, a subject and a relation. Your task is to generate a question based on the subject and relation. The generated question should include the given subject. Try to use a minimum number of words that are not present in either context, subject or relation while generating question.\n\nContext : Elias Durnford died from yellow fever on 21 June 1794 while on the island of Tobago. \nSubject : Elias Durnford \nRelation : occupation"
},
{
"from": "gpt",
"value": "What was Elias Durnford's occupation?"
}
] |
[
{
"from": "human",
"value": "Given a command in a limited form of natural language, provide the correct sequence of actions that executes the command to thus navigate an agent in its environment. A command can be broken down into many different actions. Actions are uppercase and are individual steps that serve as the building blocks for a command. For commands, 'left' and 'right' are used to denote the direction of an action. The word 'opposite' turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. Actions and commands do not have quotations in the input and output.\n\n[Q]: jump twice after jump right thrice\n[A]: I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_JUMP I_JUMP\n\n\n[Q]: jump left thrice and run thrice\n[A]: I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_RUN I_RUN I_RUN\n\n\n[Q]: jump right twice after turn left twice\n[A]:"
},
{
"from": "gpt",
"value": "I_TURN_LEFT I_TURN_LEFT I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP\n\n\n"
}
] |
[
{
"from": "human",
"value": "Definition: 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\".\nInput: Donald spent a lot of time jumping rope on the playground but Samuel did not because _ had very little energy. (A) Donald (B) Samuel\nOutput:"
},
{
"from": "gpt",
"value": "B"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given a sentence from the research paper and the category to which it belongs. Your task is to classify whether the given category is correct or not by providing \"True\" and \"False\", respectively. Here are the definitions for the categories: Background (Why is this problem important? What relevant works have been created before? What is still missing in the previous works? What are the high-level research questions? How might this help other research or researchers?), Purpose (What specific things do the researchers want to do? What specific knowledge do the researchers want to gain? What specific hypothesis do the researchers want to test?), Method (How did the researchers do the work or find what they sought? What are the procedures and steps of the research?), or Finding (What did the researchers find out? Did the proposed methods work? Did the thing behave as the researchers expected?). \",\nQ: Sentence: expanding the spectrum of viruses inhibited by IFITM proteins. \n Section: finding\nA:"
},
{
"from": "gpt",
"value": "True"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nGiven a sentence in Somali language, translate the sentence to English language keeping the meaning of the original sentence intact\n\nSomali sentence: Ceeb aad on iyo waxaad caabudaysaan oo Eebe ka soo!\nOutput:"
},
{
"from": "gpt",
"value": "Shame on you and that you worship, other than Allah!"
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: In this task you are given a sentence. You must judge whether there exist two consecutive words within the sentence with flipped orders, that is, whether the sentence will make sense and be correct if the order of two consecutive words changes. Label the instances as \"Inversion\" or \"Original\" based on your judgment.\nPROBLEM: I lay my head MacKenzie on stomach and Chloe lays hers on mine.\n\nSOLUTION: Inversion\n\nPROBLEM: Looking at Nick now, he'd very changed little.\n\nSOLUTION: Inversion\n\nPROBLEM: Jessica slipped her hand between mine and tugged.\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "Original\n\n"
}
] |
[
{
"from": "human",
"value": "In this task the focus is on physical knowledge about the world. Given the provided goal task in the input, describe a process that would lead to the asked outcome. This process often involves physical motions with objects, such as moving them, arranging them in a certain way, mixing them, shaking them, etc. \n\nHow do I make a PB&J?\nTake bread, spread peanut butter on one side and jelly on the other, then place spread sides together.\n\nReduce amount of time cook steak.\nSet at room temperature for 20 minutes before cooking.\n\nHow to attach a necklace when you've lost your clasp?\n"
},
{
"from": "gpt",
"value": "use a paper clip to secure the two ends together\n\n"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task, you have given an input which is user's command or question, based on that you have to return what will be Agent's response/reply for that particular user's command or question\nTeacher: Now, understand the problem? Solve this instance: You got it!\nStudent:"
},
{
"from": "gpt",
"value": "I've changed \"oil change\" to be for 1 hour."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you will be shown a conversation and a question. You need to answer the question and choose the correct option based on the conversation. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\nSee one example below:\nProblem: M: I am considering dropping my dancing class. I am not making any progress. W: If I were you, I stick with it. It's definitely worth time and effort., Question: What does the man suggest the woman do? (A) Consult her dancing teacher. (B) Take a more interesting class. (C) Continue her dancing class.\nSolution: (C) Continue her dancing class.\nExplanation: This is a good example. Based on the conversation, we could understand that only option (C) is correct.\n\nProblem: M: When are you leaving? W: I'm leaving on Sunday night. M: What's your schedule? W: I arrive in Wellington on Monday, attend a conference there on Tuesday, and leave for Brisbane early Wednesday morning. M: How long will you stay there? W: I'll see our new agent Mr. Graig there on Thursday. I'm free on Friday, but I'm catching the 10 o'clock plane on Saturday to go to the fair in Sydney. M: You've got a full schedule., Question: When will the woman leave for Brisbane? (A) On Monday. (B) On Tuesday. (C) On Wednesday.\nSolution:"
},
{
"from": "gpt",
"value": "(C) On Wednesday."
}
] |
[
{
"from": "human",
"value": "In this task, you're given a context, a sentence, and a character. The sentence describes an action or job of the given character. Also, the context provides more information about the sentence or the character. Your task is to return one of the emotions which are expressed by the Character in the given sentence. For that you can use the Context; however, Context is not provided in all the inputs. Also, in some inputs, there can be zero emotion; for that return 'None'.\nOne example is below.\nQ: Context: A cook was carrying an armful of oranged in the kitchen. \n Sentence: He dropped one on the floor by accident. \n Character: Cook\nA: annoyed\nRationale: The cook dropped one orange on the floor, so, he must feel annoyed at that time.\nQ: Context: In 1982, my coworkers Tommy and Barbara dated. They ended up in a relationship. \n Sentence: One day they had a fight in the office. \n Character: I (myself)\nA:"
},
{
"from": "gpt",
"value": "alarmed"
}
] |
[
{
"from": "human",
"value": "Definition: Given a sentence in German, generate a new German sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\nInput: Sie werden wahrscheinlich einen Artikel in einem Kurs in der Zeitung finden.\nOutput:"
},
{
"from": "gpt",
"value": "Sie werden wahrscheinlich einen Artikel in einer Zeitung in der Zeitung finden."
}
] |
[
{
"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 shown a conversation. You need to write a question with three choices for the conversation. Your question should be answerable based on the conversation and only have one correct answer. Note that you don't need to answer your question. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\n\nW: The movie next Tuesday has been cancelled due to lack of interest. M: What do you mean? W: Well, by last night only a few tickets has been sold.\nSolution: What can we conclude about the movie? (A) They want to buy the tickets for the movie. (B) The tickets for the movie were sold. (C) The movie will not be shown.\nWhy? This is a good example. Based on the conversation, the movie has been canceled, and it will not be shown. We could understand that only option (C) is correct. As mentioned in the conversation, only a few tickets have been sold, so option (B) is incorrect. We don't know if they wanted to buy a ticket or not, so option (A) is incorrect as well.\n\nNew input: W: Do you like your apple? M: Yes. It's nice and sweet. Is yours sweet, too? W: No. Mine is rather sour. M: Oh, I'm sorry about that.\nSolution:"
},
{
"from": "gpt",
"value": "What is the taste of the woman's apple? (A) It is nice and sweet. (B) It looks nice but tastes sour. (C) It is rather sour."
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nTurn the given fact into a question by a simple rearrangement of words. This typically involves replacing some part of the given fact with a WH word. For example, replacing the subject of the provided fact with the word \"what\" can form a valid question. Don't be creative! You just need to rearrange the words to turn the fact into a question - easy! Don't just randomly remove a word from the given fact to form a question. Remember that your question must evaluate scientific understanding. Pick a word or a phrase in the given fact to be the correct answer, then make the rest of the question. You can also form a question without any WH words. For example, \"A radio converts electricity into?\"\n\nFact: goats conserve body heat with their hair or fur.\nOutput:"
},
{
"from": "gpt",
"value": "what conserves body heat with their hair or fur?"
}
] |
[
{
"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\n1, 4, ['7669', '7377', '8311', '1525', 'l', 'Y', 'U', 'q', 'X', '2077', 'L', 's', 'H', 'S', '4303', '8085', '2215', 's']"
},
{
"from": "gpt",
"value": "7669, 7377, 8311, 1525"
}
] |
[
{
"from": "human",
"value": "Q: In this task you will be given a list of integers. A list contains numbers separated by a comma. You need to round every integer to the closest power of 2. A power of 2 is a number in the form '2^n', it is a number that is the result of multiplying by 2 n times. The following are all powers of 2, '2, 4, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096'. If an integer is exactly in equally far from two different powers of 2 then you should output the larger power of 2. The output should be a list of integers that is the result of rounding each integer int the input list to the closest power of 2. The output should include a '[' to denote the start of the output list and ']' to denote the end of the output list.\n[174, 636, 2778, 1480, 7, 42, 2, 57]\nA:"
},
{
"from": "gpt",
"value": "[128, 512, 2048, 1024, 8, 32, 2, 64]"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task you will be given a string of characters. You should remove all vowels from the given string. Vowels are: i,e,a,u,o. The character 'y' or 'Y' does not count as a vowel.\n\naduqUlAeILwUVEOeyWdV\n"
},
{
"from": "gpt",
"value": "dqlLwVyWdV"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nWe would like you to assess the QUALITY of each of the following argument (discussing Gun Control) and determine if the argument is Valid or Invalid. A valid argument is clearly interpretable and either expresses an argument, or a premise or a conclusion that can be used in an argument for the topic of gun control. An invalid argument is a phrase that cannot be interpreted as an argument or not on the topic of gun control.\n\nIt is here, on this blog site, that we see people abandon reasons and common sense to play this blame game.\nOutput:"
},
{
"from": "gpt",
"value": "Invalid"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: You need to create a question containing a blank (_), based on the given context word. Your question must contain two persons --PersonX and PersonY. The expected answer to your question must be PersonX. PersonX and PersonY should not be equally likely to fill the blank. There should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people (e.g., Donald Trump, Putin, etc.) in your question. Avoid repeating the same style, pattern, or phrases in each question, try to increase diversity by varying sentence structure, blank placement, etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Person X and Person Y have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY.\nProblem:Context Word: grasshopper.\nSolution:"
},
{
"from": "gpt",
"value": "PersonX asked PersonY what to feed her new pet grasshopper, but _ did not know."
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you're given a context, a question, three options, and an answer. Your task is to classify whether the given answer is correct or not by providing 'Yes' or 'No', based on the context with commonsense reasoning about social situations.\n\nContext: Robin went after the enemies in order to avenge the name of their father. \n Question: How would Others feel as a result? \n Options: (A) A vigilante (B) Happy for Robin (C) Scared of Robin \n Answer: C\nOutput:"
},
{
"from": "gpt",
"value": "No"
}
] |
[
{
"from": "human",
"value": "You are given a short poem which is written by a kid. Your task is to predict if the kid is in elementary school or high school. Anyone who is from grade 1st to 6th-grade will be considered as in elementary school, and 7th to 12th-grade kids will be considered as in high school. There are only two possible outputs, i.e., elementary and high. All inputs have at least one output and it cannot have both categories at a time.\n\nEx Input:\ni need a bowl hurry run the popcorn 's popping it 's almost do get the salt get the butter the smell 's terrific my stomach 's a flutter mmmm mmmm sit down to eat the movie 's on kick up my foot pop the popcorn in my mouth that 's what we do in the south\n\nEx Output:\nelementary\n\n\nEx Input:\ni find a love letter lay upon my desk i look up and saw a boy who smile and wink at me what be i to think it be pink and lacy it have a greeting too that say i love you today be the day for a chance for romance at the end of the day i set to find my secret admirer who hold my heart to his desire and he be the one and that deal be do\n\nEx Output:\nelementary\n\n\nEx Input:\nbig green alligator it be crawl underwater grumpy gator\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "elementary\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task you are expected to fix an SQL query based on feedback. You will be given an SQL statement and an English description with what is wrong about that SQL statement. You must correct the SQL statement based off of the feedback. An SQL query works by selecting data from a table where certain conditions apply. A table contains columns where every row in that table must have a value for each column. Every table has a primary key that uniquely identifies each row, usually an id. To choose which columns are returned you specify that after the \"SELECT\" statement. Next, you use a \"FROM\" statement to specify what tables you want to select the data from. When you specify a table you can rename it with the \"AS\" statement. You can reference that table by whatever name follows the \"AS\" statement. If you want to select data from multiple tables you need to use the \"JOIN\" statement. This will join the tables together by pairing a row in one table with every row in the other table (Cartesian Product). To limit the number of rows returned you should use the \"ON\" statement. This will only return rows where the condition specified after the statement is true, this is usually an equals operator with primary keys. You can also use the \"WHERE\" statement to specify that only rows with column values statisfying a certain condition, should be returned. The \"GROUP BY\" statement will group rows together that have equal column values for whatever columns follows the statement. The \"HAVING\" statement will return groups that statisfy whatever condition follows the statement. Any column(s) being returned from grouped rows must either be an aggregate function, (AVG, MAX, COUNT, SUM, ...) of a column, or the column(s) that the data was grouped by. To sort the returned data you can use the \"ORDER BY\" command which will order the data by whatever aggregate function or column follows the statement. The \"DESC\" statement will sort in descending order and the \"ASC\" statement will sort in ascending order. Finally, you can use the \"LIMIT\" statement to return a certain number of rows. When \"*\" is used in an SQL statement every column is returned. For example, SELECT * FROM table WHERE attribute = 1, will select every column from rows with the attribute column equal to 1. \nOne example: SQL: SELECT avg ( Area ) , max ( Capacity ) FROM stadium\nFeedback: Swap the average of \"Area\" with the average of \"Capacity\"\nSolution is here: SELECT avg(capacity) , max(capacity) FROM stadium\nExplanation: The SQL statement was adjusted to find the average of the capacity. This is a good example.\n\nNow, solve this: SQL: SELECT Max ( T2.length_feet ) FROM architect AS T1 JOIN bridge AS T2 ON T1.id = T2.architect_id WHERE T1.name = \"Frank Lloyd Wright\"\nFeedback: Replace length feet with length meters , find architect's names for bridge , remove whole last part of step 2.\nSolution:"
},
{
"from": "gpt",
"value": "SELECT max(T1.length_meters) , T2.name FROM bridge AS T1 JOIN architect AS T2 ON T1.architect_id = T2.id"
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.