{"conversations": [{"role": "user", "content": "Show me the top 5 ERC20 tokens with the highest total supply, along with their names and contract addresses, but only include tokens where the price is greater than $0.10."}, {"role": "assistant", "content": "SELECT tm.name, tm.contract_address, tm.total_supply FROM token_metas tm WHERE tm.is_erc20 = 1 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "I think there's a typo in your query - it should be 'total_supply' not 'total_supply'. Also, can you join this with the token_prices_latest table to include the current price of each token?"}, {"role": "assistant", "content": "SELECT tm.name, tm.contract_address, tm.total_supply, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price > 0.10 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "The token_prices_latest table isn't in the schema. Can you modify the query to use the erc20_balances table instead to show the total balance held across all wallets for each token?"}, {"role": "assistant", "content": "SELECT tm.name, tm.contract_address, tm.total_supply, SUM(CAST(eb.amount AS decimal)) AS total_balance FROM token_metas tm JOIN erc20_balances eb ON tm.contract_address = eb.contract_address WHERE tm.is_erc20 = 1 GROUP BY tm.name, tm.contract_address, tm.total_supply ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas (\n block_timestamp timestamp(6) NOT NULL, -- Timestamp of the block when token metadata was recorded\n block_number bigint NOT NULL, -- Block number uniquely identifying the block\n transaction_hash varchar NOT NULL, -- Hash value of the transaction\n transaction_index bigint NOT NULL, -- Index of the transaction within the block\n from_address varchar NOT NULL, -- Address from which the transaction originated\n contract_address varchar NOT NULL, -- Address of the token contract\n symbol varchar NOT NULL, -- Symbol of the token\n total_supply varchar NOT NULL, -- erc20 contract total supply\n name varchar NOT NULL, -- Name of the token\n decimals bigint NOT NULL, -- Number of decimal places for the token\n is_erc20 integer NOT NULL, -- Flag indicating if the token is an ERC-20 token (0 or 1)\n is_erc721 integer NOT NULL, -- Flag indicating if the token is an ERC-721 token (0 or 1)\n is_erc1155 integer NOT NULL, -- Flag indicating if the token is an ERC-1155 token (0 or 1)\n is_proxy integer NOT NULL, -- Flag indicating if the token is a proxy (0 or 1)\n extra_info varchar NOT NULL, -- Additional information about the token\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 5760))\n)\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders (\n block_number bigint NOT NULL, -- Block number containing the transaction\n contract_address varchar NOT NULL, -- Event contract address\n wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n token_id varchar NOT NULL, -- NFT token id\n contract_type varchar NOT NULL, -- NFT contract type\n amount varchar NOT NULL, -- Number of held NFTs\n pk varchar NOT NULL -- The last string partition of the contract.\n)\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_info (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar NOT NULL, -- Token tick\n max_supply decimal(38,0) NOT NULL, -- Max supply\n lim decimal(38,0) NOT NULL, -- Limit of each mint\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n log_index integer NOT NULL, -- Index of the log within the transaction\n type varchar NOT NULL, -- mint | transfer | burn\n tick varchar NOT NULL, -- Token tick\n id varchar(255) NOT NULL, -- Unique identifier of the inscription\n amt decimal(38,0) NOT NULL, -- Mint amount\n from_address varchar(42) NOT NULL, -- Address sending the inscription (matches from_address in transactions table)\n to_address varchar(42) NOT NULL -- Address receiving the inscription (match to_address in transactions table)\n)\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\n"} {"conversations": [{"role": "user", "content": "List all clients along with their case_number and case_type for cases that are currently 'Open'."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, c.email, cs.case_number, cs.case_type\nFROM legal_services.clients AS c\nJOIN legal_services.cases AS cs\n ON c.client_id = cs.client_id\nWHERE cs.status = 'Open';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, company_name character varying(200), email character varying(128) UNIQUE NOT NULL, phone character varying(32), address text, date_registered timestamp NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (client_id) )\nCREATE TABLE legal_services.lawyers ( lawyer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, bar_number character varying(64) UNIQUE NOT NULL, firm_id character varying(64), email character varying(128) UNIQUE NOT NULL, phone character varying(32), specialization text, hire_date timestamp NOT NULL, is_partner boolean DEFAULT false, PRIMARY KEY (lawyer_id) )\nCREATE TABLE legal_services.law_firms ( firm_id character varying(64) NOT NULL, firm_name character varying(200) NOT NULL, address text NOT NULL, phone character varying(32), website character varying(255), founded_date date, managing_partner_id character varying(64), PRIMARY KEY (firm_id) )\nCREATE TABLE legal_services.cases ( case_id character varying(64) NOT NULL, case_number character varying(100) UNIQUE, case_name text NOT NULL, client_id character varying(64) NOT NULL, lead_lawyer_id character varying(64) NOT NULL, case_type character varying(100) NOT NULL, status character varying(50) NOT NULL, date_opened timestamp NOT NULL, date_closed timestamp, description text, court_jurisdiction character varying(128), PRIMARY KEY (case_id) )\nCREATE TABLE legal_services.documents ( document_id character varying(64) NOT NULL, case_id character varying(64) NOT NULL, document_name character varying(255) NOT NULL, document_type character varying(100), storage_path text NOT NULL, uploaded_by_lawyer_id character varying(64), upload_timestamp timestamp NOT NULL, version integer DEFAULT 1, description text, PRIMARY KEY (document_id) )\nCREATE TABLE legal_services.time_entries ( entry_id character varying(64) NOT NULL, case_id character varying(64) NOT NULL, lawyer_id character varying(64) NOT NULL, date_worked date NOT NULL, hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), billing_rate numeric(10, 2) NOT NULL, description text NOT NULL, is_billable boolean DEFAULT true, is_billed boolean DEFAULT false, invoice_id character varying(64), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (entry_id) )\nCREATE TABLE legal_services.appointments ( appointment_id character varying(64) NOT NULL, client_id character varying(64) NOT NULL, lawyer_id character varying(64) NOT NULL, case_id character varying(64), start_time timestamp NOT NULL, end_time timestamp NOT NULL, location text, subject character varying(255), notes text, status character varying(50) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (appointment_id) )\n"} {"conversations": [{"role": "user", "content": "Calculate the average number of days between when an incident occurred and when the claim was reported, but only for claims that were settled in the year 2023."}, {"role": "assistant", "content": "SELECT\n AVG(EXTRACT(EPOCH FROM (reported_date - incident_date)) / 86400.0)::numeric(10, 2)\nFROM\n insurance.claims\nWHERE\n settlement_date IS NOT NULL AND EXTRACT(YEAR FROM settlement_date) = 2023;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims (\n claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n description text NOT NULL, -- detailed description of the incident and claim\n estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n settlement_amount numeric(15, 2), -- final amount paid out\n settlement_date date,\n claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n police_report_number character varying(100),\n PRIMARY KEY (claim_id)\n)\n"} {"conversations": [{"role": "user", "content": "Find all smart contracts where the code length is greater than 1000 characters."}, {"role": "assistant", "content": "SELECT contract_id, creator_address, timestamp FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000;"}, {"role": "user", "content": "Now group these by creator_address and show the count of such contracts per creator."}, {"role": "assistant", "content": "SELECT creator_address, COUNT(*) AS long_code_contracts FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000 GROUP BY creator_address;"}, {"role": "user", "content": "Can you order the results by the count in descending order?"}, {"role": "assistant", "content": "SELECT creator_address, COUNT(*) AS long_code_contracts FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000 GROUP BY creator_address ORDER BY long_code_contracts DESC;"}, {"role": "user", "content": "Now show only creators who have more than 3 such contracts."}, {"role": "assistant", "content": "SELECT creator_address, COUNT(*) AS long_code_contracts FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000 GROUP BY creator_address HAVING COUNT(*) > 3 ORDER BY long_code_contracts DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.smart_contracts ( contract_id text PRIMARY KEY, creator_address text, code text, timestamp timestamp )\n"} {"conversations": [{"role": "user", "content": "Please show me all locations that do not have a state or province recorded. Include the location name, city, and country."}, {"role": "assistant", "content": "SELECT name, city, country\nFROM transportation.locations\nWHERE state_province IS NULL OR state_province = '';"}, {"role": "user", "content": "For these locations, also include their location_id and type."}, {"role": "assistant", "content": "SELECT location_id, name, type, city, country\nFROM transportation.locations\nWHERE state_province IS NULL OR state_province = '';"}, {"role": "user", "content": "Could you additionally list any routes for which these locations are either the origin or the destination? Show the location name, route number, and specify if the location is origin or destination."}, {"role": "assistant", "content": "SELECT l.name, r.route_number,\n CASE \n WHEN r.origin_location_id = l.location_id THEN 'origin'\n WHEN r.destination_location_id = l.location_id THEN 'destination'\n END AS role\nFROM transportation.locations l\nJOIN transportation.routes r\n ON r.origin_location_id = l.location_id OR r.destination_location_id = l.location_id\nWHERE l.state_province IS NULL OR l.state_province = '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.locations ( location_id character varying(64) NOT NULL, name character varying(255) NOT NULL, type character varying(64) NOT NULL, address_line1 character varying(255), city character varying(128), state_province character varying(128), postal_code character varying(32), country character varying(64) NOT NULL, latitude numeric(9, 6), longitude numeric(9, 6), timezone character varying(64), PRIMARY KEY (location_id) )\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"} {"conversations": [{"role": "user", "content": "Show me all business center services (category = 'Business Center') along with their property IDs and descriptions, where the service is available."}, {"role": "assistant", "content": "SELECT service_name, property_id, description FROM hospitality_technology.services WHERE category = 'Business Center' AND is_available = true;"}, {"role": "user", "content": "Now, join this with another query to include the property names from the properties table (assuming properties table has property_id and property_name columns)."}, {"role": "assistant", "content": "SELECT s.service_name, s.property_id, s.description, p.property_name FROM hospitality_technology.services s JOIN hospitality_technology.properties p ON s.property_id = p.property_id WHERE s.category = 'Business Center' AND s.is_available = true;"}, {"role": "user", "content": "The query is missing the price information. Can you include that as well?"}, {"role": "assistant", "content": "SELECT s.service_name, s.property_id, s.description, p.property_name, s.price FROM hospitality_technology.services s JOIN hospitality_technology.properties p ON s.property_id = p.property_id WHERE s.category = 'Business Center' AND s.is_available = true;"}, {"role": "user", "content": "Actually, I need to see only services priced per hour (unit = 'Per Hour'), and order them by property name in alphabetical order."}, {"role": "assistant", "content": "SELECT s.service_name, s.property_id, s.description, p.property_name, s.price FROM hospitality_technology.services s JOIN hospitality_technology.properties p ON s.property_id = p.property_id WHERE s.category = 'Business Center' AND s.is_available = true AND s.unit = 'Per Hour' ORDER BY p.property_name ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.services (\n service_id character varying(64) NOT NULL, -- unique identifier for a chargeable service\n property_id character varying(64) NOT NULL, -- FK to properties table\n service_name character varying(150) NOT NULL, -- e.g., Room Service - Burger, Spa - Massage 60min, Laundry - Shirt\n description text,\n category character varying(100), -- e.g., Food & Beverage, Wellness, Business Center, Activities\n price numeric(10, 2) NOT NULL, -- price per unit/instance\n unit character varying(30), -- e.g., Per Item, Per Hour, Per Day\n is_available boolean NOT NULL DEFAULT true, -- is the service currently offered?\n department character varying(100), -- department responsible (e.g., F&B, Spa, Housekeeping)\n PRIMARY KEY (service_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all document IDs, file names, and uploaded timestamps for documents that were uploaded on a weekend."}, {"role": "assistant", "content": "SELECT document_id, file_name, uploaded_at FROM insurance.claim_documents WHERE EXTRACT(DOW FROM uploaded_at) IN (0, 6);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claim_documents ( document_id text PRIMARY KEY, claim_id text, document_type text, file_name text, file_path text, file_size_bytes int, mime_type text, uploaded_by text, uploaded_at timestamp, description text )\n"} {"conversations": [{"role": "user", "content": "What is the detailed repair history of the equipment used by the staff with staff_id 'STAFF123' during maintenance tasks?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the detailed repair history of equipment used by staff members. The data in the maintenance_records table only includes information about maintenance tasks, such as record_id, asset_id, maintenance type, and staff_id, but does not cover equipment repair histories."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.maintenance_records ( record_id.text, asset_id.text, asset_type.text, maintenance_type.text, staff_id.text, start_datetime.timestamp, end_datetime.timestamp, description.text, cost.numeric, status.text )\n"} {"conversations": [{"role": "user", "content": "Show a list of group chat names with their conversation_id, the total number of participants, and the total number of messages sent in each group chat."}, {"role": "assistant", "content": "SELECT c.conversation_id,\n c.group_name,\n COUNT(cp.participant_id) AS participant_count,\n COUNT(m.message_id) AS message_count\nFROM social_media.conversations c\nJOIN social_media.conversation_participants cp ON c.conversation_id = cp.conversation_id\nLEFT JOIN social_media.messages m ON c.conversation_id = m.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY c.conversation_id, c.group_name;"}, {"role": "user", "content": "Please filter to include only group chats that have at least 5 participants."}, {"role": "assistant", "content": "SELECT c.conversation_id,\n c.group_name,\n COUNT(cp.participant_id) AS participant_count,\n COUNT(m.message_id) AS message_count\nFROM social_media.conversations c\nJOIN social_media.conversation_participants cp ON c.conversation_id = cp.conversation_id\nLEFT JOIN social_media.messages m ON c.conversation_id = m.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY c.conversation_id, c.group_name\nHAVING COUNT(cp.participant_id) >= 5;"}, {"role": "user", "content": "Now order the results by message_count descending and limit to the top 10 group chats."}, {"role": "assistant", "content": "SELECT c.conversation_id,\n c.group_name,\n COUNT(cp.participant_id) AS participant_count,\n COUNT(m.message_id) AS message_count\nFROM social_media.conversations c\nJOIN social_media.conversation_participants cp ON c.conversation_id = cp.conversation_id\nLEFT JOIN social_media.messages m ON c.conversation_id = m.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY c.conversation_id, c.group_name\nHAVING COUNT(cp.participant_id) >= 5\nORDER BY message_count DESC\nLIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, content text, media_url text, media_type character varying(20), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, visibility character varying(20) NOT NULL DEFAULT 'public', location_lat numeric(9,6), location_lon numeric(9,6), PRIMARY KEY (post_id) )\nCREATE TABLE social_media.likes ( like_id.text, user_id.text, post_id.text, comment_id.text, created_at.timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.post_hashtags (\n post_hashtag_id character varying(64) NOT NULL, -- unique identifier for the post-hashtag link\n post_id character varying(64) NOT NULL, -- identifier of the post (FK to posts.post_id)\n hashtag_id character varying(64) NOT NULL, -- identifier of the hashtag (FK to hashtags.hashtag_id)\n PRIMARY KEY (post_hashtag_id),\n CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) -- prevent duplicate tags on a post\n)\nCREATE TABLE social_media.messages ( message_id text PRIMARY KEY, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\nCREATE TABLE social_media.conversations (\n conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated\n last_message_at timestamp, -- timestamp of the last message in the conversation\n is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message\n group_name character varying(100), -- name of the group chat (if applicable)\n PRIMARY KEY (conversation_id)\n)\nCREATE TABLE social_media.conversation_participants ( participant_id text PRIMARY KEY, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications ( notification_id.text, recipient_user_id.text, sender_user_id.text, notification_type.text, target_entity_id.text, target_entity_type.text, created_at.timestamp, read_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "Show the property name, star rating, and number of rooms for each property."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, COUNT(r.room_id) AS room_count\nFROM hospitality_technology.properties p\nLEFT JOIN hospitality_technology.rooms r ON p.property_id = r.property_id\nGROUP BY p.property_id, p.property_name, p.star_rating;"}, {"role": "user", "content": "Only include properties that have more than 30 rooms."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, COUNT(r.room_id) AS room_count\nFROM hospitality_technology.properties p\nLEFT JOIN hospitality_technology.rooms r ON p.property_id = r.property_id\nGROUP BY p.property_id, p.property_name, p.star_rating\nHAVING COUNT(r.room_id) > 30;"}, {"role": "user", "content": "Add a column showing the total number of unique room types at each property."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, COUNT(r.room_id) AS room_count, COUNT(DISTINCT rt.room_type_id) AS unique_room_type_count\nFROM hospitality_technology.properties p\nLEFT JOIN hospitality_technology.rooms r ON p.property_id = r.property_id\nLEFT JOIN hospitality_technology.room_types rt ON p.property_id = rt.property_id\nGROUP BY p.property_id, p.property_name, p.star_rating\nHAVING COUNT(r.room_id) > 30;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.rooms (\n room_id character varying(64) NOT NULL, -- unique identifier for the room\n property_id character varying(64) NOT NULL, -- FK to properties table\n room_number character varying(10) NOT NULL, -- room number identifier (e.g., '101', 'Suite 2B')\n room_type_id character varying(64) NOT NULL, -- FK to room_types table\n floor integer, -- floor number the room is on\n status character varying(50) NOT NULL, -- e.g., Available, Occupied, Cleaning, OutOfOrder, Maintenance\n is_smoking boolean NOT NULL DEFAULT false, -- smoking allowed flag\n features text, -- description of features (e.g., Balcony, Sea View, Jacuzzi)\n current_condition text, -- notes on room condition\n last_cleaned_at timestamp with time zone, -- timestamp of last cleaning\n PRIMARY KEY (room_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.room_types (\n room_type_id character varying(64) NOT NULL, -- unique identifier for the room type\n property_id character varying(64) NOT NULL, -- FK to properties table (type might be property-specific)\n type_name character varying(100) NOT NULL, -- e.g., Standard King, Deluxe Queen, Executive Suite\n description text, -- description of the room type\n base_rate numeric(10, 2) NOT NULL, -- standard price per night\n max_occupancy integer NOT NULL, -- maximum number of guests\n bed_type character varying(50), -- e.g., King, Queen, 2 Doubles, Twin\n area_sqft numeric(8,2), -- size of the room in square feet\n amenities text, -- comma-separated list or JSON of amenities\n PRIMARY KEY (room_type_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\nCREATE TABLE hospitality_technology.guests ( guest_id text, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.reservations ( reservation_id.text, property_id.text, guest_id.text, room_id.text, room_type_id.text, check_in_date.date, check_out_date.date, actual_check_in_ts.timestamp, actual_check_out_ts.timestamp, num_adults.integer, num_children.integer, status.text, booking_source.text, rate_plan_id.text, total_amount.numeric, amount_paid.numeric, special_requests.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id text, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level integer, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.payments (\n payment_id character varying(64) NOT NULL, -- unique identifier for the payment transaction\n reservation_id character varying(64), -- FK to reservations (if payment is for a stay)\n guest_id character varying(64) NOT NULL, -- FK to guests (who paid)\n bill_id character varying(64), -- FK to bills/invoices this payment applies to\n amount numeric(12,2) NOT NULL, -- amount of the payment\n currency_code character varying(3) NOT NULL, -- ISO currency code (e.g., USD, EUR)\n payment_method character varying(50) NOT NULL, -- e.g., CreditCard, Cash, BankTransfer, Points, Voucher\n card_type character varying(50), -- e.g., Visa, MasterCard, Amex (if CC)\n card_last_four character varying(4), -- last 4 digits of CC (if CC)\n transaction_ref character varying(128), -- reference ID from payment gateway or processor\n payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the payment occurred\n status character varying(50) NOT NULL, -- e.g., Pending, Succeeded, Failed, Refunded, Disputed\n staff_id_processed character varying(64), -- FK to staff (who processed the payment)\n notes text, -- notes about the payment\n PRIMARY KEY (payment_id),\n FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "For each medication, show the total number of prescriptions where at least one refill was allowed."}, {"role": "assistant", "content": "SELECT medication_id, COUNT(*) AS prescription_count FROM healthcare.prescriptions WHERE refills_allowed > 0 GROUP BY medication_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.doctors ( doctor_id text PRIMARY KEY, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id text PRIMARY KEY, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes int, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id text PRIMARY KEY, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.prescriptions ( prescription_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed int, prescription_date timestamp )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text PRIMARY KEY, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 narratives by market cap, along with their 24-hour trading volume and 7-day price change percentage."}, {"role": "assistant", "content": "SELECT narrative.text, volume_24h.numeric, price_change_percentage_7d.numeric FROM narrative_info ORDER BY market_cap.numeric DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the top 3 coins for each of these narratives?"}, {"role": "assistant", "content": "SELECT narrative.text, volume_24h.numeric, price_change_percentage_7d.numeric, top_3_coins.text FROM narrative_info ORDER BY market_cap.numeric DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE narrative_info ( narrative.text, top_3_coins.text, price_change_percentage_1h.numeric, price_change_percentage_24h.numeric, price_change_percentage_7d.numeric, market_cap.numeric, volume_24h.numeric, trend_rank.numeric, token_num.numeric )\n"} {"conversations": [{"role": "user", "content": "Can you show me all diagnoses with code_type 'ICD-9' that were made in 2022, including diagnosis_id, patient_id, diagnosis_code, and diagnosis_date?"}, {"role": "assistant", "content": "SELECT diagnosis_id, patient_id, diagnosis_code, diagnosis_date FROM healthcare.diagnoses WHERE code_type = 'ICD-9' AND EXTRACT(year FROM diagnosis_date) = 2022;"}, {"role": "user", "content": "Actually, also include the doctor_id and description fields in the results."}, {"role": "assistant", "content": "SELECT diagnosis_id, patient_id, doctor_id, diagnosis_code, description, diagnosis_date FROM healthcare.diagnoses WHERE code_type = 'ICD-9' AND EXTRACT(year FROM diagnosis_date) = 2022;"}, {"role": "user", "content": "Now, only show diagnoses that have status 'Resolved' and sort the results by diagnosis_date ascending."}, {"role": "assistant", "content": "SELECT diagnosis_id, patient_id, doctor_id, diagnosis_code, description, diagnosis_date FROM healthcare.diagnoses WHERE code_type = 'ICD-9' AND EXTRACT(year FROM diagnosis_date) = 2022 AND status = 'Resolved' ORDER BY diagnosis_date ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.diagnoses (\n diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n description text, -- textual description of the diagnosis\n diagnosis_date date NOT NULL, -- date the diagnosis was made\n status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n is_chronic boolean DEFAULT false, -- flag for chronic conditions\n PRIMARY KEY (diagnosis_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 users who have created the most wallets, along with their email addresses and the creation date of their first wallet."}, {"role": "assistant", "content": "SELECT u.user_id, u.email, MIN(w.created_at) AS first_wallet_date, COUNT(w.wallet_id) AS wallet_count FROM trading_platform.users u JOIN trading_platform.wallets w ON u.user_id = w.user_id GROUP BY u.user_id, u.email ORDER BY wallet_count DESC LIMIT 5;"}, {"role": "user", "content": "Now modify the query to only include wallets created in the last 6 months."}, {"role": "assistant", "content": "SELECT u.user_id, u.email, MIN(w.created_at) AS first_wallet_date, COUNT(w.wallet_id) AS wallet_count FROM trading_platform.users u JOIN trading_platform.wallets w ON u.user_id = w.user_id WHERE w.created_at >= NOW() - INTERVAL '6 months' GROUP BY u.user_id, u.email ORDER BY wallet_count DESC LIMIT 5;"}, {"role": "user", "content": "Actually, I want to see the total balance across all wallets for each of these users, calculated from unspent UTXOs."}, {"role": "assistant", "content": "SELECT u.user_id, u.email, MIN(w.created_at) AS first_wallet_date, COUNT(w.wallet_id) AS wallet_count, COALESCE(SUM(ut.amount), 0) AS total_balance FROM trading_platform.users u JOIN trading_platform.wallets w ON u.user_id = w.user_id LEFT JOIN trading_platform.utxos ut ON w.address = ut.address AND ut.spent = false WHERE w.created_at >= NOW() - INTERVAL '6 months' GROUP BY u.user_id, u.email ORDER BY wallet_count DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.wallets (\n wallet_id character varying(64) NOT NULL, -- unique identifier for the wallet\n user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n address character varying(128) NOT NULL, -- address of the wallet\n private_key text NOT NULL, -- private key of the wallet\n created_at timestamp NOT NULL, -- time when the wallet was created\n PRIMARY KEY (wallet_id)\n)\nCREATE TABLE trading_platform.orders (\n order_id character varying(64) NOT NULL, -- unique identifier for the order\n user_id character varying(64) NOT NULL, -- identifier of the user placing the order\n wallet_id character varying(64) NOT NULL, -- identifier of the wallet used for the order\n asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n order_type character varying(32) NOT NULL, -- type of the order (e.g., buy, sell)\n quantity numeric(38,14) NOT NULL, -- quantity of the asset in the order\n price numeric(38,14) NOT NULL, -- price per unit of the asset\n status character varying(32) NOT NULL, -- status of the order (e.g., open, filled, canceled)\n created_at timestamp NOT NULL, -- time when the order was created\n PRIMARY KEY (order_id)\n)\nCREATE TABLE trading_platform.trades (\n trade_id character varying(64) NOT NULL, -- unique identifier for the trade\n order_id character varying(64) NOT NULL, -- identifier of the order that led to the trade\n buyer_id character varying(64) NOT NULL, -- identifier of the buyer\n seller_id character varying(64) NOT NULL, -- identifier of the seller\n asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n quantity numeric(38,14) NOT NULL, -- quantity of the asset in the trade\n price numeric(38,14) NOT NULL, -- price per unit of the asset\n traded_at timestamp NOT NULL, -- time when the trade was executed\n PRIMARY KEY (trade_id)\n)\nCREATE TABLE trading_platform.assets (\n asset_id character varying(64) NOT NULL, -- unique identifier for the asset\n name character varying(128) NOT NULL, -- name of the asset\n symbol character varying(32) NOT NULL, -- symbol of the asset\n type character varying(32) NOT NULL, -- type of the asset (e.g., cryptocurrency, stock)\n PRIMARY KEY (asset_id)\n)\nCREATE TABLE trading_platform.utxos (\n utxo_id character varying(64) NOT NULL, -- unique identifier for the UTXO\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction that created the UTXO\n output_index integer NOT NULL, -- index of the output in the transaction\n address character varying(128) NOT NULL, -- address that can spend the UTXO\n amount numeric(38,14) NOT NULL, -- amount of the asset in the UTXO\n spent boolean NOT NULL, -- whether the UTXO has been spent\n PRIMARY KEY (utxo_id)\n)\nCREATE TABLE trading_platform.dapps (\n dapp_id character varying(64) NOT NULL, -- unique identifier for the DApp\n name character varying(128) NOT NULL, -- name of the DApp\n description text NOT NULL, -- description of the DApp\n url character varying(256) NOT NULL, -- URL of the DApp\n PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.peers (\n peer_id character varying(64) NOT NULL, -- unique identifier for the peer\n ip_address character varying(15) NOT NULL, -- IP address of the peer\n port integer NOT NULL, -- port number of the peer\n last_seen timestamp NOT NULL, -- last time the peer was active\n PRIMARY KEY (peer_id)\n)\nCREATE TABLE trading_platform.metadata (\n metadata_id character varying(64) NOT NULL, -- unique identifier for the metadata\n asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with\n key character varying(128) NOT NULL, -- key of the metadata\n value text NOT NULL, -- value of the metadata\n PRIMARY KEY (metadata_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me all in-progress trips with their current locations (origin_location_id) and destinations, along with the scheduled vs actual departure time difference in minutes."}, {"role": "assistant", "content": "SELECT trip_id, origin_location_id, destination_location_id, EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/60 AS departure_delay_minutes FROM transportation.trips WHERE status = 'In Progress';"}, {"role": "user", "content": "Can you also include the vehicle_id and driver_id, and order by the departure delay in descending order?"}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, origin_location_id, destination_location_id, EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/60 AS departure_delay_minutes FROM transportation.trips WHERE status = 'In Progress' ORDER BY departure_delay_minutes DESC;"}, {"role": "user", "content": "Now filter to only show trips that have been delayed by more than 30 minutes."}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, origin_location_id, destination_location_id, EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/60 AS departure_delay_minutes FROM transportation.trips WHERE status = 'In Progress' AND EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/60 > 30 ORDER BY departure_delay_minutes DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.trips (\n trip_id character varying(64) NOT NULL, -- unique identifier for a specific trip instance\n route_id character varying(64), -- identifier of the route being followed (can be null for ad-hoc trips)\n vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle used\n driver_id character varying(64) NOT NULL, -- identifier of the driver operating\n scheduled_departure timestamp with time zone NOT NULL, -- planned departure time\n actual_departure timestamp with time zone, -- actual departure time\n scheduled_arrival timestamp with time zone NOT NULL, -- planned arrival time\n actual_arrival timestamp with time zone, -- actual arrival time\n origin_location_id character varying(64) NOT NULL, -- actual starting location (could differ from route origin)\n destination_location_id character varying(64) NOT NULL, -- actual ending location (could differ from route destination)\n status character varying(32) NOT NULL, -- e.g., Scheduled, In Progress, Completed, Delayed, Cancelled\n passenger_count integer, -- number of passengers (if applicable)\n cargo_manifest_id character varying(64), -- link to cargo details (if applicable)\n PRIMARY KEY (trip_id)\n)\n"} {"conversations": [{"role": "user", "content": "For each developer, can you find the next developer in the same country using a self join, returning developer_ids and names?"}, {"role": "assistant", "content": "SELECT d1.developer_id AS current_dev,\n d1.name AS current_name,\n d2.developer_id AS next_dev,\n d2.name AS next_name,\n d2.founded_year - d1.founded_year AS years_diff\nFROM developers d1\nJOIN developers d2\n ON d1.country = d2.country\n AND d2.founded_year > d1.founded_year;"}, {"role": "user", "content": "Exclude developers who don't have a next developer, and ensure we only pick the closest next by founded_year."}, {"role": "assistant", "content": "SELECT d1.developer_id AS current_dev,\n d1.name AS current_name,\n d2.developer_id AS next_dev,\n d2.name AS next_name,\n d2.founded_year - d1.founded_year AS years_diff\nFROM developers d1\nJOIN LATERAL (\n SELECT d2.developer_id, d2.name, d2.founded_year\n FROM developers d2\n WHERE d2.country = d1.country\n AND d2.founded_year > d1.founded_year\n ORDER BY d2.founded_year ASC\n LIMIT 1\n) d2 ON true;"}, {"role": "user", "content": "Finally, only include pairs where the difference in founded years is at most 5 years."}, {"role": "assistant", "content": "SELECT d1.developer_id AS current_dev,\n d1.name AS current_name,\n d2.developer_id AS next_dev,\n d2.name AS next_name,\n d2.founded_year - d1.founded_year AS years_diff\nFROM developers d1\nJOIN LATERAL (\n SELECT d2.developer_id, d2.name, d2.founded_year\n FROM developers d2\n WHERE d2.country = d1.country\n AND d2.founded_year > d1.founded_year\n ORDER BY d2.founded_year ASC\n LIMIT 1\n) d2 ON true\nWHERE (d2.founded_year - d1.founded_year) <= 5\nORDER BY d1.developer_id, years_diff ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.developers ( developer_id uuid PRIMARY KEY, name text, country text, founded_year int, website text, created_at timestamptz )\n"} {"conversations": [{"role": "user", "content": "Show me the top 3 tokens by trend rank in the 'NFT' narrative, along with their price and 24-hour trading volume."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, price, total_volume FROM token_basic_info WHERE narrative = 'NFT' ORDER BY trend_rank ASC LIMIT 3;"}, {"role": "user", "content": "Can you also include their 1-hour and 7-day price change percentages?"}, {"role": "assistant", "content": "SELECT token_name, token_symbol, price, total_volume, price_change_percentage_1h, price_change_percentage_7d FROM token_basic_info WHERE narrative = 'NFT' ORDER BY trend_rank ASC LIMIT 3;"}, {"role": "user", "content": "Actually, I only want tokens with positive price changes in both time frames."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, price, total_volume, price_change_percentage_1h, price_change_percentage_7d FROM token_basic_info WHERE narrative = 'NFT' AND price_change_percentage_1h > 0 AND price_change_percentage_7d > 0 ORDER BY trend_rank ASC LIMIT 3;"}, {"role": "user", "content": "Now order the results by 24-hour trading volume instead of trend rank."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, price, total_volume, price_change_percentage_1h, price_change_percentage_7d FROM token_basic_info WHERE narrative = 'NFT' AND price_change_percentage_1h > 0 AND price_change_percentage_7d > 0 ORDER BY total_volume::numeric DESC LIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, token_name character varying(100) NOT NULL, token_symbol character varying(100) NOT NULL, token_address character varying(100) NOT NULL, chain text, price double precision, price_change_percentage_1h double precision, price_change_percentage_24h double precision, price_change_percentage_7d double precision, highest_price_24h double precision, lowest_price_24h double precision, market_cap double precision, market_cap_rank bigint, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank bigint )\n"} {"conversations": [{"role": "user", "content": "For each transaction, find the next transaction initiated by the same sender. List the original transaction_id, the next transaction_id, the sender address, and the time difference in hours between them."}, {"role": "assistant", "content": "SELECT t1.transaction_id AS original_tx,\n t2.transaction_id AS next_tx,\n t1.from_address,\n EXTRACT(EPOCH FROM (t2.timestamp - t1.timestamp)) / 3600 AS hours_diff\nFROM transactions t1\nJOIN transactions t2\n ON t1.from_address = t2.from_address\n AND t2.timestamp = (\n SELECT MIN(timestamp)\n FROM transactions t3\n WHERE t3.from_address = t1.from_address\n AND t3.timestamp > t1.timestamp\n );"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.transactions ( transaction_id text, from_address text, to_address text, value numeric, gas_used integer, gas_price numeric, block_number integer, timestamp timestamp, input_data text, status text, nonce integer )\n"} {"conversations": [{"role": "user", "content": "能否帮我查询特定路线(route_id 为 'route_ne_corr')上的所有车站信息，并包含每个车站的平台数量？"}, {"role": "assistant", "content": "ZRANGE route:route_ne_corr:stops 0 -1\nHGETALL route_station: for each route_station_id in result\nHGETALL station: for each station_id in result\nSCARD station::platforms for each station_id in result"}, {"role": "user", "content": "能否将结果按照车站的顺序(sequence_order)进行排序？"}, {"role": "assistant", "content": "ZRANGE route:route_ne_corr:stops 0 -1 WITHSCORES\nHGETALL route_station: for each route_station_id in result\nHGETALL station: for each station_id in result\nSCARD station::platforms for each station_id in result\nSort results by sequence_order (score from ZRANGE)"}, {"role": "user", "content": "能否只显示有超过5个平台的车站信息？"}, {"role": "assistant", "content": "ZRANGE route:route_ne_corr:stops 0 -1 WITHSCORES\nHGETALL route_station: for each route_station_id in result\nHGETALL station: for each station_id in result\nSCARD station::platforms for each station_id in result\nFilter results where SCARD result > 5\nSort results by sequence_order (score from ZRANGE)"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// Use Hashes to store station details. Key format: station:\n// Example:\n// HSET station:station_xyz station_id \"station_xyz\" station_name \"Grand Central Terminal\" city \"New York\" state_province \"NY\" country_code \"USA\" address \"89 E 42nd St...\" timezone \"America/New_York\" number_of_platforms 44 created_at \"2023-01-15T10:00:00Z\" last_updated_at \"2023-10-28T15:30:00Z\"\n\n// To quickly find stations by city (optional index):\n// SADD stations:city:NewYork station:station_xyz\n// Use Hashes for platform details. Key format: platform:\n// HSET platform:plat_123 platform_id \"plat_123\" station_id \"station_xyz\" platform_number \"1A\" track_number \"T1\" status \"Operational\" length_meters 250.50 accessible 1\n\n// To link platforms to stations (optional):\n// SADD station:station_xyz:platforms platform:plat_123 platform:plat_456\n// Use Hashes for train details. Key format: train:\n// HSET train:train_789 train_id \"train_789\" train_number \"Acela 2151\" model \"Siemens Velaro\" ... status \"Active\" ...\n\n// To find train by train_number (optional index):\n// SET train_number:\"Acela 2151\" train:train_789\n// Use Hashes for car details. Key format: car:\n// HSET car:car_abc car_id \"car_abc\" train_id \"train_789\" car_number \"C3\" car_type \"Passenger\" class \"Business\" capacity 60 features \"WiFi,Power Outlet\"\n\n// To link cars to trains (optional):\n// SADD train:train_789:cars car:car_abc car:car_def\n// Use Hashes for route details. Key format: route:\n// HSET route:route_ne_corr route_id \"route_ne_corr\" route_name \"Northeast Corridor\" ... origin_station_id \"station_bos\" ... is_active 1\n// Use Hashes for details. Key format: route_station:\n// HSET route_station:rs_ne_1 route_station_id \"rs_ne_1\" route_id \"route_ne_corr\" station_id \"station_bos\" sequence_order 1 ...\n\n// To find stops for a route, use a Sorted Set (score by sequence_order):\n// ZADD route:route_ne_corr:stops 1 route_station:rs_ne_1\n// ZADD route:route_ne_corr:stops 2 route_station:rs_ne_2\n// Use Hashes for passenger details. Key format: passenger:\n// HSET passenger:pass_pqr passenger_id \"pass_pqr\" first_name \"Alice\" last_name \"Smith\" email \"alice.smith@example.com\" ...\n\n// To find passenger by email (optional index):\n// SET passenger_email:\"alice.smith@example.com\" passenger:pass_pqr\n// Use Hashes for booking details. Key format: booking:\n// HSET booking:book_zyx booking_id \"book_zyx\" passenger_id \"pass_pqr\" schedule_id \"sched_1122\" ... status \"Confirmed\" ...\n\n// To link bookings to passengers/schedules (optional):\n// SADD passenger:pass_pqr:bookings booking:book_zyx\n// SADD schedule:sched_1122:bookings booking:book_zyx\n// Use Hashes for ticket details. Key format: ticket:\n// HSET ticket:tkt_1a2b ticket_id \"tkt_1a2b\" booking_id \"book_zyx\" car_id \"car_abc\" seat_number \"12A\" ... is_checked_in 0 ...\n\n// To link tickets to bookings (optional):\n// SADD booking:book_zyx:tickets ticket:tkt_1a2b\n"} {"conversations": [{"role": "user", "content": "What is the average daily trading volume for each security_id in the market_data table from the last 30 days?"}, {"role": "assistant", "content": "SELECT security_id, AVG(volume) as avg_daily_volume FROM financial_services.market_data WHERE data_timestamp >= CURRENT_DATE - INTERVAL '30 days' GROUP BY security_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.accounts ( account_id text, customer_id text, account_number text, account_type text, balance numeric, currency text, opened_date date, status text, interest_rate numeric, last_updated_at timestamp )\nCREATE TABLE financial_services.securities ( security_id.text, ticker_symbol.text, isin_code.text, cusip_code.text, security_name.text, security_type.text, exchange.text, currency.text, issuer_name.text, sector.text, last_updated.timestamp )\nCREATE TABLE financial_services.trades ( trade_id text, account_id text, security_id text, order_id text, trade_type text, quantity numeric, price_per_unit numeric, total_amount numeric, commission numeric, trade_timestamp timestamp, settlement_date date, status text, execution_venue text )\nCREATE TABLE financial_services.market_data ( data_point_id.bigint, security_id.text, data_timestamp.timestamp, open_price.numeric, high_price.numeric, low_price.numeric, close_price.numeric, adjusted_close_price.numeric, volume.bigint, source.text )\nCREATE TABLE financial_services.employees ( employee_id text, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\n"} {"conversations": [{"role": "user", "content": "List all insurance products that have 'auto' in their product type and are currently active, showing their product name and base premium."}, {"role": "assistant", "content": "SELECT product_name, base_premium FROM insurance.insurance_products WHERE product_type LIKE '%auto%' AND is_active = true;"}, {"role": "user", "content": "Now order these results by base premium in descending order and include the coverage details."}, {"role": "assistant", "content": "SELECT product_name, base_premium, coverage_details FROM insurance.insurance_products WHERE product_type LIKE '%auto%' AND is_active = true ORDER BY base_premium DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\nCREATE TABLE insurance.insurance_products ( product_id character varying(64) NOT NULL, product_name character varying(150) NOT NULL, product_type character varying(50) NOT NULL, description text, base_premium numeric(10, 2) NOT NULL, coverage_details text, underwriting_rules text, is_active boolean NOT NULL DEFAULT true, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp, PRIMARY KEY (product_id) )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, relationship character varying(50) NOT NULL, percentage_share numeric(5, 2) NOT NULL CHECK (percentage_share > 0 AND percentage_share <= 100), contact_info text, added_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (beneficiary_id), UNIQUE (policy_id, customer_id) )\n"} {"conversations": [{"role": "user", "content": "What is the total market cap for all tokens listed on the 'Polygon' chain?"}, {"role": "assistant", "content": "SELECT SUM(market_cap) FROM token_dexpool_info WHERE chain = 'Polygon';"}, {"role": "user", "content": "Only sum the market cap for tokens on 'Polygon' that have a 24-hour volume greater than 500000."}, {"role": "assistant", "content": "SELECT SUM(market_cap) FROM token_dexpool_info WHERE chain = 'Polygon' AND volume_24h > 500000;"}, {"role": "user", "content": "Also show the number of unique tokens that meet these criteria."}, {"role": "assistant", "content": "SELECT COUNT(DISTINCT token_symbol), SUM(market_cap) FROM token_dexpool_info WHERE chain = 'Polygon' AND volume_24h > 500000;"}, {"role": "user", "content": "Can you show the total market cap and token count for *each* chain that meets these volume criteria, ordered by total market cap descending?"}, {"role": "assistant", "content": "SELECT chain, COUNT(DISTINCT token_symbol) AS token_count, SUM(market_cap) AS total_market_cap FROM token_dexpool_info WHERE volume_24h > 500000 GROUP BY chain ORDER BY total_market_cap DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, -- the id of dexpool token_name character varying(100) NOT NULL, -- the name of the token in the dexpool token_symbol character varying(100) NOT NULL, -- the token's symbol chain text, -- the chain that the dexpool resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_6h double precision, -- change in value divided by the absolute price value of the original token price in 6 hours price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours makers_24h double precision, -- the makers of the dex pool in 24 hours volume_24h double precision, -- the trade volume of the dex pool in 24 hours liquidity double precision, -- the liquidity of the dex pool market_cap double precision, -- the market cap of the token trend_rank bigint, -- the rank of token in the dex pool of recent trending, value 1 expresses the most popular token. ,PRIMARY KEY (pair_address, chain) )\n"} {"conversations": [{"role": "user", "content": "For each ERC20 token contract, show the contract address and the total number of approval events recorded."}, {"role": "assistant", "content": "SELECT contract_address, COUNT(*) AS approval_count\nFROM erc20_approval\nGROUP BY contract_address;"}, {"role": "user", "content": "Now, only include contract addresses where the approval_count is greater than 100."}, {"role": "assistant", "content": "SELECT contract_address, COUNT(*) AS approval_count\nFROM erc20_approval\nGROUP BY contract_address\nHAVING COUNT(*) > 100;"}, {"role": "user", "content": "Can you add the latest approval block_number for each contract address as well?"}, {"role": "assistant", "content": "SELECT a.contract_address, COUNT(*) AS approval_count, MAX(a.block_number) AS latest_approval_block_number\nFROM erc20_approval a\nGROUP BY a.contract_address\nHAVING COUNT(*) > 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp.timestamp, block_number.bigint, transaction_hash.text, transaction_index.bigint, from_address.text, contract_address.text, symbol.text, total_supply.text, name.text, decimals.bigint, is_erc20.integer, is_erc721.integer, is_erc1155.integer, is_proxy.integer, extra_info.text, pk.integer )\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint, contract_address text, wallet_address text, amount text, pk text )\nCREATE TABLE nft_holder_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest (\n blockchain varchar(36) NOT NULL, -- blockchain fields for the functionType in contract\n address varchar(42) NOT NULL, -- address fields for the functionType in contract\n decimals bigint NOT NULL, -- decimals fields for the functionType in contract\n symbol varchar(36) NOT NULL, -- symbol fields for the functionType in contract\n price real NOT NULL, -- price fields for the functionType in contract\n timestamp timestamp(6) NOT NULL -- timestamp fields for the functionType in contract\n)\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_info (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar NOT NULL, -- Token tick\n max_supply decimal(38,0) NOT NULL, -- Max supply\n lim decimal(38,0) NOT NULL, -- Limit of each mint\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE mud_holesky_redstone (\n address varchar NOT NULL, -- address fields for the functionType in contract\n table_id varchar NOT NULL, -- table_id fields for the functionType in contract\n key_bytes varchar NOT NULL, -- key_bytes fields for the functionType in contract\n key0 varchar NOT NULL, -- key0 fields for the functionType in contract\n key1 varchar NOT NULL, -- key1 fields for the functionType in contract\n static_data varchar NOT NULL, -- static_data fields for the functionType in contract\n encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType in contract\n dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType in contract\n is_deleted boolean NOT NULL, -- is_deleted fields for the functionType in contract\n block_number bigint NOT NULL, -- Block number uniquely identifying the block\n log_index bigint NOT NULL -- Index of the log within the transaction\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n log_index integer NOT NULL, -- Index of the log within the transaction\n type varchar(20) NOT NULL, -- Operation: Type of event (deploy, mint, transfer, list)\n tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n id varchar(255) NOT NULL, -- Unique identifier of the inscription\n amt decimal(38,0) NOT NULL, -- Amount to mint: States the amount of the inscription to operation. When operation is mint, has to be less or equal to \"lim\"\n from_address varchar(42) NOT NULL, -- Address sending the inscription\n to_address varchar(42) NOT NULL -- Address receiving the inscription\n)\n"} {"conversations": [{"role": "user", "content": "For each user, can you show their username and the length of their email address?"}, {"role": "assistant", "content": "SELECT user_id, username, LENGTH(email) AS email_length FROM web3.users;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "What is the current location of train number Acela 2151?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to real-time location data for trains. The database only contains static information such as train ID, model, capacity, and maintenance schedules. For current location updates, please check with the train operator or a tracking service."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.trains (\n train_id character varying(64) NOT NULL, -- Unique identifier for the train set\n train_number character varying(32) NOT NULL, -- Operational number of the train (e.g., 'Acela 2151')\n model character varying(128), -- Model of the train (e.g., 'Siemens Velaro')\n manufacturer character varying(128), -- Manufacturer of the train\n year_manufactured integer, -- Year the train was built\n capacity integer NOT NULL, -- Total passenger capacity\n status character varying(32) NOT NULL DEFAULT 'Active', -- e.g., Active, Maintenance, Retired\n last_maintenance_date date, -- Date of last scheduled maintenance\n next_maintenance_date date, -- Date of next scheduled maintenance\n PRIMARY KEY (train_id),\n UNIQUE (train_number)\n)\n"} {"conversations": [{"role": "user", "content": "List each vehicle and the date of its most recent maintenance, including the service type and cost."}, {"role": "assistant", "content": "SELECT vehicle_id, service_type, cost, service_date FROM (SELECT *, ROW_NUMBER() OVER (PARTITION BY vehicle_id ORDER BY service_date DESC) AS rn FROM transportation.maintenance_logs) AS ranked_logs WHERE rn = 1;"}, {"role": "user", "content": "I received an error that 'service_type' does not exist in the outermost query."}, {"role": "assistant", "content": "SELECT vehicle_id, service_date, service_type, cost FROM (SELECT log_id, vehicle_id, service_date, service_type, cost, ROW_NUMBER() OVER (PARTITION BY vehicle_id ORDER BY service_date DESC) AS rn FROM transportation.maintenance_logs) AS ranked_logs WHERE rn = 1;"}, {"role": "user", "content": "Also include the name of the mechanic for each latest maintenance."}, {"role": "assistant", "content": "SELECT vehicle_id, service_date, service_type, cost, mechanic_name FROM (SELECT log_id, vehicle_id, service_date, service_type, cost, mechanic_name, ROW_NUMBER() OVER (PARTITION BY vehicle_id ORDER BY service_date DESC) AS rn FROM transportation.maintenance_logs) AS ranked_logs WHERE rn = 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.maintenance_logs ( log_id text, vehicle_id text, service_date date, odometer_reading integer, service_type text, description text, cost numeric, mechanic_name text, next_service_due_date date )\n"} {"conversations": [{"role": "user", "content": "List the document ID, file name, and size for all documents uploaded in the last 30 days by user 'agent_smith' that are larger than 5 megabytes, ordered by upload time descending."}, {"role": "assistant", "content": "SELECT document_id, file_name, file_size_bytes FROM insurance.claim_documents WHERE uploaded_at >= CURRENT_TIMESTAMP - INTERVAL '30 day' AND uploaded_by = 'agent_smith' AND file_size_bytes > 5242880 ORDER BY uploaded_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claim_documents ( document_id text PRIMARY KEY, claim_id text, document_type text, file_name text, file_path text, file_size_bytes int, mime_type text, uploaded_by text, uploaded_at timestamp, description text )\n"} {"conversations": [{"role": "user", "content": "What is the schedule of trains arriving at platform 1A at station XYZ on December 25th, 2023?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about train schedules or specific arrival times as this data is not included in the platform management table. For train schedules, please refer to the train timetable or contact the station's customer service."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.platforms (\n platform_id character varying(64) NOT NULL, -- Unique identifier for the platform\n station_id character varying(64) NOT NULL, -- Foreign key referencing stations\n platform_number character varying(10) NOT NULL, -- Platform identifier (e.g., '1A', '5')\n track_number character varying(10), -- Associated track number, if different\n status character varying(32) NOT NULL DEFAULT 'Operational', -- e.g., Operational, Maintenance, Closed\n length_meters numeric(8,2), -- Length of the platform in meters\n accessible boolean NOT NULL DEFAULT false, -- Is the platform accessible (e.g., wheelchair)?\n PRIMARY KEY (platform_id),\n FOREIGN KEY (station_id) REFERENCES train_station_management.stations(station_id)\n)\n"} {"conversations": [{"role": "user", "content": "List the first name, last name, and hire date of all lawyers who are partners."}, {"role": "assistant", "content": "SELECT first_name , last_name , hire_date FROM legal_services.lawyers WHERE is_partner = TRUE"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers (\n lawyer_id character varying(64) NOT NULL, -- unique identifier for the lawyer\n first_name character varying(100) NOT NULL, -- lawyer's first name\n last_name character varying(100) NOT NULL, -- lawyer's last name\n bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n firm_id character varying(64), -- FK to law_firms table\n email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n phone character varying(32), -- lawyer's contact phone number\n specialization text, -- areas of legal expertise\n hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n PRIMARY KEY (lawyer_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all NFT collections where the floor price is greater than 0.5 ETH, including their names and contract addresses."}, {"role": "assistant", "content": "SELECT name, contract_address FROM nft_collections WHERE CAST(floor_price AS decimal) > 0.5 AND floor_price_symbol = 'ETH';"}, {"role": "user", "content": "Can you also include the banner image URL and filter to only show ERC721 collections?"}, {"role": "assistant", "content": "SELECT name, contract_address, banner_image_url FROM nft_collections WHERE CAST(floor_price AS decimal) > 0.5 AND floor_price_symbol = 'ETH' AND erc_type = 'ERC721';"}, {"role": "user", "content": "Now sort these results by floor price in descending order and limit to the top 10."}, {"role": "assistant", "content": "SELECT name, contract_address, banner_image_url, floor_price FROM nft_collections WHERE CAST(floor_price AS decimal) > 0.5 AND floor_price_symbol = 'ETH' AND erc_type = 'ERC721' ORDER BY CAST(floor_price AS decimal) DESC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas (\n block_timestamp timestamp(6) NOT NULL, -- Timestamp of the block when token metadata was recorded\n block_number bigint NOT NULL, -- Block number uniquely identifying the block\n transaction_hash varchar NOT NULL, -- Hash value of the transaction\n transaction_index bigint NOT NULL, -- Index of the transaction within the block\n from_address varchar NOT NULL, -- Address from which the transaction originated\n contract_address varchar NOT NULL, -- Address of the token contract\n symbol varchar NOT NULL, -- Symbol of the token\n total_supply varchar NOT NULL, -- erc20 contract total supply\n name varchar NOT NULL, -- Name of the token\n decimals bigint NOT NULL, -- Number of decimal places for the token\n is_erc20 integer NOT NULL, -- Flag indicating if the token is an ERC-20 token (0 or 1)\n is_erc721 integer NOT NULL, -- Flag indicating if the token is an ERC-721 token (0 or 1)\n is_erc1155 integer NOT NULL, -- Flag indicating if the token is an ERC-1155 token (0 or 1)\n is_proxy integer NOT NULL, -- Flag indicating if the token is a proxy (0 or 1)\n extra_info varchar NOT NULL, -- Additional information about the token\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 5760))\n)\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders (\n block_number bigint NOT NULL, -- Block number containing the transaction\n contract_address varchar NOT NULL, -- Event contract address\n wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n token_id varchar NOT NULL, -- NFT token id\n contract_type varchar NOT NULL, -- NFT contract type\n amount varchar NOT NULL, -- Number of held NFTs\n pk varchar NOT NULL -- The last string partition of the contract.\n)\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk integer )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata ( object_id.text, coin_type.text, status.text, decimals.bigint, description.text, icon_url.text, symbol.text, name.text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain varchar, contract_address varchar, name varchar, symbol varchar, deploy_block_number bigint, deploy_block_time bigint, erc_type varchar, owner varchar, traits varchar, description varchar, slug varchar, media_info varchar, image_url varchar, banner_image_url varchar, updated_at bigint, banner varchar, token_count bigint, floor_price varchar, floor_price_symbol varchar, floor_price_contract varchar, pk integer )\nCREATE TABLE token_prices ( uuid.text, blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE token_prices_latest ( blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_balances ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.decimal, amount.decimal )\nCREATE TABLE token_info (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar NOT NULL, -- Token tick\n max_supply decimal(38,0) NOT NULL, -- Max supply\n lim decimal(38,0) NOT NULL, -- Limit of each mint\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n log_index integer NOT NULL, -- Index of the log within the transaction\n type varchar NOT NULL, -- mint | transfer | burn\n tick varchar NOT NULL, -- Token tick\n id varchar(255) NOT NULL, -- Unique identifier of the inscription\n amt decimal(38,0) NOT NULL, -- Mint amount\n from_address varchar(42) NOT NULL, -- Address sending the inscription (matches from_address in transactions table)\n to_address varchar(42) NOT NULL -- Address receiving the inscription (match to_address in transactions table)\n)\nCREATE TABLE mud_holesky_redstone ( address varchar, table_id varchar, key_bytes varchar, key0 varchar, key1 varchar, static_data varchar, encoded_lengths varchar, dynamic_data varchar, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"} {"conversations": [{"role": "user", "content": "For each vehicle, list its vehicle_id, license_plate, and any older vehicle of the same type (showing older_vehicle_id and older year)."}, {"role": "assistant", "content": "SELECT cur.vehicle_id,\n cur.license_plate,\n old.vehicle_id AS older_vehicle_id,\n old.year AS older_vehicle_year\nFROM transportation.vehicles cur\nJOIN transportation.vehicles old\n ON cur.type = old.type\n AND old.year < cur.year\nORDER BY cur.vehicle_id, old.year DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles (\n vehicle_id character varying(64) NOT NULL, -- unique identifier for the vehicle\n license_plate character varying(32) NOT NULL UNIQUE, -- vehicle license plate\n vin character varying(17) UNIQUE, -- vehicle identification number\n make character varying(64) NOT NULL, -- manufacturer of the vehicle\n model character varying(64) NOT NULL, -- model of the vehicle\n year integer NOT NULL, -- manufacturing year\n type character varying(32) NOT NULL, -- type of vehicle (e.g., Bus, Train, Truck, Car, Van)\n capacity integer, -- passenger or cargo capacity\n fuel_type character varying(32) NOT NULL, -- e.g., Diesel, Gasoline, Electric, Hydrogen\n status character varying(32) NOT NULL, -- e.g., Active, Maintenance, Decommissioned\n depot_id character varying(64), -- identifier of the home depot/base\n acquisition_date date, -- date the vehicle was acquired\n PRIMARY KEY (vehicle_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show the total trade amount for each account. Include the account_id and account_number."}, {"role": "assistant", "content": "SELECT\n T1.account_id,\n T1.account_number,\n SUM(T2.total_amount) AS total_traded_amount\nFROM financial_services.accounts AS T1\nINNER JOIN financial_services.trades AS T2\n ON T1.account_id = T2.account_id\nGROUP BY\n T1.account_id,\n T1.account_number;"}, {"role": "user", "content": "Only include trades with a status of 'SETTLED'."}, {"role": "assistant", "content": "SELECT\n T1.account_id,\n T1.account_number,\n SUM(T2.total_amount) AS total_traded_amount\nFROM financial_services.accounts AS T1\nINNER JOIN financial_services.trades AS T2\n ON T1.account_id = T2.account_id\nWHERE\n T2.status = 'SETTLED'\nGROUP BY\n T1.account_id,\n T1.account_number;"}, {"role": "user", "content": "Filter out accounts where the total traded amount for settled trades is less than 5000."}, {"role": "assistant", "content": "SELECT\n T1.account_id,\n T1.account_number,\n SUM(T2.total_amount) AS total_traded_amount\nFROM financial_services.accounts AS T1\nINNER JOIN financial_services.trades AS T2\n ON T1.account_id = T2.account_id\nWHERE\n T2.status = 'SETTLED'\nGROUP BY\n T1.account_id,\n T1.account_number\nHAVING\n SUM(T2.total_amount) >= 5000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.customers ( customer_id text, first_name text, last_name text, date_of_birth date, ssn_hash text, address text, city text, state text, zip_code text, country text, email text, phone_number text, created_at timestamp, status text, risk_profile text )\nCREATE TABLE financial_services.accounts ( account_id text, customer_id text, account_number text, account_type text, balance numeric, currency text, opened_date date, status text, interest_rate numeric, last_updated_at timestamp )\nCREATE TABLE financial_services.transactions (\n transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n account_id character varying(64) NOT NULL, -- account involved in the transaction\n related_account_id character varying(64), -- counterpart account for transfers\n transaction_type character varying(50) NOT NULL, -- e.g., Deposit, Withdrawal, Transfer, Payment, Fee, Interest\n amount numeric(19, 4) NOT NULL, -- transaction amount\n currency character varying(3) NOT NULL, -- transaction currency\n transaction_date timestamp NOT NULL, -- exact time of the transaction\n effective_date date NOT NULL, -- date the transaction affects the balance\n description text, -- description or memo of the transaction\n status character varying(32) NOT NULL, -- e.g., Pending, Completed, Failed, Reversed\n reference_number character varying(128), -- external reference if applicable (e.g., check number)\n PRIMARY KEY (transaction_id),\n FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id),\n FOREIGN KEY (related_account_id) REFERENCES financial_services.accounts(account_id)\n)\nCREATE TABLE financial_services.securities ( security_id.text, ticker_symbol.text, isin_code.text, cusip_code.text, security_name.text, security_type.text, exchange.text, currency.text, issuer_name.text, sector.text, last_updated.timestamp )\nCREATE TABLE financial_services.trades ( trade_id text PRIMARY KEY, account_id text, security_id text, order_id text, trade_type text, quantity numeric, price_per_unit numeric, total_amount numeric, commission numeric, trade_timestamp timestamp, settlement_date date, status text, execution_venue text )\nCREATE TABLE financial_services.market_data ( data_point_id.bigint, security_id.text, data_timestamp.timestamp, open_price.numeric, high_price.numeric, low_price.numeric, close_price.numeric, adjusted_close_price.numeric, volume.bigint, source.text )\nCREATE TABLE financial_services.employees (\n employee_id character varying(64) NOT NULL, -- unique identifier for the employee\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n job_title character varying(100) NOT NULL, -- e.g., Teller, Branch Manager, Financial Advisor, Analyst\n department character varying(100), -- e.g., Retail Banking, Wealth Management, IT\n branch_id character varying(64), -- Identifier for the branch they work at (if applicable)\n email character varying(128) NOT NULL UNIQUE,\n phone_extension character varying(20),\n hire_date date NOT NULL,\n termination_date date, -- Date of termination, null if currently employed\n manager_id character varying(64), -- Self-referencing key for manager relationship\n status character varying(32) NOT NULL, -- e.g., Active, Terminated, On Leave\n PRIMARY KEY (employee_id),\n FOREIGN KEY (branch_id) REFERENCES financial_services.branches(branch_id), -- Assuming a branches table exists\n FOREIGN KEY (manager_id) REFERENCES financial_services.employees(employee_id)\n)\n"} {"conversations": [{"role": "user", "content": "Find pairs of token transfers within the same transaction and for the same token, where the value of one transfer is exactly twice the value of the other. Show the transaction ID, token ID, and both transfer IDs and their values."}, {"role": "assistant", "content": "SELECT\n t1.transaction_id,\n t1.token_id,\n t1.transfer_id AS transfer_id_1,\n t1.value AS value_1,\n t2.transfer_id AS transfer_id_2,\n t2.value AS value_2\nFROM web3.token_transfers AS t1\nJOIN web3.token_transfers AS t2\n ON t1.transaction_id = t2.transaction_id\n AND t1.token_id = t2.token_id\n AND t1.transfer_id < t2.transfer_id\nWHERE\n t1.value = 2 * t2.value\n OR t2.value = 2 * t1.value;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.token_transfers (\n transfer_id character varying(64) NOT NULL, -- unique identifier for the transfer\n token_id character varying(64) NOT NULL, -- identifier of the token being transferred\n from_address character varying(128) NOT NULL, -- address of the sender\n to_address character varying(128) NOT NULL, -- address of the receiver\n value numeric(38,14) NOT NULL, -- amount of tokens transferred\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction containing the transfer\n log_index integer NOT NULL, -- index of the transfer log in the transaction\n PRIMARY KEY (transfer_id)\n)\n"} {"conversations": [{"role": "user", "content": "How many documents of each type exist in the system? Show the document type and the count."}, {"role": "assistant", "content": "SELECT document_type, COUNT(*) AS document_count\nFROM legal_services.documents\ngroup BY document_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text, first_name text, last_name text, company_name text, email text, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.law_firms ( firm_id text, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\nCREATE TABLE legal_services.documents ( document_id text, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version integer, description text )\nCREATE TABLE legal_services.time_entries ( entry_id text, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable boolean, is_billed boolean, invoice_id text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me all users who have wallets but have never placed any orders, along with their wallet addresses and creation dates."}, {"role": "assistant", "content": "SELECT u.user_id, u.email, w.address AS wallet_address, w.created_at FROM trading_platform.users u JOIN trading_platform.wallets w ON u.user_id = w.user_id LEFT JOIN trading_platform.orders o ON u.user_id = o.user_id WHERE o.order_id IS NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id character varying(64) NOT NULL, username character varying(128) NOT NULL, email character varying(128) NOT NULL, password_hash text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (user_id) )\nCREATE TABLE trading_platform.wallets ( wallet_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, address character varying(128) NOT NULL, private_key text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (wallet_id) )\nCREATE TABLE trading_platform.orders ( order_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, wallet_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, order_type character varying(32) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, status character varying(32) NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (order_id) )\nCREATE TABLE trading_platform.assets ( asset_id character varying(64) NOT NULL, name character varying(128) NOT NULL, symbol character varying(32) NOT NULL, type character varying(32) NOT NULL, PRIMARY KEY (asset_id) )\nCREATE TABLE trading_platform.dapps ( dapp_id character varying(64) NOT NULL, name character varying(128) NOT NULL, description text NOT NULL, url character varying(256) NOT NULL, PRIMARY KEY (dapp_id) )\nCREATE TABLE trading_platform.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\nCREATE TABLE trading_platform.logs ( log_id character varying(64) NOT NULL, user_id character varying(64), action character varying(128) NOT NULL, details text NOT NULL, logged_at timestamp NOT NULL, PRIMARY KEY (log_id) )\nCREATE TABLE trading_platform.notifications ( notification_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, message text NOT NULL, sent_at timestamp NOT NULL, read_at timestamp, PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "Could you show me each employee's full name along with their manager's full name?"}, {"role": "assistant", "content": "SELECT e.employee_id,\n e.first_name || ' ' || e.last_name AS employee_name,\n m.employee_id AS manager_id,\n m.first_name || ' ' || m.last_name AS manager_name\nFROM government_services.employees e\nLEFT JOIN government_services.employees m ON e.manager_employee_id = m.employee_id;"}, {"role": "user", "content": "Actually, only include employees who were hired after January 1, 2020."}, {"role": "assistant", "content": "SELECT e.employee_id,\n e.first_name || ' ' || e.last_name AS employee_name,\n m.employee_id AS manager_id,\n m.first_name || ' ' || m.last_name AS manager_name\nFROM government_services.employees e\nLEFT JOIN government_services.employees m ON e.manager_employee_id = m.employee_id\nWHERE e.hire_date > '2020-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.employees (\n employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n job_title character varying(150) NOT NULL,\n department character varying(100),\n work_email character varying(128) NOT NULL UNIQUE,\n work_phone character varying(32),\n hire_date date NOT NULL,\n termination_date date, -- null if currently employed\n access_level character varying(50), -- Role or permission level\n manager_employee_id character varying(64), -- FK to self for reporting structure\n PRIMARY KEY (employee_id)\n)\n"} {"conversations": [{"role": "user", "content": "Can you help me retrieve the list of components made of a specific material along with their supplier details?"}, {"role": "assistant", "content": "SMEMBERS material_components:mat:TI64\nHGETALL component:\nHGET component: supplier_id"}, {"role": "user", "content": "Can you also include the part number for each component in the result?"}, {"role": "assistant", "content": "SMEMBERS material_components:mat:TI64\nHGETALL component:\nHGET component: supplier_id\nHGET component: part_number"}, {"role": "user", "content": "If I want to filter out components from a specific supplier, how can I modify the query?"}, {"role": "assistant", "content": "SMEMBERS material_components:mat:TI64\nHGETALL component:\nHGET component: supplier_id\nHGET component: part_number\nIF HGET component: supplier_id != 'sup:ACME_AERO' THEN INCLUDE"}, {"role": "user", "content": "Can you also sort the results based on the part number?"}, {"role": "assistant", "content": "SMEMBERS material_components:mat:TI64\nHGETALL component:\nHGET component: supplier_id\nHGET component: part_number\nIF HGET component: supplier_id != 'sup:ACME_AERO' THEN INCLUDE\nSORT BY part_number ASC"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nUse Hashes. Key pattern: 'component:'. Example: HSET component:LGSTRUT01 part_number \"PN-5521-A\" component_name \"Landing Gear Strut\" material_id \"mat:TI64\" supplier_id \"sup:ACME_AERO\" ... Consider Sets for reverse lookups (e.g., 'material_components:' -> Set).\n"} {"conversations": [{"role": "user", "content": "Provide a list of all log entries recorded since the start of 2024, including the user ID, action, and the exact time the log occurred."}, {"role": "assistant", "content": "SELECT user_id, action, logged_at FROM logs WHERE logged_at >= '2024-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.wallets ( wallet_id.text, user_id.text, address.text, private_key.text, created_at.timestamp )\nCREATE TABLE trading_platform.utxos ( utxo_id.text, transaction_id.text, output_index.integer, address.text, amount.numeric, spent.boolean )\nCREATE TABLE trading_platform.logs ( log_id.text, user_id.text, action.text, details.text, logged_at.timestamp )\nCREATE TABLE trading_platform.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me all bookings with a status of 'confirmed' that were made in the last 7 days, including passenger_id and fare."}, {"role": "assistant", "content": "SELECT booking_id, passenger_id, fare FROM transportation.bookings WHERE status = 'confirmed' AND booking_time >= CURRENT_DATE - INTERVAL '7 days';"}, {"role": "user", "content": "Now include only bookings where the fare is greater than $50 and order them by booking_time in descending order."}, {"role": "assistant", "content": "SELECT booking_id, passenger_id, fare FROM transportation.bookings WHERE status = 'confirmed' AND booking_time >= CURRENT_DATE - INTERVAL '7 days' AND fare > 50 ORDER BY booking_time DESC;"}, {"role": "user", "content": "Can you also include the trip_id and filter to only show bookings for trip_id 'TRIP789'?"}, {"role": "assistant", "content": "SELECT booking_id, passenger_id, fare, trip_id FROM transportation.bookings WHERE status = 'confirmed' AND booking_time >= CURRENT_DATE - INTERVAL '7 days' AND fare > 50 AND trip_id = 'TRIP789' ORDER BY booking_time DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.bookings ( booking_id text PRIMARY KEY, passenger_id text, trip_id text, seat_number text, booking_time timestamp, status text, fare numeric, payment_transaction_id text, special_requests text )\n"} {"conversations": [{"role": "user", "content": "Find all wallet addresses that don't have an associated user_id."}, {"role": "assistant", "content": "SELECT address_id FROM blockchain.wallets WHERE user_id IS NULL;"}, {"role": "user", "content": "Now show me these addresses along with their private_key, and join with another table to see if they have any transactions."}, {"role": "assistant", "content": "SELECT w.address_id, w.private_key FROM blockchain.wallets w WHERE w.user_id IS NULL;"}, {"role": "user", "content": "Actually, I want to see the count of such wallet addresses grouped by the first 3 characters of their address_id."}, {"role": "assistant", "content": "SELECT SUBSTRING(address_id, 1, 3) as address_prefix, COUNT(*) as address_count FROM blockchain.wallets WHERE user_id IS NULL GROUP BY SUBSTRING(address_id, 1, 3);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.wallets ( wallet_id.text, user_id.text, address_id.text, private_key.text )\n"} {"conversations": [{"role": "user", "content": "What is the history of incidents or accidents that occurred on platform 5 at station GHI?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about the history of incidents or accidents on platform 5 at station GHI. My data is limited to the structural and operational details of the platforms, such as platform ID, station ID, and status. For incident history, you may need to consult a different database or contact the relevant authorities."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.platforms ( platform_id.text, station_id.text, platform_number.text, track_number.text, status.text, length_meters.numeric, accessible.boolean )\n"} {"conversations": [{"role": "user", "content": "List all medical records created in the last 7 days, including patient_id, doctor_id, and record_date."}, {"role": "assistant", "content": "SELECT patient_id, doctor_id, record_date FROM healthcare.medical_records WHERE created_at >= CURRENT_DATE - INTERVAL '7 days';"}, {"role": "user", "content": "Actually, I only need records where the treatment_plan is not empty."}, {"role": "assistant", "content": "SELECT patient_id, doctor_id, record_date FROM healthcare.medical_records WHERE created_at >= CURRENT_DATE - INTERVAL '7 days' AND treatment_plan IS NOT NULL AND treatment_plan != '';"}, {"role": "user", "content": "Can you also sort them by record_date in descending order?"}, {"role": "assistant", "content": "SELECT patient_id, doctor_id, record_date FROM healthcare.medical_records WHERE created_at >= CURRENT_DATE - INTERVAL '7 days' AND treatment_plan IS NOT NULL AND treatment_plan != '' ORDER BY record_date DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.medical_records ( record_id.text, patient_id.text, appointment_id.text, doctor_id.text, record_date.timestamp, chief_complaint.text, present_illness_history.text, past_medical_history.text, physical_examination_notes.text, assessment.text, treatment_plan.text, vitals.json, created_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 projects by valuation that have completed fundraising rounds in the last 6 months, along with their token symbol and current price from the token_basic_info table."}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.valuation, tbi.token_symbol, tbi.price FROM project_fundraising_record pfr LEFT JOIN token_basic_info tbi ON pfr.project_id = tbi.coin_id WHERE pfr.investment_date >= DATE_SUB(CURRENT_DATE, INTERVAL 6 MONTH) ORDER BY pfr.valuation DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the 24-hour trading volume for these projects' tokens and filter to only include projects with valuation over $100 million?"}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.valuation, tbi.token_symbol, tbi.price, tbi.total_volume FROM project_fundraising_record pfr LEFT JOIN token_basic_info tbi ON pfr.project_id = tbi.coin_id WHERE pfr.investment_date >= DATE_SUB(CURRENT_DATE, INTERVAL 6 MONTH) AND pfr.valuation > 100000000 ORDER BY pfr.valuation DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\n \"CREATE TABLE project_fundraising_record (\",\n \"id character varying(32) NOT NULL, -- fundraising record id\",\n \"project_id character varying(32) NOT NULL, -- the invested project's id\",\n \"project_name character varying(128) NOT NULL, -- name of the invested project\",\n \"rounds_name character varying(32), -- name of the fundraising round\",\n \"investment_value numeric(38,14), -- amount of the fundraising in USD\",\n \"investment_date character varying(128), -- the date of the investment happened\",\n \"introduction character varying(128), -- the introduction of the invested project\",\n \"valuation numeric(38,14), -- the valuation of the project in USD when invested\",\n\n \"CREATE TABLE token_basic_info (\",\n \"coin_id character varying(100) NOT NULL, -- the id of the token\",\n \"token_name character varying(100) NOT NULL, -- the token's name\",\n \"token_symbol character varying(100) NOT NULL, -- the token's symbol\",\n \"token_address character varying(100) NOT NULL, -- the token's address\",\n \"chain text, -- the chain that the token resides\",\n \"price double precision, -- the current price of the token\",\n \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour\",\n \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours\",\n \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days\",\n \"highest_price_24h double precision, -- the highest price of the token in 24 hours\",\n \"lowest_price_24h double precision, -- the lowest price of the token in 24 hours\",\n \"market_cap double precision, -- the market cap of the token\",\n \"market_cap_rank bigint, -- the rank of the token market cap in desc\",\n \"market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours\",\n \"total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX)\", \n \"narrative text, -- the category or narrative of the token\",\n \"trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token.\",\n \",PRIMARY KEY (coin_id, chain));\",\n\n \"CREATE TABLE narrative_info (\",\n \"narrative character varying(512) NOT NULL, -- the id of narrative\",\n \"top_3_coins text, -- the top 3 tokens in the narrative\",\n \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative\",\n \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative\",\n \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative\",\n \"market_cap double precision, -- the market cap of the narrative\",\n \"volume_24h double precision, -- the trade volume of the narrative\",\n \"trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative\",\n \"token_num bigint, -- total token number in the narrative\",\n \",PRIMARY KEY (narrative));\"\n\n \"CREATE TABLE cex_token_balance (\",\n \"snapshot_time character varying(32) NOT NULL, -- the snapshot time of record, converted from original timestamp\",\n \"chain character varying(128) NOT NULL, -- the chain that the token resides\",\n \"address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX\",\n \"exchange character varying(512) NOT NULL, -- a centralized exchange name\",\n \"token_address character varying(128) NOT NULL, -- token contract address\",\n \"token_symbol character varying(512), --token symbol\",\n \"balance numeric(38,10), -- token balance\",\n \"usd_value numeric(38,14), -- value of the token held in USD\",\n \"price double precision, --price of the token in USD\",\n \",PRIMARY KEY (snapshot_time, exchange, address, chain, token_address));\"\n\n \"CREATE TABLE smart_money_token_performance (\",\n \"token_address character varying(100) NOT NULL, -- the token's address\",\n \"token_symbol character varying(100), -- the tokens's symbol\",\n \"pnl numeric(38,2), -- the profit users made on this token\",\n \"net_flow numeric(38,2), -- the netflow of the token, means the money user spent minus the the money user sold of this token\",\n \"avg_cost numeric(38,16), -- the average cost price of user spent on this token\",\n \"price double precision, -- the current price of the token\",\n \"realized_ratio numeric(10,2), -- the ratio user sold of the token\",\n \"roi numeric(10,2), -- the roi users made of this token\",\n \"chain character varying(100), -- the chain that the token resides\",\n \"PRIMARY KEY (token_address, chain));\",\n\n"} {"conversations": [{"role": "user", "content": "List game titles released on the 'PC' platform along with the count of servers currently hosting each game."}, {"role": "assistant", "content": "SELECT T1.title, count(T2.server_id) FROM games AS T1 JOIN servers AS T2 ON T1.game_id = T2.game_id WHERE T1.platform = 'PC' GROUP BY T1.title;"}, {"role": "user", "content": "Now, only show games with more than 3 servers and sort the results by the server count in descending order."}, {"role": "assistant", "content": "SELECT T1.title, count(T2.server_id) AS server_count FROM games AS T1 JOIN servers AS T2 ON T1.game_id = T2.game_id WHERE T1.platform = 'PC' GROUP BY T1.title HAVING count(T2.server_id) > 3 ORDER BY server_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players (\n player_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the player\n username character varying(100) NOT NULL UNIQUE, -- player's chosen display name\n email character varying(255) NOT NULL UNIQUE, -- player's email address for login/recovery\n password_hash text NOT NULL, -- securely hashed password\n registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the player account was created\n last_login timestamp with time zone, -- timestamp of the last successful login\n country_code character(2), -- player's country (ISO 3166-1 alpha-2)\n status character varying(20) NOT NULL DEFAULT 'active', -- account status (e.g., active, banned, suspended)\n profile_data jsonb, -- flexible field for avatar url, bio, preferences etc.\n PRIMARY KEY (player_id)\n)\nCREATE TABLE gaming_technology.games (\n game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n title character varying(200) NOT NULL, -- official title of the game\n developer_id uuid NOT NULL, -- FK linking to the developers table\n publisher_id uuid, -- FK linking to a potential publishers table (optional)\n genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n release_date date, -- official release date\n description text, -- short description or synopsis of the game\n platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n website character varying(255), -- official website URL\n PRIMARY KEY (game_id)\n -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.game_sessions (\n session_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game session\n player_id uuid NOT NULL, -- FK linking to the players table\n game_id uuid NOT NULL, -- FK linking to the games table\n server_id uuid, -- FK linking to the servers table (nullable for single-player)\n start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the session began\n end_time timestamp with time zone, -- when the session ended (null if ongoing)\n duration_seconds integer, -- calculated duration of the session in seconds\n score integer, -- player's score for the session, if applicable\n session_data jsonb, -- flexible field for session-specific info (e.g., map played, character used)\n PRIMARY KEY (session_id)\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id),\n -- FOREIGN KEY (server_id) REFERENCES gaming_technology.servers(server_id)\n)\nCREATE TABLE gaming_technology.servers (\n server_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game server instance\n game_id uuid NOT NULL, -- FK linking to the game this server hosts\n server_name character varying(150), -- display name for the server\n region character varying(50) NOT NULL, -- geographical region (e.g., us-east-1, eu-west-2)\n ip_address character varying(45), -- IP address (IPv4 or IPv6)\n port integer, -- network port number\n current_players integer NOT NULL DEFAULT 0, -- number of players currently connected\n max_players integer NOT NULL, -- maximum player capacity\n status character varying(30) NOT NULL DEFAULT 'offline', -- server status (e.g., online, offline, maintenance)\n last_heartbeat timestamp with time zone, -- last time the server reported its status\n PRIMARY KEY (server_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.achievements (\n achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an achievement definition\n game_id uuid NOT NULL, -- FK linking to the game the achievement belongs to\n name character varying(150) NOT NULL, -- name of the achievement\n description text NOT NULL, -- how to unlock the achievement\n icon_url character varying(255), -- URL for the achievement's icon\n points integer DEFAULT 0, -- points awarded for unlocking (optional)\n hidden boolean DEFAULT false, -- whether the achievement details are hidden until unlocked\n PRIMARY KEY (achievement_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_achievements (\n player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n PRIMARY KEY (player_achievement_id),\n UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\nCREATE TABLE gaming_technology.in_game_items (\n item_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the item definition\n game_id uuid NOT NULL, -- FK linking to the game this item belongs to\n item_name character varying(150) NOT NULL, -- name of the item\n item_type character varying(50) NOT NULL, -- type (e.g., Cosmetic, Consumable, Weapon, Armor)\n description text, -- description of the item\n rarity character varying(30), -- item rarity (e.g., Common, Rare, Epic, Legendary)\n cost_currency character varying(10), -- currency code if purchasable (e.g., USD, EUR, GOLD)\n cost_amount numeric(12, 2), -- price if purchasable\n attributes jsonb, -- flexible field for item stats or properties\n PRIMARY KEY (item_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_inventory (\n inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an inventory entry\n player_id uuid NOT NULL, -- FK linking to the player owning the item\n item_id uuid NOT NULL, -- FK linking to the item definition\n quantity integer NOT NULL DEFAULT 1, -- number of items held (for stackable items)\n acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the item was acquired\n instance_data jsonb, -- data specific to this instance (e.g., weapon mods, durability)\n PRIMARY KEY (inventory_id),\n -- Optional unique constraint if items are non-stackable or unique instances\n -- UNIQUE (player_id, item_id) -- Use if quantity is always 1\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (item_id) REFERENCES gaming_technology.in_game_items(item_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me all home loans (loan_id, principal_amount, interest_rate) where the current principal balance is more than 75% of the original principal amount, along with the account_id and employee details (first_name, last_name) of the employee who processed the loan application."}, {"role": "assistant", "content": "SELECT l.loan_id, l.principal_amount, l.interest_rate, l.account_id, e.first_name, e.last_name FROM financial_services.loans l JOIN financial_services.employees e ON l.account_id = e.employee_id WHERE l.loan_type = 'Home' AND l.current_principal_balance > (l.principal_amount * 0.75)"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.transactions ( transaction_id.text, account_id.text, related_account_id.text, transaction_type.text, amount.numeric, currency.text, transaction_date.timestamp, effective_date.date, description.text, status.text, reference_number.text )\nCREATE TABLE financial_services.securities ( security_id.text, ticker_symbol.text, isin_code.text, cusip_code.text, security_name.text, security_type.text, exchange.text, currency.text, issuer_name.text, sector.text, last_updated.timestamp )\nCREATE TABLE financial_services.market_data ( data_point_id.bigint, security_id.text, data_timestamp.timestamp, open_price.numeric, high_price.numeric, low_price.numeric, close_price.numeric, adjusted_close_price.numeric, volume.bigint, source.text )\nCREATE TABLE financial_services.employees ( employee_id.text, first_name.text, last_name.text, job_title.text, department.text, branch_id.text, email.text, phone_extension.text, hire_date.date, termination_date.date, manager_id.text, status.text )\nCREATE TABLE financial_services.loans ( loan_id.text, account_id.text, loan_type.text, principal_amount.numeric, current_principal_balance.numeric, interest_rate.numeric, term_months.integer, origination_date.date, maturity_date.date, monthly_payment.numeric, collateral_description.text, status.text )\n"} {"conversations": [{"role": "user", "content": "List all follow IDs that were created on '2024-06-18'."}, {"role": "assistant", "content": "SELECT follow_id FROM social_media.follows WHERE DATE(created_at) = '2024-06-18';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.follows ( follow_id.text, follower_user_id.text, following_user_id.text, created_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "What are the qualifications or training history of the staff member who performed the maintenance with record_id 'REC123'?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about the qualifications or training history of staff members as this data is not stored in the maintenance_records table. This table only contains details about maintenance activities, such as asset information, maintenance type, dates, and costs. If you have another question or need assistance with data available in this table, I'm happy to help."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.maintenance_records (\n record_id character varying(64) NOT NULL, -- Unique identifier for the maintenance record\n asset_id character varying(64) NOT NULL, -- ID of the asset being maintained (train_id, car_id, platform_id, etc.)\n asset_type character varying(32) NOT NULL, -- Type of asset ('Train', 'Car', 'Platform', 'Track')\n maintenance_type character varying(128) NOT NULL, -- e.g., 'Scheduled Inspection', 'Repair', 'Cleaning'\n staff_id character varying(64), -- Staff member performing/overseeing maintenance\n start_datetime timestamp NOT NULL, -- When maintenance started\n end_datetime timestamp, -- When maintenance completed (nullable if ongoing)\n description text NOT NULL, -- Details of the maintenance performed\n cost numeric(12, 2), -- Cost associated with the maintenance\n status character varying(32) NOT NULL DEFAULT 'Completed', -- e.g., 'Scheduled', 'In Progress', 'Completed', 'Cancelled'\n PRIMARY KEY (record_id),\n FOREIGN KEY (staff_id) REFERENCES train_station_management.staff(staff_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all insurance plans along with their provider, plan type, and the contact phone number. Also, for each plan, show how many doctors have their hospital affiliation ID matching the plan ID."}, {"role": "assistant", "content": "SELECT ip.plan_id, ip.plan_name, ip.insurance_provider, ip.plan_type, ip.contact_phone, COUNT(d.doctor_id) FROM healthcare.insurance_plans ip LEFT JOIN healthcare.doctors d ON ip.plan_id = d.hospital_affiliation_id GROUP BY ip.plan_id, ip.plan_name, ip.insurance_provider, ip.plan_type, ip.contact_phone"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.doctors ( doctor_id text, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id text, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\n"} {"conversations": [{"role": "user", "content": "I need to find all components associated with a specific supplier. Can you help with that?"}, {"role": "assistant", "content": "HGETALL component:\nIF HGET component: supplier_id = 'sup:ACME_AERO' THEN INCLUDE"}, {"role": "user", "content": "Can you also show me the material ID for each of these components?"}, {"role": "assistant", "content": "HGETALL component:\nIF HGET component: supplier_id = 'sup:ACME_AERO' THEN INCLUDE\nHGET component: material_id"}, {"role": "user", "content": "What if I want to exclude components with a specific material ID?"}, {"role": "assistant", "content": "HGETALL component:\nIF HGET component: supplier_id = 'sup:ACME_AERO' THEN INCLUDE\nHGET component: material_id\nIF HGET component: material_id != 'mat:TI64' THEN INCLUDE"}, {"role": "user", "content": "Can you add the component name to the result as well?"}, {"role": "assistant", "content": "HGETALL component:\nIF HGET component: supplier_id = 'sup:ACME_AERO' THEN INCLUDE\nHGET component: material_id\nIF HGET component: material_id != 'mat:TI64' THEN INCLUDE\nHGET component: component_name"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nUse Hashes. Key pattern: 'component:'. Example: HSET component:LGSTRUT01 part_number \"PN-5521-A\" component_name \"Landing Gear Strut\" material_id \"mat:TI64\" supplier_id \"sup:ACME_AERO\" ... Consider Sets for reverse lookups (e.g., 'material_components:' -> Set).\n"} {"conversations": [{"role": "user", "content": "For each property, show the most expensive room type by base_rate, including the property name, room type name, and the highest base_rate."}, {"role": "assistant", "content": "SELECT p.property_name,\n rt.type_name,\n MAX(rt.base_rate) AS max_base_rate\nFROM hospitality_technology.room_types rt\nJOIN hospitality_technology.properties p\n ON rt.property_id = p.property_id\nGROUP BY p.property_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text PRIMARY KEY, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.rooms (\n room_id character varying(64) NOT NULL, -- unique identifier for the room\n property_id character varying(64) NOT NULL, -- FK to properties table\n room_number character varying(10) NOT NULL, -- room number identifier (e.g., '101', 'Suite 2B')\n room_type_id character varying(64) NOT NULL, -- FK to room_types table\n floor integer, -- floor number the room is on\n status character varying(50) NOT NULL, -- e.g., Available, Occupied, Cleaning, OutOfOrder, Maintenance\n is_smoking boolean NOT NULL DEFAULT false, -- smoking allowed flag\n features text, -- description of features (e.g., Balcony, Sea View, Jacuzzi)\n current_condition text, -- notes on room condition\n last_cleaned_at timestamp with time zone, -- timestamp of last cleaning\n PRIMARY KEY (room_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.room_types ( room_type_id text, property_id text, type_name text, description text, base_rate numeric, max_occupancy integer, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.guests ( guest_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id text, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level integer, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.services (\n service_id character varying(64) NOT NULL, -- unique identifier for a chargeable service\n property_id character varying(64) NOT NULL, -- FK to properties table\n service_name character varying(150) NOT NULL, -- e.g., Room Service - Burger, Spa - Massage 60min, Laundry - Shirt\n description text,\n category character varying(100), -- e.g., Food & Beverage, Wellness, Business Center, Activities\n price numeric(10, 2) NOT NULL, -- price per unit/instance\n unit character varying(30), -- e.g., Per Item, Per Hour, Per Day\n is_available boolean NOT NULL DEFAULT true, -- is the service currently offered?\n department character varying(100), -- department responsible (e.g., F&B, Spa, Housekeeping)\n PRIMARY KEY (service_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\nCREATE TABLE hospitality_technology.payments (\n payment_id character varying(64) NOT NULL, -- unique identifier for the payment transaction\n reservation_id character varying(64), -- FK to reservations (if payment is for a stay)\n guest_id character varying(64) NOT NULL, -- FK to guests (who paid)\n bill_id character varying(64), -- FK to bills/invoices this payment applies to\n amount numeric(12,2) NOT NULL, -- amount of the payment\n currency_code character varying(3) NOT NULL, -- ISO currency code (e.g., USD, EUR)\n payment_method character varying(50) NOT NULL, -- e.g., CreditCard, Cash, BankTransfer, Points, Voucher\n card_type character varying(50), -- e.g., Visa, MasterCard, Amex (if CC)\n card_last_four character varying(4), -- last 4 digits of CC (if CC)\n transaction_ref character varying(128), -- reference ID from payment gateway or processor\n payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the payment occurred\n status character varying(50) NOT NULL, -- e.g., Pending, Succeeded, Failed, Refunded, Disputed\n staff_id_processed character varying(64), -- FK to staff (who processed the payment)\n notes text, -- notes about the payment\n PRIMARY KEY (payment_id),\n FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "How many lawyers are there in each specialization?"}, {"role": "assistant", "content": "SELECT specialization, COUNT(*) AS lawyer_count\nFROM legal_services.lawyers\nGROUP BY specialization;"}, {"role": "user", "content": "Only include specializations with more than 5 lawyers."}, {"role": "assistant", "content": "SELECT specialization, COUNT(*) AS lawyer_count\nFROM legal_services.lawyers\nGROUP BY specialization\nHAVING COUNT(*) > 5;"}, {"role": "user", "content": "Also display the average years since hire for each specialization."}, {"role": "assistant", "content": "SELECT specialization,\n COUNT(*) AS lawyer_count,\n AVG(EXTRACT(YEAR FROM AGE(CURRENT_DATE, hire_date)))::numeric(5,2) AS avg_years_since_hire\nFROM legal_services.lawyers\nGROUP BY specialization\nHAVING COUNT(*) > 5;"}, {"role": "user", "content": "Sort the results by lawyer_count descending and limit to the top 3 specializations."}, {"role": "assistant", "content": "SELECT specialization,\n COUNT(*) AS lawyer_count,\n AVG(EXTRACT(YEAR FROM AGE(CURRENT_DATE, hire_date)))::numeric(5,2) AS avg_years_since_hire\nFROM legal_services.lawyers\nGROUP BY specialization\nHAVING COUNT(*) > 5\nORDER BY lawyer_count DESC\nLIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers ( lawyer_id.text, first_name.text, last_name.text, bar_number.text, firm_id.text, email.text, phone.text, specialization.text, hire_date.timestamp, is_partner.boolean )\n"} {"conversations": [{"role": "user", "content": "List tokens that have a 24-hour trading volume greater than $10,000,000 and a negative price change percentage over the last 24 hours. Show the token symbol, chain, total volume, and the 24-hour price change percentage."}, {"role": "assistant", "content": "SELECT token_symbol, chain, total_volume, price_change_percentage_24h FROM token_basic_info WHERE CAST(REPLACE(total_volume, ',', '') AS numeric) > 10000000 AND price_change_percentage_24h < 0"}, {"role": "user", "content": "From those results, filter further to only include tokens with a market cap rank of 100 or better. Order the results by 24-hour trading volume in descending order."}, {"role": "assistant", "content": "SELECT token_symbol, chain, total_volume, price_change_percentage_24h FROM token_basic_info WHERE CAST(REPLACE(total_volume, ',', '') AS numeric) > 10000000 AND price_change_percentage_24h < 0 AND market_cap_rank IS NOT NULL AND market_cap_rank <= 100 ORDER BY CAST(REPLACE(total_volume, ',', '') AS numeric) DESC"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_basic_info ( coin_id text, token_name text, token_symbol text, token_address text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, highest_price_24h numeric, lowest_price_24h numeric, market_cap numeric, market_cap_rank numeric, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank numeric )\n"} {"conversations": [{"role": "user", "content": "Show all users who have liked comments made by users with a specified location, say 'Paris'. For each, show their username, the comment_id, and the location of the comment's author."}, {"role": "assistant", "content": "SELECT l.user_id AS liker_user_id, u_liker.username, l.comment_id, u_author.location AS comment_author_location\nFROM social_media.likes l\nJOIN social_media.comments c ON l.comment_id = c.comment_id\nJOIN social_media.users u_author ON c.user_id = u_author.user_id\nJOIN social_media.users u_liker ON l.user_id = u_liker.user_id\nWHERE u_author.location = 'Paris';"}, {"role": "user", "content": "Actually, please also include the full name of the user who made the comment, and restrict to likes created after April 1, 2024."}, {"role": "assistant", "content": "SELECT l.user_id AS liker_user_id, u_liker.username, l.comment_id, u_author.location AS comment_author_location, u_author.full_name AS comment_author_full_name\nFROM social_media.likes l\nJOIN social_media.comments c ON l.comment_id = c.comment_id\nJOIN social_media.users u_author ON c.user_id = u_author.user_id\nJOIN social_media.users u_liker ON l.user_id = u_liker.user_id\nWHERE u_author.location = 'Paris' AND l.created_at >= '2024-04-01';"}, {"role": "user", "content": "I see duplicate users for the same comment. Show only unique username-comment_id pairs, and order the results by liker username ascending."}, {"role": "assistant", "content": "SELECT DISTINCT u_liker.username, l.comment_id, u_author.location AS comment_author_location, u_author.full_name AS comment_author_full_name\nFROM social_media.likes l\nJOIN social_media.comments c ON l.comment_id = c.comment_id\nJOIN social_media.users u_author ON c.user_id = u_author.user_id\nJOIN social_media.users u_liker ON l.user_id = u_liker.user_id\nWHERE u_author.location = 'Paris' AND l.created_at >= '2024-04-01'\nORDER BY u_liker.username ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(50) NOT NULL UNIQUE, -- user's unique handle\n email character varying(128) NOT NULL UNIQUE, -- user's email address\n password_hash text NOT NULL, -- hashed password\n full_name character varying(100), -- user's full name\n profile_picture_url text, -- URL to the profile picture\n bio text, -- short user biography\n location character varying(100), -- user's location\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of account creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last profile update\n is_verified boolean NOT NULL DEFAULT false, -- verification status\n PRIMARY KEY (user_id)\n)\nCREATE TABLE social_media.comments (\n comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n content text NOT NULL, -- textual content of the comment\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n PRIMARY KEY (comment_id)\n)\nCREATE TABLE social_media.likes (\n like_id character varying(64) NOT NULL, -- unique identifier for the like\n user_id character varying(64) NOT NULL, -- identifier of the user who liked (FK to users.user_id)\n post_id character varying(64), -- identifier of the post being liked (FK to posts.post_id, nullable)\n comment_id character varying(64), -- identifier of the comment being liked (FK to comments.comment_id, nullable)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the like occurred\n PRIMARY KEY (like_id),\n CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), -- prevent duplicate likes\n CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) -- ensure it likes something\n)\nCREATE TABLE social_media.follows (\n follow_id character varying(64) NOT NULL, -- unique identifier for the follow relationship\n follower_user_id character varying(64) NOT NULL, -- identifier of the user who is following (FK to users.user_id)\n following_user_id character varying(64) NOT NULL, -- identifier of the user being followed (FK to users.user_id)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the follow started\n PRIMARY KEY (follow_id),\n CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) -- prevent duplicate follows\n)\nCREATE TABLE social_media.hashtags (\n hashtag_id character varying(64) NOT NULL, -- unique identifier for the hashtag\n tag_name character varying(100) NOT NULL UNIQUE, -- the actual hashtag text (without '#')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when the hashtag was first used\n PRIMARY KEY (hashtag_id)\n)\nCREATE TABLE social_media.conversations (\n conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated\n last_message_at timestamp, -- timestamp of the last message in the conversation\n is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message\n group_name character varying(100), -- name of the group chat (if applicable)\n PRIMARY KEY (conversation_id)\n)\nCREATE TABLE social_media.conversation_participants (\n participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n PRIMARY KEY (participant_id),\n CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n read_at timestamp, -- timestamp notification was marked as read\n PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings (\n setting_id character varying(64) NOT NULL, -- unique identifier for the setting entry\n user_id character varying(64) NOT NULL UNIQUE, -- user the settings belong to (FK to users.user_id)\n theme character varying(20) DEFAULT 'light', -- UI theme ('light', 'dark')\n email_notifications_enabled boolean DEFAULT true, -- enable/disable email notifications\n push_notifications_enabled boolean DEFAULT true, -- enable/disable push notifications\n private_profile boolean DEFAULT false, -- is the user profile private\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last setting change\n PRIMARY KEY (setting_id)\n)\n"} {"conversations": [{"role": "user", "content": "What is the reason behind the cost variation for maintenance of asset_id 'ASSET456' over the past year?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the reasons behind cost variations for maintenance. The data in the maintenance_records table includes only the cost amount and other basic details of each maintenance record, but it does not contain explanations or factors influencing cost changes."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.maintenance_records ( record_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, asset_type character varying(32) NOT NULL, maintenance_type character varying(128) NOT NULL, staff_id character varying(64), start_datetime timestamp NOT NULL, end_datetime timestamp, description text NOT NULL, cost numeric(12, 2), status character varying(32) NOT NULL DEFAULT 'Completed', PRIMARY KEY (record_id), FOREIGN KEY (staff_id) REFERENCES train_station_management.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "Show for every asset the usernames of users who have both bought and sold that asset, along with the asset name."}, {"role": "assistant", "content": "SELECT DISTINCT a.asset_id, a.name AS asset_name, u.username\nFROM trading_platform.assets a\nJOIN trading_platform.trades t_buyer ON t_buyer.asset_id = a.asset_id\nJOIN trading_platform.users u ON u.user_id = t_buyer.buyer_id\nWHERE EXISTS (\n SELECT 1 FROM trading_platform.trades t_seller \n WHERE t_seller.asset_id = a.asset_id AND t_seller.seller_id = t_buyer.buyer_id\n);"}, {"role": "user", "content": "Only include assets where at least 2 different users have both bought and sold them, and list the number of such users."}, {"role": "assistant", "content": "SELECT a.asset_id, a.name AS asset_name, COUNT(DISTINCT u.user_id) AS user_count\nFROM trading_platform.assets a\nJOIN trading_platform.trades t_buyer ON t_buyer.asset_id = a.asset_id\nJOIN trading_platform.users u ON u.user_id = t_buyer.buyer_id\nWHERE EXISTS (\n SELECT 1 FROM trading_platform.trades t_seller \n WHERE t_seller.asset_id = a.asset_id AND t_seller.seller_id = t_buyer.buyer_id\n)\nGROUP BY a.asset_id, a.name\nHAVING COUNT(DISTINCT u.user_id) >= 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.trades (\n trade_id character varying(64) NOT NULL, -- unique identifier for the trade\n order_id character varying(64) NOT NULL, -- identifier of the order that led to the trade\n buyer_id character varying(64) NOT NULL, -- identifier of the buyer\n seller_id character varying(64) NOT NULL, -- identifier of the seller\n asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n quantity numeric(38,14) NOT NULL, -- quantity of the asset in the trade\n price numeric(38,14) NOT NULL, -- price per unit of the asset\n traded_at timestamp NOT NULL, -- time when the trade was executed\n PRIMARY KEY (trade_id)\n)\nCREATE TABLE trading_platform.assets (\n asset_id character varying(64) NOT NULL, -- unique identifier for the asset\n name character varying(128) NOT NULL, -- name of the asset\n symbol character varying(32) NOT NULL, -- symbol of the asset\n type character varying(32) NOT NULL, -- type of the asset (e.g., cryptocurrency, stock)\n PRIMARY KEY (asset_id)\n)\nCREATE TABLE trading_platform.dapps (\n dapp_id character varying(64) NOT NULL, -- unique identifier for the DApp\n name character varying(128) NOT NULL, -- name of the DApp\n description text NOT NULL, -- description of the DApp\n url character varying(256) NOT NULL, -- URL of the DApp\n PRIMARY KEY (dapp_id)\n)\n"} {"conversations": [{"role": "user", "content": "How many notifications have been sent for comments in total?"}, {"role": "assistant", "content": "SELECT COUNT(*)\nFROM social_media.notifications\nWHERE target_entity_type = 'comment';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id.text, username.text, email.text, password_hash.text, full_name.text, profile_picture_url.text, bio.text, location.text, created_at.timestamp, updated_at.timestamp, is_verified.boolean )\nCREATE TABLE social_media.likes ( like_id.text, user_id.text, post_id.text, comment_id.text, created_at.timestamp )\nCREATE TABLE social_media.follows ( follow_id.text, follower_user_id.text, following_user_id.text, created_at.timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id.text, tag_name.text, created_at.timestamp )\nCREATE TABLE social_media.notifications ( notification_id.text, recipient_user_id.text, sender_user_id.text, notification_type.text, target_entity_id.text, target_entity_type.text, created_at.timestamp, read_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me pairs of passengers who share the same loyalty program, including their IDs, first and last names, and the loyalty_program_id."}, {"role": "assistant", "content": "SELECT p1.passenger_id AS passenger1_id, p1.first_name AS first1, p1.last_name AS last1, p2.passenger_id AS passenger2_id, p2.first_name AS first2, p2.last_name AS last2, p1.loyalty_program_id FROM transportation.passengers p1 JOIN transportation.passengers p2 ON p1.loyalty_program_id = p2.loyalty_program_id AND p1.passenger_id < p2.passenger_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.passengers ( passenger_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, loyalty_program_id text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "List all DApps that have 'wallet' in their description, along with their URLs."}, {"role": "assistant", "content": "SELECT name, url FROM trading_platform.dapps WHERE description LIKE '%wallet%';"}, {"role": "user", "content": "Now show only DApps created in the last year, and include their creation date."}, {"role": "assistant", "content": "SELECT name, url, created_at FROM trading_platform.dapps WHERE description LIKE '%wallet%' AND created_at >= NOW() - INTERVAL '1 year';"}, {"role": "user", "content": "Actually, I want to see the count of such DApps grouped by month of creation."}, {"role": "assistant", "content": "SELECT DATE_TRUNC('month', created_at) AS month, COUNT(*) AS dapp_count FROM trading_platform.dapps WHERE description LIKE '%wallet%' AND created_at >= NOW() - INTERVAL '1 year' GROUP BY month ORDER BY month;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id.text, username.text, email.text, password_hash.text, created_at.timestamp )\nCREATE TABLE trading_platform.dapps ( dapp_id.text, name.text, description.text, url.text )\n"} {"conversations": [{"role": "user", "content": "List all ERC20 tokens with their names and symbols where the price is greater than $100, sorted by price in descending order."}, {"role": "assistant", "content": "SELECT scm.name, scm.symbol, tpl.price FROM sui_coins_metadata scm JOIN token_prices_latest tpl ON scm.coin_type = tpl.address WHERE tpl.price > 100 ORDER BY tpl.price DESC;"}, {"role": "user", "content": "I think there's an error in your query - it should be joining on address not coin_type. Also, can you add the decimals to the results?"}, {"role": "assistant", "content": "SELECT scm.name, scm.symbol, scm.decimals, tpl.price FROM sui_coins_metadata scm JOIN token_prices_latest tpl ON scm.object_id = tpl.address WHERE tpl.price > 100 ORDER BY tpl.price DESC;"}, {"role": "user", "content": "Now filter these results to only show tokens with decimals equal to 18 and limit to the top 10."}, {"role": "assistant", "content": "SELECT scm.name, scm.symbol, scm.decimals, tpl.price FROM sui_coins_metadata scm JOIN token_prices_latest tpl ON scm.object_id = tpl.address WHERE tpl.price > 100 AND scm.decimals = 18 ORDER BY tpl.price DESC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_coins_metadata ( object_id.text, coin_type.text, status.text, decimals.bigint, description.text, icon_url.text, symbol.text, name.text )\nCREATE TABLE sui_nfts ( object_id.text, status.text, collection_type.text, package_id.text, previous_transaction.text, display.text, owner.text, name.text )\nCREATE TABLE nft_metadata ( blockchain.text, contract_address.text, token_id.text, contract_name.text, erc_type.text, amount.bigint, minter.text, owner.text, mint_block_number.bigint, mint_time.bigint, mint_transaction_hash.text, mint_price.text, token_uri.text, metadata.text, name.text, image_uri.text, traits.text, updated_at.bigint, status.text, rarity_score.real, rarity_rank.integer, unique_attribute_count.integer, pk.integer )\nCREATE TABLE token_prices_latest ( blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE erc20_approval ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text, pk.integer )\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_info_bitcoin ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_avalanche ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.decimal, amount.decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text, minted.decimal, holders.decimal, txs.decimal, updated_timestamp.timestamp, completed_timestamp.timestamp, id.text )\n"} {"conversations": [{"role": "user", "content": "能否帮我统计特定车站(station_id 为 'station_xyz')的所有工作人员数量？"}, {"role": "assistant", "content": "MATCH (s:Station {station_id: 'station_xyz'})<-[:BASED_AT]-(staff:Staff)\nRETURN COUNT(staff) AS total_staff"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// Node Label: :Station\n// Properties:\n// station_id: String (Constraint: UNIQUE)\n// station_name: String\n// city: String (Index recommended)\n// state_province: String\n// country_code: String\n// address: String\n// timezone: String\n// number_of_platforms: Integer\n// created_at: DateTime\n// last_updated_at: DateTime\n// Example Cypher CREATE:\n// CREATE (:Station {station_id: 'station_xyz', station_name: 'Grand Central Terminal', city: 'New York', ...})\n// Node Label: :Platform\n// Properties:\n// platform_id: String (Constraint: UNIQUE)\n// platform_number: String\n// track_number: String\n// status: String\n// length_meters: Float\n// accessible: Boolean\n// Relationship: (:Platform)-[:LOCATED_AT]->(:Station)\n// Example Cypher CREATE:\n// MATCH (s:Station {station_id: 'station_xyz'})\n// CREATE (p:Platform {platform_id: 'plat_123', ...})-[:LOCATED_AT]->(s)\n// Node Label: :Train\n// Properties:\n// train_id: String (Constraint: UNIQUE)\n// train_number: String (Constraint: UNIQUE)\n// model: String\n// manufacturer: String\n// year_manufactured: Integer\n// capacity: Integer\n// status: String\n// last_maintenance_date: Date\n// next_maintenance_date: Date\n// Example Cypher CREATE:\n// CREATE (:Train {train_id: 'train_789', train_number: 'Acela 2151', ...})\n// Node Label: :TrainCar\n// Properties:\n// car_id: String (Constraint: UNIQUE)\n// car_number: String\n// car_type: String\n// class: String\n// capacity: Integer\n// features: String (Or List if driver supports)\n// Relationship: (:TrainCar)-[:PART_OF_TRAIN]->(:Train)\n// Example Cypher CREATE:\n// MATCH (t:Train {train_id: 'train_789'})\n// CREATE (c:TrainCar {car_id: 'car_abc', ...})-[:PART_OF_TRAIN]->(t)\n// Node Label: :Route\n// Properties:\n// route_id: String (Constraint: UNIQUE)\n// route_name: String\n// description: String\n// is_active: Boolean\n// Relationships:\n// (:Route)-[:STARTS_AT]->(:Station)\n// (:Route)-[:ENDS_AT]->(:Station)\n// Example Cypher CREATE:\n// MATCH (origin:Station {station_id: 'station_bos'}), (dest:Station {station_id: 'station_was'})\n// CREATE (r:Route {route_id: 'route_ne_corr', ...})-[:STARTS_AT]->(origin), (r)-[:ENDS_AT]->(dest)\n// Relationship: (:Route)-[rel:HAS_STOP]->(:Station)\n// Relationship Properties on :HAS_STOP:\n// sequence_order: Integer\n// distance_from_previous_km: Float\n// typical_stop_duration_minutes: Integer\n// Example Cypher CREATE:\n// MATCH (r:Route {route_id: 'route_ne_corr'}), (s:Station {station_id: 'station_pvd'})\n// CREATE (r)-[:HAS_STOP {sequence_order: 2, distance_from_previous_km: 70.5, ...}]->(s)\n// Node Label: :ScheduledTrip (or just :Trip)\n// Properties:\n// schedule_id: String (Constraint: UNIQUE)\n// departure_datetime: DateTime\n// arrival_datetime: DateTime\n// status: String\n// notes: String\n// Relationships:\n// (:ScheduledTrip)-[:USES_TRAIN]->(:Train)\n// (:ScheduledTrip)-[:FOLLOWS_ROUTE]->(:Route)\n// Example Cypher CREATE:\n// MATCH (t:Train {train_id: 'train_789'}), (r:Route {route_id: 'route_ne_corr'})\n// CREATE (sched:ScheduledTrip {schedule_id: 'sched_1122', ...})-[:USES_TRAIN]->(t), (sched)-[:FOLLOWS_ROUTE]->(r)\n// Relationship: (:ScheduledTrip)-[rel:SCHEDULED_STOP]->(:Station)\n// Relationship Properties on :SCHEDULED_STOP:\n// sequence_order: Integer\n// platform_id: String (references Platform node if modeled, or just store ID)\n// scheduled_arrival_time: DateTime\n// scheduled_departure_time: DateTime\n// actual_arrival_time: DateTime\n// actual_departure_time: DateTime\n// status: String\n// Example Cypher CREATE:\n// MATCH (sched:ScheduledTrip {schedule_id: 'sched_1122'}), (s:Station {station_id: 'station_pvd'})\n// CREATE (sched)-[:SCHEDULED_STOP {sequence_order: 2, platform_id: 'plat_pvd_1', ...}]->(s)\n// Node Label: :Passenger\n// Properties:\n// passenger_id: String (Constraint: UNIQUE)\n// first_name: String\n// last_name: String\n// email: String (Constraint: UNIQUE, if not null)\n// phone_number: String (Constraint: UNIQUE, if not null)\n// date_of_birth: Date\n// loyalty_program_id: String\n// created_at: DateTime\n// Example Cypher CREATE:\n// CREATE (:Passenger {passenger_id: 'pass_pqr', first_name: 'Alice', ...})\n// Node Label: :Booking\n// Properties:\n// booking_id: String (Constraint: UNIQUE)\n// booking_datetime: DateTime\n// status: String\n// total_price: Float\n// currency_code: String\n// special_requests: String\n// Relationships:\n// (:Passenger)-[:MADE_BOOKING]->(:Booking)\n// (:Booking)-[:FOR_TRIP]->(:ScheduledTrip)\n// Example Cypher CREATE:\n// MATCH (p:Passenger {passenger_id: 'pass_pqr'}), (sched:ScheduledTrip {schedule_id: 'sched_1122'})\n// CREATE (p)-[:MADE_BOOKING]->(b:Booking {booking_id: 'book_zyx', ...})-[:FOR_TRIP]->(sched)\n// Node Label: :Ticket\n// Properties:\n// ticket_id: String (Constraint: UNIQUE)\n// seat_number: String\n// ticket_type: String\n// price: Float\n// is_checked_in: Boolean\n// qr_code_data: String\n// Relationships:\n// (:Ticket)-[:PART_OF_BOOKING]->(:Booking)\n// (:Ticket)-[:ASSIGNED_TO_CAR]->(:TrainCar)\n// Example Cypher CREATE:\n// MATCH (b:Booking {booking_id: 'book_zyx'}), (c:TrainCar {car_id: 'car_abc'})\n// CREATE (t:Ticket {ticket_id: 'tkt_1a2b', ...})-[:PART_OF_BOOKING]->(b), (t)-[:ASSIGNED_TO_CAR]->(c)\n// Node Label: :Staff\n// Properties:\n// staff_id: String (Constraint: UNIQUE)\n// first_name: String\n// last_name: String\n// role: String\n// employee_number: String (Constraint: UNIQUE)\n// hire_date: Date\n// contact_email: String (Constraint: UNIQUE, if not null)\n// contact_phone: String\n// is_active: Boolean\n// Relationship (Optional):\n// (:Staff)-[:BASED_AT]->(:Station)\n// Example Cypher CREATE:\n// CREATE (:Staff {staff_id: 'staff_mno', first_name: 'Bob', ...})\n// OPTIONAL MATCH (s:Station {station_id: 'station_xyz'}) // If primary_station_id exists\n// WITH s, staff_mno // Need to get the created staff node reference\n// WHERE s IS NOT NULL\n// CREATE (staff_mno)-[:BASED_AT]->(s)\n"} {"conversations": [{"role": "user", "content": "List all customers who have two policies with overlapping coverage periods and show both policy numbers along with the overlap start and end dates."}, {"role": "assistant", "content": "SELECT p1.customer_id, p1.policy_number AS policy_number1, p2.policy_number AS policy_number2, GREATEST(p1.start_date, p2.start_date) AS overlap_start, LEAST(p1.end_date, p2.end_date) AS overlap_end FROM insurance.policies p1 JOIN insurance.policies p2 ON p1.customer_id = p2.customer_id AND p1.policy_id < p2.policy_id WHERE p1.start_date <= p2.end_date AND p2.start_date <= p1.end_date;"}, {"role": "user", "content": "Actually, I only want overlapping policies where both policies are currently active."}, {"role": "assistant", "content": "SELECT p1.customer_id, p1.policy_number AS policy_number1, p2.policy_number AS policy_number2, GREATEST(p1.start_date, p2.start_date) AS overlap_start, LEAST(p1.end_date, p2.end_date) AS overlap_end FROM insurance.policies p1 JOIN insurance.policies p2 ON p1.customer_id = p2.customer_id AND p1.policy_id < p2.policy_id WHERE p1.status = 'active' AND p2.status = 'active' AND p1.start_date <= p2.end_date AND p2.start_date <= p1.end_date;"}, {"role": "user", "content": "Also include the number of days of overlap as overlap_days."}, {"role": "assistant", "content": "SELECT p1.customer_id, p1.policy_number AS policy_number1, p2.policy_number AS policy_number2, GREATEST(p1.start_date, p2.start_date) AS overlap_start, LEAST(p1.end_date, p2.end_date) AS overlap_end, (LEAST(p1.end_date, p2.end_date) - GREATEST(p1.start_date, p2.start_date)) AS overlap_days FROM insurance.policies p1 JOIN insurance.policies p2 ON p1.customer_id = p2.customer_id AND p1.policy_id < p2.policy_id WHERE p1.status = 'active' AND p2.status = 'active' AND p1.start_date <= p2.end_date AND p2.start_date <= p1.end_date;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\n"} {"conversations": [{"role": "user", "content": "I want to list all employees who currently manage at least one other employee, showing their full name, email, and the total number of direct reports for each manager."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name || ' ' || e.last_name AS manager_full_name, e.email, COUNT(r.employee_id) AS direct_report_count\nFROM financial_services.employees e\nJOIN financial_services.employees r ON e.employee_id = r.manager_id\nWHERE e.status = 'Active'\nGROUP BY e.employee_id, e.first_name, e.last_name, e.email;"}, {"role": "user", "content": "Can you also include the job_title and department of each manager in the result?"}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name || ' ' || e.last_name AS manager_full_name, e.email, e.job_title, e.department, COUNT(r.employee_id) AS direct_report_count\nFROM financial_services.employees e\nJOIN financial_services.employees r ON e.employee_id = r.manager_id\nWHERE e.status = 'Active'\nGROUP BY e.employee_id, e.first_name, e.last_name, e.email, e.job_title, e.department;"}, {"role": "user", "content": "I noticed some managers don't have any reports—that shouldn't be the case. Only show managers who have at least two direct reports."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name || ' ' || e.last_name AS manager_full_name, e.email, e.job_title, e.department, COUNT(r.employee_id) AS direct_report_count\nFROM financial_services.employees e\nJOIN financial_services.employees r ON e.employee_id = r.manager_id\nWHERE e.status = 'Active'\nGROUP BY e.employee_id, e.first_name, e.last_name, e.email, e.job_title, e.department\nHAVING COUNT(r.employee_id) >= 2;"}, {"role": "user", "content": "Please order the output by the number of direct reports in descending order."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name || ' ' || e.last_name AS manager_full_name, e.email, e.job_title, e.department, COUNT(r.employee_id) AS direct_report_count\nFROM financial_services.employees e\nJOIN financial_services.employees r ON e.employee_id = r.manager_id\nWHERE e.status = 'Active'\nGROUP BY e.employee_id, e.first_name, e.last_name, e.email, e.job_title, e.department\nHAVING COUNT(r.employee_id) >= 2\nORDER BY direct_report_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.accounts (\n account_id character varying(64) NOT NULL, -- unique identifier for the account\n customer_id character varying(64) NOT NULL, -- foreign key linking to the customer\n account_number character varying(128) NOT NULL UNIQUE, -- unique account number visible to customer\n account_type character varying(50) NOT NULL, -- e.g., Checking, Savings, Investment, Loan, Credit Card\n balance numeric(19, 4) NOT NULL DEFAULT 0.00, -- current account balance\n currency character varying(3) NOT NULL, -- currency code (e.g., USD, EUR)\n opened_date date NOT NULL, -- date the account was opened\n status character varying(32) NOT NULL, -- e.g., Open, Closed, Frozen\n interest_rate numeric(5, 4), -- annual interest rate, if applicable\n last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last account update\n PRIMARY KEY (account_id),\n FOREIGN KEY (customer_id) REFERENCES financial_services.customers(customer_id)\n)\nCREATE TABLE financial_services.transactions (\n transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n account_id character varying(64) NOT NULL, -- account involved in the transaction\n related_account_id character varying(64), -- counterpart account for transfers\n transaction_type character varying(50) NOT NULL, -- e.g., Deposit, Withdrawal, Transfer, Payment, Fee, Interest\n amount numeric(19, 4) NOT NULL, -- transaction amount\n currency character varying(3) NOT NULL, -- transaction currency\n transaction_date timestamp NOT NULL, -- exact time of the transaction\n effective_date date NOT NULL, -- date the transaction affects the balance\n description text, -- description or memo of the transaction\n status character varying(32) NOT NULL, -- e.g., Pending, Completed, Failed, Reversed\n reference_number character varying(128), -- external reference if applicable (e.g., check number)\n PRIMARY KEY (transaction_id),\n FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id),\n FOREIGN KEY (related_account_id) REFERENCES financial_services.accounts(account_id)\n)\nCREATE TABLE financial_services.employees (\n employee_id character varying(64) NOT NULL, -- unique identifier for the employee\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n job_title character varying(100) NOT NULL, -- e.g., Teller, Branch Manager, Financial Advisor, Analyst\n department character varying(100), -- e.g., Retail Banking, Wealth Management, IT\n branch_id character varying(64), -- Identifier for the branch they work at (if applicable)\n email character varying(128) NOT NULL UNIQUE,\n phone_extension character varying(20),\n hire_date date NOT NULL,\n termination_date date, -- Date of termination, null if currently employed\n manager_id character varying(64), -- Self-referencing key for manager relationship\n status character varying(32) NOT NULL, -- e.g., Active, Terminated, On Leave\n PRIMARY KEY (employee_id),\n FOREIGN KEY (branch_id) REFERENCES financial_services.branches(branch_id), -- Assuming a branches table exists\n FOREIGN KEY (manager_id) REFERENCES financial_services.employees(employee_id)\n)\n"} {"conversations": [{"role": "user", "content": "Can you help me fetch the inventory details for components associated with a specific aircraft build, including the batch number, quantity, and warehouse location?"}, {"role": "assistant", "content": "MATCH (ab:AircraftBuild {build_id: 'specific_build_id'})-[:IS_MODEL]->(am:AircraftModel),\n(ib:InventoryBatch)-[:IS_INSTANCE_OF]->(c:Component)\nRETURN ib.inventory_record_id, ib.batch_number, ib.quantity, ib.location_warehouse"}, {"role": "user", "content": "Can you modify this to show only inventory batches received after a specific date, say June 1, 2023?"}, {"role": "assistant", "content": "MATCH (ab:AircraftBuild {build_id: 'specific_build_id'})-[:IS_MODEL]->(am:AircraftModel),\n(ib:InventoryBatch)-[:IS_INSTANCE_OF]->(c:Component)\nWHERE ib.received_date > datetime('2023-06-01')\nRETURN ib.inventory_record_id, ib.batch_number, ib.quantity, ib.location_warehouse"}, {"role": "user", "content": "What if I also want to exclude batches with quantities less than 10?"}, {"role": "assistant", "content": "MATCH (ab:AircraftBuild {build_id: 'specific_build_id'})-[:IS_MODEL]->(am:AircraftModel),\n(ib:InventoryBatch)-[:IS_INSTANCE_OF]->(c:Component)\nWHERE ib.received_date > datetime('2023-06-01') AND ib.quantity >= 10\nRETURN ib.inventory_record_id, ib.batch_number, ib.quantity, ib.location_warehouse"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nNode Label ':AircraftModel'. Properties: { model_id: String (Constraint: UNIQUE), model_name: String, manufacturer: String, passenger_capacity: Integer, max_range_km: Integer, engine_type: String, wingspan_m: Float, status: String, first_flight_date: Date }. Index on model_id.\nNode Label ':Material'. Properties: { material_id: String (Constraint: UNIQUE), material_name: String, specification: String, description: String, density_kg_m3: Float, tensile_strength_mpa: Integer }. Index on material_id.\nNode Label ':AssemblyLine'. Properties: { line_id: String (Constraint: UNIQUE), line_name: String, location_building: String, location_area: String, capacity_units_per_month: Integer, status: String }. Relationship: (:AssemblyLine)-[:BUILDS_MODEL]->(:AircraftModel {model_id}). Index on line_id.\nNode Label ':AssemblyStep'. Properties: { step_id: String (Constraint: UNIQUE), step_number: Integer, step_name: String, description: String, standard_duration_hours: Float, required_skill_level: String, workstation: String }. Relationship: (:AssemblyLine {line_id})-[:HAS_STEP {sequence: }]->(:AssemblyStep). Index on step_id.\nNode Label ':AircraftBuild'. Properties: { build_id: String (Constraint: UNIQUE), serial_number: String (Constraint: UNIQUE), build_start_date: Datetime, estimated_completion_date: Date, actual_completion_date: Datetime, current_status: String, customer_order_id: String }. Relationships: (:AircraftBuild)-[:IS_MODEL]->(:AircraftModel {model_id}), (:AircraftBuild)-[:ASSEMBLED_ON]->(:AssemblyLine {line_id}). Index on build_id, serial_number, current_status.\nNode Label ':Employee'. Properties: { employee_id: String (Constraint: UNIQUE), first_name: String, last_name: String, job_title: String, skill_certifications: String[], hire_date: Date, employment_status: String }. Relationships: (:Employee)-[:ASSIGNED_TO]->(:AssemblyLine {line_id}), (:Employee)-[:REPORTS_TO]->(:Employee {employee_id as supervisor_id}). Index on employee_id.\nNode Label ':InventoryBatch'. Properties: { inventory_record_id: String (Constraint: UNIQUE), quantity: Integer, location_warehouse: String, location_bin: String, received_date: Datetime, expiry_date: Date, batch_number: String, last_updated: Datetime }. Relationship: (:InventoryBatch)-[:IS_INSTANCE_OF]->(:Component {component_id}). Index on inventory_record_id, component_id.\n"} {"conversations": [{"role": "user", "content": "Show the total hours spent by each lawyer across all their time entries. Display the lawyer's first name, last name, and the total hours."}, {"role": "assistant", "content": "SELECT l.first_name, l.last_name, SUM(te.hours_spent) AS total_hours FROM legal_services.time_entries te JOIN legal_services.lawyers l ON te.lawyer_id = l.lawyer_id GROUP BY l.lawyer_id, l.first_name, l.last_name ORDER BY total_hours DESC;"}, {"role": "user", "content": "Modify the previous query to only include time entries that are marked as billable."}, {"role": "assistant", "content": "SELECT l.first_name, l.last_name, SUM(te.hours_spent) AS total_billable_hours FROM legal_services.time_entries te JOIN legal_services.lawyers l ON te.lawyer_id = l.lawyer_id WHERE te.is_billable = true GROUP BY l.lawyer_id, l.first_name, l.last_name ORDER BY total_billable_hours DESC;"}, {"role": "user", "content": "Now, filter the results to only show lawyers who are partners and have logged more than 100 billable hours in total."}, {"role": "assistant", "content": "SELECT l.first_name, l.last_name, SUM(te.hours_spent) AS total_billable_hours FROM legal_services.time_entries te JOIN legal_services.lawyers l ON te.lawyer_id = l.lawyer_id WHERE te.is_billable = true AND l.is_partner = true GROUP BY l.lawyer_id, l.first_name, l.last_name HAVING SUM(te.hours_spent) > 100 ORDER BY total_billable_hours DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers (\n lawyer_id character varying(64) NOT NULL, -- unique identifier for the lawyer\n first_name character varying(100) NOT NULL, -- lawyer's first name\n last_name character varying(100) NOT NULL, -- lawyer's last name\n bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n firm_id character varying(64), -- FK to law_firms table\n email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n phone character varying(32), -- lawyer's contact phone number\n specialization text, -- areas of legal expertise\n hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n PRIMARY KEY (lawyer_id)\n)\nCREATE TABLE legal_services.time_entries (\n entry_id character varying(64) NOT NULL, -- unique identifier for the time entry\n case_id character varying(64) NOT NULL, -- FK to cases table\n lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (who performed the work)\n date_worked date NOT NULL, -- date the work was performed\n hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), -- duration of work in hours (e.g., 1.5 for 1h 30m)\n billing_rate numeric(10, 2) NOT NULL, -- hourly rate applied for this entry\n description text NOT NULL, -- detailed description of the work performed\n is_billable boolean DEFAULT true, -- whether this time entry is billable to the client\n is_billed boolean DEFAULT false, -- whether this entry has been included in an invoice\n invoice_id character varying(64), -- FK to invoices table (once billed)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the entry was recorded\n PRIMARY KEY (entry_id)\n)\nCREATE TABLE legal_services.invoices (\n invoice_id character varying(64) NOT NULL, -- unique identifier for the invoice\n invoice_number character varying(100) UNIQUE NOT NULL, -- user-facing invoice number\n client_id character varying(64) NOT NULL, -- FK to clients table\n case_id character varying(64), -- FK to cases table (optional, could be general retainer)\n issue_date date NOT NULL, -- date the invoice was generated\n due_date date NOT NULL, -- date the payment is due\n total_amount numeric(12, 2) NOT NULL, -- total amount due on the invoice\n amount_paid numeric(12, 2) DEFAULT 0.00, -- amount already paid\n status character varying(50) NOT NULL, -- e.g., Draft, Sent, Paid, Partially Paid, Overdue, Void\n payment_date timestamp, -- date the invoice was fully paid (nullable)\n notes text, -- additional notes or terms on the invoice\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (invoice_id)\n)\n"} {"conversations": [{"role": "user", "content": "List the citizen IDs for individuals who have both uploaded documents and made payments."}, {"role": "assistant", "content": "SELECT DISTINCT T1.citizen_id FROM documents AS T1 JOIN payments AS T2 ON T1.citizen_id = T2.citizen_id"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.documents ( document_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, document_type character varying(100) NOT NULL, file_reference text NOT NULL, upload_timestamp timestamp NOT NULL, expiry_date date, verification_status character varying(30) DEFAULT 'Pending', verified_by_employee_id character varying(64), verification_timestamp timestamp, PRIMARY KEY (document_id) )\nCREATE TABLE government_services.payments ( payment_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, service_id character varying(64), amount numeric(12, 2) NOT NULL, currency character varying(3) NOT NULL DEFAULT 'USD', payment_method character varying(50), payment_provider_reference character varying(128), payment_timestamp timestamp NOT NULL, status character varying(30) NOT NULL, notes text, PRIMARY KEY (payment_id) )\n"} {"conversations": [{"role": "user", "content": "How many hashtags have been created in March 2024?"}, {"role": "assistant", "content": "```sql\nSELECT COUNT(*) AS march_2024_hashtag_count\nFROM social_media.hashtags\nWHERE created_at >= '2024-03-01'\n AND created_at < '2024-04-01';\n```"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified bool )\nCREATE TABLE social_media.hashtags ( hashtag_id text PRIMARY KEY, tag_name text, created_at timestamp )\nCREATE TABLE social_media.conversation_participants ( participant_id text PRIMARY KEY, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications ( notification_id text PRIMARY KEY, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\n"} {"conversations": [{"role": "user", "content": "How many policies are there for each status, and what is the average premium amount for policies in each status?"}, {"role": "assistant", "content": "SELECT status, COUNT(policy_id), AVG(premium_amount) FROM insurance.policies GROUP BY status ORDER BY COUNT(policy_id) DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text PRIMARY KEY, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\n"} {"conversations": [{"role": "user", "content": "List the contact phone and website for all insurance plans provided by 'Continental Health'."}, {"role": "assistant", "content": "SELECT plan_name, contact_phone, website\nFROM healthcare.insurance_plans\nWHERE insurance_provider = 'Continental Health';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id text PRIMARY KEY, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes int, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, appointment_id character varying(64) UNIQUE, doctor_id character varying(64) NOT NULL, record_date timestamp with time zone NOT NULL, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals jsonb, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (record_id) )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.prescriptions ( prescription_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, medication_id character varying(64) NOT NULL, dosage character varying(100) NOT NULL, frequency character varying(100) NOT NULL, route character varying(50), start_date date NOT NULL, end_date date, quantity_dispensed numeric(10,2), refills_allowed integer NOT NULL DEFAULT 0, prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (prescription_id) )\nCREATE TABLE healthcare.insurance_plans ( plan_id character varying(64) NOT NULL, plan_name character varying(200) NOT NULL, insurance_provider character varying(100) NOT NULL, plan_type character varying(50), contact_phone character varying(20), website character varying(255), PRIMARY KEY (plan_id) )\nCREATE TABLE healthcare.patient_insurance (\n patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n patient_id character varying(64) NOT NULL, -- FK to patients table\n plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n policy_number character varying(100) NOT NULL, -- patient's policy number\n group_number character varying(100), -- group number, if applicable\n subscriber_name character varying(200), -- name of the primary policy holder\n effective_date date NOT NULL, -- date the coverage begins\n expiration_date date, -- date the coverage ends (if known)\n is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n PRIMARY KEY (patient_insurance_id),\n UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"} {"conversations": [{"role": "user", "content": "Show me all fuel logs where the location is 'LOC456', including the vehicle ID, fuel type, and quantity."}, {"role": "assistant", "content": "SELECT fuel_log_id, vehicle_id, fuel_type, quantity FROM transportation.fuel_logs WHERE location_id = 'LOC456';"}, {"role": "user", "content": "Can you also include the trip ID and filter to only show logs from the last 3 months?"}, {"role": "assistant", "content": "SELECT fuel_log_id, vehicle_id, trip_id, fuel_type, quantity FROM transportation.fuel_logs WHERE location_id = 'LOC456' AND log_timestamp >= CURRENT_DATE - INTERVAL '3 months';"}, {"role": "user", "content": "Now group these results by fuel type and show the total quantity for each type."}, {"role": "assistant", "content": "SELECT fuel_type, SUM(quantity) AS total_quantity FROM transportation.fuel_logs WHERE location_id = 'LOC456' AND log_timestamp >= CURRENT_DATE - INTERVAL '3 months' GROUP BY fuel_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\n"} {"conversations": [{"role": "user", "content": "List all pairs of law firms that were founded on the same month and day, showing their names, and the shared founding date. Exclude firms founded on January 1st."}, {"role": "assistant", "content": "SELECT t1.firm_name AS firm1_name, t2.firm_name AS firm2_name, t1.founded_date FROM legal_services.law_firms AS t1 JOIN legal_services.law_firms AS t2 ON MONTH(t1.founded_date) = MONTH(t2.founded_date) AND DAY(t1.founded_date) = DAY(t2.founded_date) AND t1.firm_id < t2.firm_id WHERE MONTH(t1.founded_date) <> 1 OR DAY(t1.founded_date) <> 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.law_firms ( firm_id character varying(64) NOT NULL, firm_name character varying(200) NOT NULL, address text NOT NULL, phone character varying(32), website character varying(255), founded_date date, managing_partner_id character varying(64), PRIMARY KEY (firm_id) )\n"} {"conversations": [{"role": "user", "content": "List all assets mentioned in DApp descriptions along with the DApp name and URL."}, {"role": "assistant", "content": "SELECT a.name AS asset_name,\n a.symbol AS asset_symbol,\n d.name AS dapp_name,\n d.url\nFROM trading_platform.assets a\nJOIN trading_platform.dapps d\n ON d.description ILIKE '%' || a.symbol || '%';"}, {"role": "user", "content": "Actually, only include assets of type 'cryptocurrency'."}, {"role": "assistant", "content": "SELECT a.name AS asset_name,\n a.symbol AS asset_symbol,\n d.name AS dapp_name,\n d.url\nFROM trading_platform.assets a\nJOIN trading_platform.dapps d\n ON d.description ILIKE '%' || a.symbol || '%'\nWHERE a.type = 'cryptocurrency';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.assets (\n asset_id character varying(64) NOT NULL, -- unique identifier for the asset\n name character varying(128) NOT NULL, -- name of the asset\n symbol character varying(32) NOT NULL, -- symbol of the asset\n type character varying(32) NOT NULL, -- type of the asset (e.g., cryptocurrency, stock)\n PRIMARY KEY (asset_id)\n)\nCREATE TABLE trading_platform.utxos (\n utxo_id character varying(64) NOT NULL, -- unique identifier for the UTXO\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction that created the UTXO\n output_index integer NOT NULL, -- index of the output in the transaction\n address character varying(128) NOT NULL, -- address that can spend the UTXO\n amount numeric(38,14) NOT NULL, -- amount of the asset in the UTXO\n spent boolean NOT NULL, -- whether the UTXO has been spent\n PRIMARY KEY (utxo_id)\n)\nCREATE TABLE trading_platform.dapps (\n dapp_id character varying(64) NOT NULL, -- unique identifier for the DApp\n name character varying(128) NOT NULL, -- name of the DApp\n description text NOT NULL, -- description of the DApp\n url character varying(256) NOT NULL, -- URL of the DApp\n PRIMARY KEY (dapp_id)\n)\n"} {"conversations": [{"role": "user", "content": "For each address, show the total amount contained in UTXOs that have been spent."}, {"role": "assistant", "content": "SELECT address, SUM(amount) FROM utxos WHERE spent = TRUE GROUP BY address;"}, {"role": "user", "content": "Only include addresses where this total spent amount is greater than 500 and order the results by the total amount descending."}, {"role": "assistant", "content": "SELECT address, SUM(amount) FROM utxos WHERE spent = TRUE GROUP BY address HAVING SUM(amount) > 500 ORDER BY SUM(amount) DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.utxos (\n utxo_id character varying(64) NOT NULL, -- unique identifier for the UTXO\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction that created the UTXO\n output_index integer NOT NULL, -- index of the output in the transaction\n address character varying(128) NOT NULL, -- address that can spend the UTXO\n amount numeric(38,14) NOT NULL, -- amount of the asset in the UTXO\n spent boolean NOT NULL, -- whether the UTXO has been spent\n PRIMARY KEY (utxo_id)\n)\n"} {"conversations": [{"role": "user", "content": "For each asset, calculate the total quantity and average price of orders that have status 'filled'."}, {"role": "assistant", "content": "SELECT o.asset_id,\n SUM(o.quantity) AS total_quantity,\n AVG(o.price) AS average_price\nFROM trading_platform.orders o\nWHERE o.status = 'filled'\nGROUP BY o.asset_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.wallets (\n wallet_id character varying(64) NOT NULL, -- unique identifier for the wallet\n user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n address character varying(128) NOT NULL, -- address of the wallet\n private_key text NOT NULL, -- private key of the wallet\n created_at timestamp NOT NULL, -- time when the wallet was created\n PRIMARY KEY (wallet_id)\n)\nCREATE TABLE trading_platform.orders (\n order_id character varying(64) NOT NULL, -- unique identifier for the order\n user_id character varying(64) NOT NULL, -- identifier of the user placing the order\n wallet_id character varying(64) NOT NULL, -- identifier of the wallet used for the order\n asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n order_type character varying(32) NOT NULL, -- type of the order (e.g., buy, sell)\n quantity numeric(38,14) NOT NULL, -- quantity of the asset in the order\n price numeric(38,14) NOT NULL, -- price per unit of the asset\n status character varying(32) NOT NULL, -- status of the order (e.g., open, filled, canceled)\n created_at timestamp NOT NULL, -- time when the order was created\n PRIMARY KEY (order_id)\n)\nCREATE TABLE trading_platform.assets (\n asset_id character varying(64) NOT NULL, -- unique identifier for the asset\n name character varying(128) NOT NULL, -- name of the asset\n symbol character varying(32) NOT NULL, -- symbol of the asset\n type character varying(32) NOT NULL, -- type of the asset (e.g., cryptocurrency, stock)\n PRIMARY KEY (asset_id)\n)\nCREATE TABLE trading_platform.utxos (\n utxo_id character varying(64) NOT NULL, -- unique identifier for the UTXO\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction that created the UTXO\n output_index integer NOT NULL, -- index of the output in the transaction\n address character varying(128) NOT NULL, -- address that can spend the UTXO\n amount numeric(38,14) NOT NULL, -- amount of the asset in the UTXO\n spent boolean NOT NULL, -- whether the UTXO has been spent\n PRIMARY KEY (utxo_id)\n)\nCREATE TABLE trading_platform.dapps (\n dapp_id character varying(64) NOT NULL, -- unique identifier for the DApp\n name character varying(128) NOT NULL, -- name of the DApp\n description text NOT NULL, -- description of the DApp\n url character varying(256) NOT NULL, -- URL of the DApp\n PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.peers (\n peer_id character varying(64) NOT NULL, -- unique identifier for the peer\n ip_address character varying(15) NOT NULL, -- IP address of the peer\n port integer NOT NULL, -- port number of the peer\n last_seen timestamp NOT NULL, -- last time the peer was active\n PRIMARY KEY (peer_id)\n)\nCREATE TABLE trading_platform.metadata (\n metadata_id character varying(64) NOT NULL, -- unique identifier for the metadata\n asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with\n key character varying(128) NOT NULL, -- key of the metadata\n value text NOT NULL, -- value of the metadata\n PRIMARY KEY (metadata_id)\n)\nCREATE TABLE trading_platform.kyc_audit (\n kyc_audit_id character varying(64) NOT NULL, -- unique identifier for the KYC audit\n user_id character varying(64) NOT NULL, -- identifier of the user being audited\n status character varying(32) NOT NULL, -- status of the KYC audit (e.g., pending, approved, rejected)\n reviewed_at timestamp NOT NULL, -- time when the KYC audit was reviewed\n PRIMARY KEY (kyc_audit_id)\n)\nCREATE TABLE trading_platform.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n user_id character varying(64) NOT NULL, -- identifier of the user receiving the notification\n message text NOT NULL, -- message of the notification\n sent_at timestamp NOT NULL, -- time when the notification was sent\n read_at timestamp, -- time when the notification was read\n PRIMARY KEY (notification_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all active insurance products, including their product name, type, and base premium."}, {"role": "assistant", "content": "SELECT product_name, product_type, base_premium FROM insurance.insurance_products WHERE is_active = TRUE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims ( claim_id text PRIMARY KEY, policy_id text, customer_id text, incident_date timestamp, reported_date timestamp, description text, estimated_loss numeric, status text, settlement_amount numeric, settlement_date date, claim_handler_id text, police_report_number text )\nCREATE TABLE insurance.insurance_products ( product_id text PRIMARY KEY, product_name text, product_type text, description text, base_premium numeric, coverage_details text, underwriting_rules text, is_active boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE insurance.claim_documents ( document_id text PRIMARY KEY, claim_id text, document_type text, file_name text, file_path text, file_size_bytes int, mime_type text, uploaded_by text, uploaded_at timestamp, description text )\n"} {"conversations": [{"role": "user", "content": "Provide each pair of plans that share the same plan_type but are offered by different providers."}, {"role": "assistant", "content": "SELECT p1.plan_type,\n p1.plan_id AS plan1_id,\n p1.plan_name AS plan1_name,\n p1.insurance_provider AS provider1,\n p2.plan_id AS plan2_id,\n p2.plan_name AS plan2_name,\n p2.insurance_provider AS provider2\nFROM healthcare.insurance_plans p1\nJOIN healthcare.insurance_plans p2\n ON p1.plan_type = p2.plan_type\n AND p1.insurance_provider < p2.insurance_provider;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.insurance_plans ( plan_id text PRIMARY KEY, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\n"} {"conversations": [{"role": "user", "content": "What is the total revenue generated by ticket sales at the station with ID 'ST101' for the past month?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the revenue generated by ticket sales as this data is not available in the current database table. The table only contains details about station information such as name, location, and platform count. If you have another question or need assistance with something else related to the station data, I'm happy to help."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.stations ( station_id.text, station_name.text, city.text, state_province.text, country_code.text, address.text, timezone.text, number_of_platforms.integer, created_at.timestamp, last_updated_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "What are the fuel consumption rates per hour for the Boeing 747-8 model?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the fuel consumption rates for the Boeing 747-8 model as this data is not included in the aircraft_models table. The table contains details such as model name, manufacturer, passenger capacity, and other specifications, but fuel consumption data is not available. If you have another question or need assistance with something else related to the table, I'm happy to help."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models ( model_id.text, model_name.text, manufacturer.text, passenger_capacity.integer, max_range_km.integer, engine_type.text, wingspan_m.numeric, status.text, first_flight_date.date )\n"} {"conversations": [{"role": "user", "content": "List the token symbol, token name, and contract address for all tokens that have no recorded transfers in the token_transfers table."}, {"role": "assistant", "content": "SELECT T.token_symbol, T.token_name, T.contract_address FROM web3.tokens AS T LEFT JOIN token_transfers AS TT ON T.token_id = TT.token_id WHERE TT.transfer_id IS NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.tokens (\n token_id character varying(64) NOT NULL, -- unique identifier for the token\n contract_address character varying(128) NOT NULL, -- address of the token contract\n token_name character varying(128) NOT NULL, -- name of the token\n token_symbol character varying(32) NOT NULL, -- symbol of the token\n decimals integer NOT NULL, -- number of decimals for the token\n total_supply numeric(38,14) NOT NULL, -- total supply of the token\n PRIMARY KEY (token_id)\n)\n"} {"conversations": [{"role": "user", "content": "I want to find the total number of players currently connected per region for each game."}, {"role": "assistant", "content": "SELECT\n s.region,\n s.game_id,\n SUM(s.current_players) AS total_players\nFROM gaming_technology.servers s\nGROUP BY\n s.region,\n s.game_id;"}, {"role": "user", "content": "Now include the game's title in the output."}, {"role": "assistant", "content": "SELECT\n s.region,\n s.game_id,\n g.title,\n SUM(s.current_players) AS total_players\nFROM gaming_technology.servers s\nJOIN gaming_technology.games g\n ON s.game_id = g.game_id\nGROUP BY\n s.region,\n s.game_id,\n g.title;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id uuid NOT NULL DEFAULT gen_random_uuid(), username character varying(100) NOT NULL UNIQUE, email character varying(255) NOT NULL UNIQUE, password_hash text NOT NULL, registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, last_login timestamp with time zone, country_code character(2), status character varying(20) NOT NULL DEFAULT 'active', profile_data jsonb, PRIMARY KEY (player_id) )\nCREATE TABLE gaming_technology.games ( game_id uuid PRIMARY KEY, title text, developer_id uuid, publisher_id uuid, genre text, release_date date, description text, platform text, engine text, website text )\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, game_id uuid NOT NULL, server_id uuid, start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, end_time timestamp with time zone, duration_seconds integer, score integer, session_data jsonb, PRIMARY KEY (session_id) )\nCREATE TABLE gaming_technology.servers ( server_id uuid PRIMARY KEY, game_id uuid, server_name text, region text, ip_address text, port int, current_players int, max_players int, status text, last_heartbeat timestamptz )\nCREATE TABLE gaming_technology.achievements ( achievement_id.uuid, game_id.uuid, name.text, description.text, icon_url.text, points.integer, hidden.boolean )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid PRIMARY KEY, player_id uuid, achievement_id uuid, unlocked_at timestamptz )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid PRIMARY KEY, player_id uuid, item_id uuid, quantity int, acquired_at timestamptz, instance_data jsonb )\n"} {"conversations": [{"role": "user", "content": "Show the full name of each manager and the average commission rate of the agents who report directly to them. Only include managers who have at least one reporting agent."}, {"role": "assistant", "content": "SELECT T2.first_name AS manager_first_name, T2.last_name AS manager_last_name, AVG(T1.commission_rate) AS average_agent_commission_rate FROM insurance.agents AS T1 JOIN insurance.agents AS T2 ON T1.manager_id = T2.agent_id GROUP BY T2.agent_id, T2.first_name, T2.last_name"}, {"role": "user", "content": "Filter the results to only show managers whose average agent commission rate is above 0.12."}, {"role": "assistant", "content": "SELECT T2.first_name AS manager_first_name, T2.last_name AS manager_last_name, AVG(T1.commission_rate) AS average_agent_commission_rate FROM insurance.agents AS T1 JOIN insurance.agents AS T2 ON T1.manager_id = T2.agent_id GROUP BY T2.agent_id, T2.first_name, T2.last_name HAVING AVG(T1.commission_rate) > 0.12"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.agents ( agent_id.text, first_name.text, last_name.text, agency_name.text, license_number.text, license_state.text, contact_email.text, contact_phone.text, hire_date.date, termination_date.date, status.text, commission_rate.numeric, manager_id.text )\n"} {"conversations": [{"role": "user", "content": "For each employee who has verified more than one document, list their employee ID, the first document they verified, and the next document they verified, along with both verification timestamps."}, {"role": "assistant", "content": "SELECT\n d1.verified_by_employee_id AS employee_id,\n d1.document_id AS first_verified_document,\n d1.verification_timestamp AS first_verification_time,\n d2.document_id AS next_verified_document,\n d2.verification_timestamp AS next_verification_time\nFROM government_services.documents d1\nJOIN government_services.documents d2\n ON d1.verified_by_employee_id = d2.verified_by_employee_id\n AND d2.verification_timestamp > d1.verification_timestamp\nWHERE d1.verification_status = 'Verified'\n AND d2.verification_status = 'Verified';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.documents ( document_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, document_type character varying(100) NOT NULL, file_reference text NOT NULL, upload_timestamp timestamp NOT NULL, expiry_date date, verification_status character varying(30) DEFAULT 'Pending', verified_by_employee_id character varying(64), verification_timestamp timestamp, PRIMARY KEY (document_id) )\n"} {"conversations": [{"role": "user", "content": "Find all medical records where the treatment plan includes 'physical therapy' and the patient has an active primary insurance plan, showing the patient ID, record date, and insurance provider details."}, {"role": "assistant", "content": "SELECT mr.patient_id, mr.record_date, ip.insurance_provider, ip.plan_name, pi.policy_number FROM healthcare.medical_records mr JOIN healthcare.patients p ON mr.patient_id = p.patient_id JOIN healthcare.patient_insurance pi ON p.patient_id = pi.patient_id AND pi.is_primary = true JOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id WHERE mr.treatment_plan LIKE '%physical therapy%' AND (pi.expiration_date IS NULL OR pi.expiration_date > CURRENT_DATE);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id text PRIMARY KEY, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.insurance_plans (\n plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n plan_name character varying(200) NOT NULL, -- name of the insurance plan\n insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n plan_type character varying(50), -- e.g., PPO, HMO, EPO\n contact_phone character varying(20), -- provider contact number\n website character varying(255), -- provider website\n PRIMARY KEY (plan_id)\n)\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n"} {"conversations": [{"role": "user", "content": "List each wallet that has received tokens of more than one distinct token type. Show wallet_id, address, the number of distinct tokens received as distinct_token_count, and the total received value, ordered by total_received_value descending."}, {"role": "assistant", "content": "SELECT w.wallet_id,\n w.address,\n COUNT(DISTINCT t.token_id) AS distinct_token_count,\n SUM(tt.value) AS total_received_value\nFROM web3.wallets w\nJOIN web3.token_transfers tt\n ON w.address = tt.to_address\nJOIN web3.tokens t\n ON tt.token_id = t.token_id\nGROUP BY w.wallet_id, w.address\nHAVING COUNT(DISTINCT t.token_id) > 1\nORDER BY total_received_value DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.tokens (\n token_id character varying(64) NOT NULL, -- unique identifier for the token\n contract_address character varying(128) NOT NULL, -- address of the token contract\n token_name character varying(128) NOT NULL, -- name of the token\n token_symbol character varying(32) NOT NULL, -- symbol of the token\n decimals integer NOT NULL, -- number of decimals for the token\n total_supply numeric(38,14) NOT NULL, -- total supply of the token\n PRIMARY KEY (token_id)\n)\nCREATE TABLE web3.token_transfers (\n transfer_id character varying(64) NOT NULL, -- unique identifier for the transfer\n token_id character varying(64) NOT NULL, -- identifier of the token being transferred\n from_address character varying(128) NOT NULL, -- address of the sender\n to_address character varying(128) NOT NULL, -- address of the receiver\n value numeric(38,14) NOT NULL, -- amount of tokens transferred\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction containing the transfer\n log_index integer NOT NULL, -- index of the transfer log in the transaction\n PRIMARY KEY (transfer_id)\n)\nCREATE TABLE web3.wallets (\n wallet_id character varying(64) NOT NULL, -- unique identifier for the wallet\n user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n address character varying(128) NOT NULL, -- address of the wallet\n private_key text NOT NULL, -- private key of the wallet\n created_at timestamp NOT NULL, -- time when the wallet was created\n PRIMARY KEY (wallet_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me all conversation IDs (whether group chat or not) that have at least one hashtag used in posts linked to them."}, {"role": "assistant", "content": "SELECT DISTINCT c.conversation_id\nFROM social_media.conversations c\nJOIN social_media.post_hashtags ph ON c.conversation_id = ph.post_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.post_hashtags (\n post_hashtag_id character varying(64) NOT NULL, -- unique identifier for the post-hashtag link\n post_id character varying(64) NOT NULL, -- identifier of the post (FK to posts.post_id)\n hashtag_id character varying(64) NOT NULL, -- identifier of the hashtag (FK to hashtags.hashtag_id)\n PRIMARY KEY (post_hashtag_id),\n CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) -- prevent duplicate tags on a post\n)\nCREATE TABLE social_media.conversations ( conversation_id text PRIMARY KEY, created_at timestamp, last_message_at timestamp, is_group_chat bool, group_name text )\n"} {"conversations": [{"role": "user", "content": "For each route type, show the total number of trips taken and the total distance covered across all trips for that type."}, {"role": "assistant", "content": "SELECT T1.type, COUNT(T2.trip_id), SUM(T1.distance_km) FROM transportation.routes AS T1 JOIN transportation.trips AS T2 ON T1.route_id = T2.route_id GROUP BY T1.type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id.text, license_plate.text, vin.text, make.text, model.text, year.integer, type.text, capacity.integer, fuel_type.text, status.text, depot_id.text, acquisition_date.date )\nCREATE TABLE transportation.drivers ( driver_id.text, employee_id.text, first_name.text, last_name.text, license_number.text, license_expiry_date.date, contact_number.text, email.text, hire_date.date, status.text )\nCREATE TABLE transportation.routes ( route_id.text, route_number.text, description.text, origin_location_id.text, destination_location_id.text, distance_km.numeric, estimated_duration_minutes.integer, type.text )\nCREATE TABLE transportation.trips ( trip_id.text, route_id.text, vehicle_id.text, driver_id.text, scheduled_departure.timestamp, actual_departure.timestamp, scheduled_arrival.timestamp, actual_arrival.timestamp, origin_location_id.text, destination_location_id.text, status.text, passenger_count.integer, cargo_manifest_id.text )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"} {"conversations": [{"role": "user", "content": "How many beneficiaries are there for each relationship type?"}, {"role": "assistant", "content": "SELECT relationship,\n COUNT(*) AS beneficiary_count\nFROM insurance.policy_beneficiaries\nGROUP BY relationship;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, relationship character varying(50) NOT NULL, percentage_share numeric(5, 2) NOT NULL CHECK (percentage_share > 0 AND percentage_share <= 100), contact_info text, added_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (beneficiary_id), UNIQUE (policy_id, customer_id) )\n"} {"conversations": [{"role": "user", "content": "Show me each doctor and the total number of unique patients they have prescribed medications to. Include the doctor's full name and the patient count."}, {"role": "assistant", "content": "SELECT d.doctor_id, d.first_name, d.last_name, COUNT(DISTINCT p.patient_id) AS unique_patient_count\nFROM healthcare.prescriptions p\nJOIN healthcare.doctors d ON p.doctor_id = d.doctor_id\nGROUP BY d.doctor_id, d.first_name, d.last_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.doctors ( doctor_id text PRIMARY KEY, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id text PRIMARY KEY, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text PRIMARY KEY, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed int, prescription_date timestamp )\n"} {"conversations": [{"role": "user", "content": "For each employee, find their first and last name along with the number of applications they've been assigned. Only include employees with at least 5 assigned applications."}, {"role": "assistant", "content": "SELECT e.first_name,\n e.last_name,\n COUNT(a.application_id) AS assigned_count\nFROM government_services.employees e\nJOIN government_services.applications a ON e.employee_id = a.assigned_employee_id\nGROUP BY e.first_name, e.last_name\nHAVING COUNT(a.application_id) >= 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.applications ( application_id text, citizen_id text, service_id text, submitted_at timestamp, status text, last_updated_at timestamp, assigned_employee_id text, decision_date date, notes text, reference_number text )\nCREATE TABLE government_services.documents ( document_id text, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.employees ( employee_id text, agency_id text, first_name text, last_name text, job_title text, department text, work_email text, work_phone text, hire_date date, termination_date date, access_level text, manager_employee_id text )\nCREATE TABLE government_services.service_locations ( location_id text, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.appointments ( appointment_id text, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\n"} {"conversations": [{"role": "user", "content": "List the first name, last name, and firm name for all lawyers who are partners."}, {"role": "assistant", "content": "SELECT T1.first_name , T1.last_name , T2.firm_name FROM legal_services.lawyers AS T1 JOIN law_firms AS T2 ON T1.firm_id = T2.firm_id WHERE T1.is_partner = TRUE"}, {"role": "user", "content": "Only show partners from law firms founded before 2010."}, {"role": "assistant", "content": "SELECT T1.first_name , T1.last_name , T2.firm_name FROM legal_services.lawyers AS T1 JOIN law_firms AS T2 ON T1.firm_id = T2.firm_id WHERE T1.is_partner = TRUE AND T2.founded_date < '2010-01-01'"}, {"role": "user", "content": "Sort the results by firm name and then by the lawyer's last name."}, {"role": "assistant", "content": "SELECT T1.first_name , T1.last_name , T2.firm_name FROM legal_services.lawyers AS T1 JOIN law_firms AS T2 ON T1.firm_id = T2.firm_id WHERE T1.is_partner = TRUE AND T2.founded_date < '2010-01-01' ORDER BY T2.firm_name , T1.last_name"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers (\n lawyer_id character varying(64) NOT NULL, -- unique identifier for the lawyer\n first_name character varying(100) NOT NULL, -- lawyer's first name\n last_name character varying(100) NOT NULL, -- lawyer's last name\n bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n firm_id character varying(64), -- FK to law_firms table\n email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n phone character varying(32), -- lawyer's contact phone number\n specialization text, -- areas of legal expertise\n hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n PRIMARY KEY (lawyer_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me all maintenance logs for 'Oil Change' services performed in the last 3 months, including the vehicle ID, service date, and cost."}, {"role": "assistant", "content": "SELECT vehicle_id, service_date, cost FROM transportation.maintenance_logs WHERE service_type = 'Oil Change' AND service_date >= CURRENT_DATE - INTERVAL '3 months';"}, {"role": "user", "content": "Can you also include the mechanic name and filter to only show services that cost more than $100?"}, {"role": "assistant", "content": "SELECT vehicle_id, service_date, cost, mechanic_name FROM transportation.maintenance_logs WHERE service_type = 'Oil Change' AND service_date >= CURRENT_DATE - INTERVAL '3 months' AND cost > 100;"}, {"role": "user", "content": "Now order these results by service date with the most recent first and limit to 10 records."}, {"role": "assistant", "content": "SELECT vehicle_id, service_date, cost, mechanic_name FROM transportation.maintenance_logs WHERE service_type = 'Oil Change' AND service_date >= CURRENT_DATE - INTERVAL '3 months' AND cost > 100 ORDER BY service_date DESC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.maintenance_logs (\n log_id character varying(64) NOT NULL, -- unique identifier for the maintenance record\n vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle serviced\n service_date date NOT NULL, -- date the service was performed\n odometer_reading integer, -- vehicle mileage at time of service\n service_type character varying(128) NOT NULL, -- type of service (e.g., Oil Change, Tire Rotation, Engine Repair)\n description text NOT NULL, -- detailed description of work done\n cost numeric(10, 2), -- cost of the service\n mechanic_name character varying(128), -- name or ID of the mechanic/shop\n next_service_due_date date, -- recommended date for next service\n PRIMARY KEY (log_id)\n)\n"} {"conversations": [{"role": "user", "content": "List the full names and dates of birth for all patients who do not have a phone number on record."}, {"role": "assistant", "content": "SELECT first_name, last_name, date_of_birth FROM healthcare.patients WHERE phone_number IS NULL OR TRIM(phone_number) = '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.diagnoses (\n diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n description text, -- textual description of the diagnosis\n diagnosis_date date NOT NULL, -- date the diagnosis was made\n status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n is_chronic boolean DEFAULT false, -- flag for chronic conditions\n PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id.text, patient_id.text, plan_id.text, policy_number.text, group_number.text, subscriber_name.text, effective_date.date, expiration_date.date, is_primary.boolean )\n"} {"conversations": [{"role": "user", "content": "For each Bitcoin token tick, show me the creator address from the token_info_bitcoin table and the number of unique wallets currently holding that token."}, {"role": "assistant", "content": "SELECT ti.tick, ti.creator, COUNT(DISTINCT tb.wallet_address) AS unique_wallets FROM token_info_bitcoin ti JOIN token_balances_bitcoin tb ON ti.tick = tb.tick GROUP BY ti.tick, ti.creator;"}, {"role": "user", "content": "Now, only include ticks where there are more than 5 unique wallets, and order the result by the number of unique wallets descending."}, {"role": "assistant", "content": "SELECT ti.tick, ti.creator, COUNT(DISTINCT tb.wallet_address) AS unique_wallets FROM token_info_bitcoin ti JOIN token_balances_bitcoin tb ON ti.tick = tb.tick GROUP BY ti.tick, ti.creator HAVING COUNT(DISTINCT tb.wallet_address) > 5 ORDER BY unique_wallets DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n object_id varchar NOT NULL, -- object id of the coin metadata object\n coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n status varchar NOT NULL, -- coin status, eg. exists, deleted\n decimals bigint NOT NULL, -- decimals of the coin\n description varchar NOT NULL, -- description of the coin\n icon_url varchar NOT NULL, -- icon url of the coin\n symbol varchar NOT NULL, -- symbol of the coin\n name varchar NOT NULL -- name of the coin\n)\nCREATE TABLE sui_nfts ( object_id.text, status.text, collection_type.text, package_id.text, previous_transaction.text, display.text, owner.text, name.text )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid.text, blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE token_prices_latest ( blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE erc20_approval ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text, pk.integer )\nCREATE TABLE token_balances (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar NOT NULL, -- Token tick\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply decimal(38,0) NOT NULL, -- Max supply\n amount decimal(38,0) NOT NULL -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply varchar NOT NULL, -- Max supply: Set max supply of the inscription\n amount varchar NOT NULL -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_balances_avalanche (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n amount decimal(38,0) NOT NULL -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"} {"conversations": [{"role": "user", "content": "What is the average investment_value and total number of projects for each rounds_name in project_fundraising_record?"}, {"role": "assistant", "content": "SELECT rounds_name,\n AVG(investment_value) AS avg_investment,\n COUNT(DISTINCT project_id) AS project_count\nFROM project_fundraising_record\nGROUP BY rounds_name;"}, {"role": "user", "content": "Please show only rounds where project_count > 5, and order by avg_investment descending."}, {"role": "assistant", "content": "SELECT rounds_name,\n AVG(investment_value) AS avg_investment,\n COUNT(DISTINCT project_id) AS project_count\nFROM project_fundraising_record\nGROUP BY rounds_name\nHAVING COUNT(DISTINCT project_id) > 5\nORDER BY avg_investment DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id text, project_id text, project_name text, rounds_name text, investment_value numeric, investment_date text, introduction text, valuation numeric )\nCREATE TABLE token_basic_info ( coin_id text, token_name text, token_symbol text, token_address text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, highest_price_24h numeric, lowest_price_24h numeric, market_cap numeric, market_cap_rank numeric, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank numeric )\nCREATE TABLE narrative_info ( narrative text, top_3_coins text, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, market_cap numeric, volume_24h numeric, trend_rank numeric, token_num numeric )\nCREATE TABLE token_dexpool_info ( pair_address text, token_name text, token_symbol text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_6h numeric, price_change_percentage_24h numeric, makers_24h numeric, volume_24h numeric, liquidity numeric, market_cap numeric, trend_rank numeric )\nCREATE TABLE smart_money_token_performance ( token_address text, token_symbol text, pnl numeric, net_flow numeric, avg_cost numeric, price numeric, realized_ratio numeric, roi numeric, chain text )\n"} {"conversations": [{"role": "user", "content": "List the user IDs for users who have both private profiles enabled and push notifications enabled."}, {"role": "assistant", "content": "SELECT user_id FROM social_media.user_settings WHERE private_profile = TRUE AND push_notifications_enabled = TRUE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.likes ( like_id text, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id text, tag_name text, created_at timestamp )\nCREATE TABLE social_media.messages ( message_id text, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id text, created_at timestamp, last_message_at timestamp, is_group_chat boolean, group_name text )\nCREATE TABLE social_media.user_settings ( setting_id text, user_id text, theme text, email_notifications_enabled boolean, push_notifications_enabled boolean, private_profile boolean, updated_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me all wallet addresses that hold more than 1000 of any ERC1155 token, along with the token ID and contract address."}, {"role": "assistant", "content": "SELECT wallet_address, token_id, contract_address FROM nft_holders WHERE contract_type = 'ERC1155' AND CAST(amount AS decimal) > 1000;"}, {"role": "user", "content": "Can you join this with the nft_metadata table to include the name and image_uri of each token?"}, {"role": "assistant", "content": "SELECT nh.wallet_address, nh.token_id, nh.contract_address, nm.name, nm.image_uri FROM nft_holders nh JOIN nft_metadata nm ON nh.contract_address = nm.contract_address AND nh.token_id = nm.token_id WHERE nh.contract_type = 'ERC1155' AND CAST(nh.amount AS decimal) > 1000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas (\n block_timestamp timestamp(6) NOT NULL, -- Timestamp of the block when token metadata was recorded\n block_number bigint NOT NULL, -- Block number uniquely identifying the block\n transaction_hash varchar NOT NULL, -- Hash value of the transaction\n transaction_index bigint NOT NULL, -- Index of the transaction within the block\n from_address varchar NOT NULL, -- Address from which the transaction originated\n contract_address varchar NOT NULL, -- Address of the token contract\n symbol varchar NOT NULL, -- Symbol of the token\n total_supply varchar NOT NULL, -- erc20 contract total supply\n name varchar NOT NULL, -- Name of the token\n decimals bigint NOT NULL, -- Number of decimal places for the token\n is_erc20 integer NOT NULL, -- Flag indicating if the token is an ERC-20 token (0 or 1)\n is_erc721 integer NOT NULL, -- Flag indicating if the token is an ERC-721 token (0 or 1)\n is_erc1155 integer NOT NULL, -- Flag indicating if the token is an ERC-1155 token (0 or 1)\n is_proxy integer NOT NULL, -- Flag indicating if the token is a proxy (0 or 1)\n extra_info varchar NOT NULL, -- Additional information about the token\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 5760))\n)\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders (\n block_number bigint NOT NULL, -- Block number containing the transaction\n contract_address varchar NOT NULL, -- Event contract address\n wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n token_id varchar NOT NULL, -- NFT token id\n contract_type varchar NOT NULL, -- NFT contract type\n amount varchar NOT NULL, -- Number of held NFTs\n pk varchar NOT NULL -- The last string partition of the contract.\n)\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_info (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar NOT NULL, -- Token tick\n max_supply decimal(38,0) NOT NULL, -- Max supply\n lim decimal(38,0) NOT NULL, -- Limit of each mint\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n log_index integer NOT NULL, -- Index of the log within the transaction\n type varchar NOT NULL, -- mint | transfer | burn\n tick varchar NOT NULL, -- Token tick\n id varchar(255) NOT NULL, -- Unique identifier of the inscription\n amt decimal(38,0) NOT NULL, -- Mint amount\n from_address varchar(42) NOT NULL, -- Address sending the inscription (matches from_address in transactions table)\n to_address varchar(42) NOT NULL -- Address receiving the inscription (match to_address in transactions table)\n)\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\n"} {"conversations": [{"role": "user", "content": "I want to identify pairs of bookings that share the same payment_transaction_id, showing both booking IDs and the payment_transaction_id."}, {"role": "assistant", "content": "SELECT b1.booking_id AS booking1, b2.booking_id AS booking2, b1.payment_transaction_id\nFROM transportation.bookings b1\nJOIN transportation.bookings b2\n ON b1.payment_transaction_id = b2.payment_transaction_id\n AND b1.booking_id < b2.booking_id;"}, {"role": "user", "content": "Now limit the results to only include pairs where both bookings have a status of 'Completed'."}, {"role": "assistant", "content": "SELECT b1.booking_id AS booking1, b2.booking_id AS booking2, b1.payment_transaction_id\nFROM transportation.bookings b1\nJOIN transportation.bookings b2\n ON b1.payment_transaction_id = b2.payment_transaction_id\n AND b1.booking_id < b2.booking_id\nWHERE b1.status = 'Completed'\n AND b2.status = 'Completed';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"} {"conversations": [{"role": "user", "content": "List all managers (employees who have other employees reporting to them) along with the count of their direct reports, showing only those with more than 5 reports."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name, e.last_name, COUNT(r.employee_id) as direct_reports_count FROM financial_services.employees e JOIN financial_services.employees r ON e.employee_id = r.manager_id WHERE e.status = 'Active' GROUP BY e.employee_id, e.first_name, e.last_name HAVING COUNT(r.employee_id) > 5 ORDER BY direct_reports_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.employees ( employee_id text PRIMARY KEY, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\n"} {"conversations": [{"role": "user", "content": "List all claims that were reported more than 30 days after the incident date."}, {"role": "assistant", "content": "SELECT claim_id, policy_id, customer_id, incident_date, reported_date FROM insurance.claims WHERE DATEDIFF(reported_date, incident_date) > 30;"}, {"role": "user", "content": "Now show only claims that are still pending (status = 'pending')."}, {"role": "assistant", "content": "SELECT claim_id, policy_id, customer_id, incident_date, reported_date FROM insurance.claims WHERE DATEDIFF(reported_date, incident_date) > 30 AND status = 'pending';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims ( claim_id.text, policy_id.text, customer_id.text, incident_date.timestamp, reported_date.timestamp, description.text, estimated_loss.numeric, status.text, settlement_amount.numeric, settlement_date.date, claim_handler_id.text, police_report_number.text )\n"} {"conversations": [{"role": "user", "content": "Show me all users who registered with a Gmail email address, along with their usernames and registration dates."}, {"role": "assistant", "content": "SELECT username, email FROM blockchain.users WHERE email LIKE '%@gmail.com';"}, {"role": "user", "content": "Now filter these results to only show users whose usernames start with the letter 'A'."}, {"role": "assistant", "content": "SELECT username, email FROM blockchain.users WHERE email LIKE '%@gmail.com' AND username LIKE 'A%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.users ( user_id text, username text, email text, password_hash text )\n"} {"conversations": [{"role": "user", "content": "Identify all instances where a vehicle's odometer_reading increased by more than 500 miles between two consecutive fuel log entries."}, {"role": "assistant", "content": "SELECT a.vehicle_id,\n a.fuel_log_id AS previous_log_id,\n b.fuel_log_id AS next_log_id,\n a.log_timestamp AS previous_time,\n b.log_timestamp AS next_time,\n b.odometer_reading - a.odometer_reading AS mile_increase\nFROM transportation.fuel_logs a\nJOIN transportation.fuel_logs b\n ON a.vehicle_id = b.vehicle_id\n AND b.log_timestamp = (\n SELECT MIN(log_timestamp)\n FROM transportation.fuel_logs\n WHERE vehicle_id = a.vehicle_id\n AND log_timestamp > a.log_timestamp\n )\nWHERE b.odometer_reading - a.odometer_reading > 500;"}, {"role": "user", "content": "Now restrict these increases to those where the time difference between entries is less than 7 days."}, {"role": "assistant", "content": "SELECT a.vehicle_id,\n a.fuel_log_id AS previous_log_id,\n b.fuel_log_id AS next_log_id,\n a.log_timestamp AS previous_time,\n b.log_timestamp AS next_time,\n b.odometer_reading - a.odometer_reading AS mile_increase,\n EXTRACT(epoch FROM (b.log_timestamp - a.log_timestamp))/3600 AS hours_diff\nFROM transportation.fuel_logs a\nJOIN transportation.fuel_logs b\n ON a.vehicle_id = b.vehicle_id\n AND b.log_timestamp = (\n SELECT MIN(log_timestamp)\n FROM transportation.fuel_logs\n WHERE vehicle_id = a.vehicle_id\n AND log_timestamp > a.log_timestamp\n )\nWHERE b.odometer_reading - a.odometer_reading > 500\n AND b.log_timestamp - a.log_timestamp < INTERVAL '7 days';"}, {"role": "user", "content": "Also include both the mile increase and the time difference in hours in the final output columns."}, {"role": "assistant", "content": "SELECT a.vehicle_id,\n a.fuel_log_id AS previous_log_id,\n b.fuel_log_id AS next_log_id,\n b.odometer_reading - a.odometer_reading AS mile_increase,\n EXTRACT(epoch FROM (b.log_timestamp - a.log_timestamp))/3600 AS hours_difference\nFROM transportation.fuel_logs a\nJOIN transportation.fuel_logs b\n ON a.vehicle_id = b.vehicle_id\n AND b.log_timestamp = (\n SELECT MIN(log_timestamp)\n FROM transportation.fuel_logs\n WHERE vehicle_id = a.vehicle_id\n AND log_timestamp > a.log_timestamp\n )\nWHERE b.odometer_reading - a.odometer_reading > 500\n AND b.log_timestamp - a.log_timestamp < INTERVAL '7 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\n"} {"conversations": [{"role": "user", "content": "For each user, show their username and how many unique conversations they have sent at least one message in where the conversation is a group chat."}, {"role": "assistant", "content": "SELECT u.username, COUNT(DISTINCT m.conversation_id) AS group_chats_messaged_in\nFROM social_media.users u\nJOIN social_media.messages m ON u.user_id = m.sender_user_id\nJOIN social_media.conversations c ON m.conversation_id = c.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY u.username;"}, {"role": "user", "content": "Instead, show only users who have sent messages in more than one group chat, and include their email addresses."}, {"role": "assistant", "content": "SELECT u.username, u.email, COUNT(DISTINCT m.conversation_id) AS group_chats_messaged_in\nFROM social_media.users u\nJOIN social_media.messages m ON u.user_id = m.sender_user_id\nJOIN social_media.conversations c ON m.conversation_id = c.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY u.username, u.email\nHAVING COUNT(DISTINCT m.conversation_id) > 1;"}, {"role": "user", "content": "Also add the most recent message time sent by each user in these group chats."}, {"role": "assistant", "content": "SELECT u.username, u.email, COUNT(DISTINCT m.conversation_id) AS group_chats_messaged_in, MAX(m.sent_at) AS last_message_time\nFROM social_media.users u\nJOIN social_media.messages m ON u.user_id = m.sender_user_id\nJOIN social_media.conversations c ON m.conversation_id = c.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY u.username, u.email\nHAVING COUNT(DISTINCT m.conversation_id) > 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id.text, user_id.text, content.text, media_url.text, media_type.text, created_at.timestamp, updated_at.timestamp, visibility.text, location_lat.numeric, location_lon.numeric )\nCREATE TABLE social_media.comments (\n comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n content text NOT NULL, -- textual content of the comment\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n PRIMARY KEY (comment_id)\n)\nCREATE TABLE social_media.likes ( like_id text, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.follows ( follow_id character varying(64) NOT NULL, follower_user_id character varying(64) NOT NULL, following_user_id character varying(64) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (follow_id), CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) )\nCREATE TABLE social_media.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id character varying(64) NOT NULL, post_id character varying(64) NOT NULL, hashtag_id character varying(64) NOT NULL, PRIMARY KEY (post_hashtag_id), CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) )\nCREATE TABLE social_media.messages (\n message_id character varying(64) NOT NULL, -- unique identifier for the message\n conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n content text, -- textual content of the message\n media_url text, -- URL to attached media (image/video)\n media_type character varying(20), -- type of media ('image', 'video', null)\n sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n read_at timestamp, -- timestamp when message was read by recipient(s)\n PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversations ( conversation_id text PRIMARY KEY, created_at timestamp, last_message_at timestamp, is_group_chat bool, group_name text )\nCREATE TABLE social_media.conversation_participants (\n participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n PRIMARY KEY (participant_id),\n CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications ( notification_id.text, recipient_user_id.text, sender_user_id.text, notification_type.text, target_entity_id.text, target_entity_type.text, created_at.timestamp, read_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 projects by valuation that completed fundraising rounds in the last 12 months, along with their token symbol and price from the token_basic_info table."}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.valuation, tbi.token_symbol, tbi.price FROM project_fundraising_record pfr LEFT JOIN token_basic_info tbi ON pfr.project_name = tbi.token_name WHERE pfr.investment_date >= DATE_SUB(CURRENT_DATE, INTERVAL 12 MONTH) ORDER BY pfr.valuation DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the 24-hour trading volume for these projects' tokens and filter to only include projects with valuation over $100 million?"}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.valuation, tbi.token_symbol, tbi.price, tbi.total_volume FROM project_fundraising_record pfr LEFT JOIN token_basic_info tbi ON pfr.project_name = tbi.token_name WHERE pfr.investment_date >= DATE_SUB(CURRENT_DATE, INTERVAL 12 MONTH) AND pfr.valuation > 100000000 ORDER BY pfr.valuation DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\n \"CREATE TABLE project_fundraising_record (\",\n \"id character varying(32) NOT NULL, -- fundraising record id\",\n \"project_id character varying(32) NOT NULL, -- the invested project's id\",\n \"project_name character varying(128) NOT NULL, -- name of the invested project\",\n \"rounds_name character varying(32), -- name of the fundraising round\",\n \"investment_value numeric(38,14), -- amount of the fundraising in USD\",\n \"investment_date character varying(128), -- the date of the investment happened\",\n \"introduction character varying(128), -- the introduction of the invested project\",\n \"valuation numeric(38,14), -- the valuation of the project in USD when invested\",\n\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, -- the id of the token token_name character varying(100) NOT NULL, -- the token's name token_symbol character varying(100) NOT NULL, -- the token's symbol token_address character varying(100) NOT NULL, -- the token's address chain text, -- the chain that the token resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days highest_price_24h double precision, -- the highest price of the token in 24 hours lowest_price_24h double precision, -- the lowest price of the token in 24 hours market_cap double precision, -- the market cap of the token market_cap_rank bigint, -- the rank of the token market cap in desc market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX) narrative text, -- the category or narrative of the token trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token. ,PRIMARY KEY (coin_id, chain) )\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, -- the id of narrative top_3_coins text, -- the top 3 tokens in the narrative price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative market_cap double precision, -- the market cap of the narrative volume_24h double precision, -- the trade volume of the narrative trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative token_num bigint, -- total token number in the narrative ,PRIMARY KEY (narrative) )\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, token_name character varying(100) NOT NULL, token_symbol character varying(100) NOT NULL, chain text, price double precision, price_change_percentage_1h double precision, price_change_percentage_6h double precision, price_change_percentage_24h double precision, makers_24h double precision, volume_24h double precision, liquidity double precision, market_cap double precision, trend_rank bigint )\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, rank INT, profit numeric(38,6), roi numeric(38,2), realized_ratio numeric(38,2), most_profit_token character varying(100), last_trade_time character varying(100), chain character varying(100) )\n \"CREATE TABLE smart_money_token_performance (\",\n \"token_address character varying(100) NOT NULL, -- the token's address\",\n \"token_symbol character varying(100), -- the tokens's symbol\",\n \"pnl numeric(38,2), -- the profit users made on this token\",\n \"net_flow numeric(38,2), -- the netflow of the token, means the money user spent minus the the money user sold of this token\",\n \"avg_cost numeric(38,16), -- the average cost price of user spent on this token\",\n \"price double precision, -- the current price of the token\",\n \"realized_ratio numeric(10,2), -- the ratio user sold of the token\",\n \"roi numeric(10,2), -- the roi users made of this token\",\n \"chain character varying(100), -- the chain that the token resides\",\n \"PRIMARY KEY (token_address, chain));\",\n\n \"CREATE TABLE smart_money_token_inflow (\",\n \"token_address character varying(100) NOT NULL, -- the token's address\",\n \"token_symbol character varying(100), -- the tokens's symbol\",\n \"token_amount numeric(38,2), -- the absolute value of the amount if user bought minus the amount user sold of this token\",\n \"usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token\",\n \"avg_price numeric(38,6), -- the average cost price of user spent on this token\",\n \"type int, -- the direction of the trade on this token. 1 means buying, 2 means selling\",\n \"address_amount integer, -- the amount of the user bought this token\",\n \"narrative character varying(100), -- the category or narrative of the token\",\n \"chain character varying(100), -- the chain that the token resides\",\n \",PRIMARY KEY (token_address, chain)\",\n\n"} {"conversations": [{"role": "user", "content": "List all events and any token transfers that occurred in the same transaction, showing event_id, event_name, transfer_id, and token_symbol."}, {"role": "assistant", "content": "SELECT\n e.event_id,\n e.event_name,\n tt.transfer_id,\n tk.token_symbol\nFROM web3.events e\nLEFT JOIN web3.token_transfers tt\n ON e.transaction_id = tt.transaction_id\nLEFT JOIN web3.tokens tk\n ON tt.token_id = tk.token_id\nORDER BY e.transaction_id, e.log_index;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id character varying(64) NOT NULL, address character varying(128) NOT NULL, abi text NOT NULL, bytecode text NOT NULL, deployer_address character varying(128) NOT NULL, deployed_at timestamp NOT NULL, network_id character varying(64) NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (contract_id) )\nCREATE TABLE web3.events ( event_id.text, contract_id.text, event_name.text, data.text, emitted_at.timestamp, transaction_id.text, log_index.integer )\nCREATE TABLE web3.tokens (\n token_id character varying(64) NOT NULL, -- unique identifier for the token\n contract_address character varying(128) NOT NULL, -- address of the token contract\n token_name character varying(128) NOT NULL, -- name of the token\n token_symbol character varying(32) NOT NULL, -- symbol of the token\n decimals integer NOT NULL, -- number of decimals for the token\n total_supply numeric(38,14) NOT NULL, -- total supply of the token\n PRIMARY KEY (token_id)\n)\nCREATE TABLE web3.token_transfers ( transfer_id text PRIMARY KEY, token_id text, from_address text, to_address text, value numeric, transaction_id text, log_index int )\nCREATE TABLE web3.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "How many employees work in each department? List the department name and the count."}, {"role": "assistant", "content": "SELECT department, COUNT(*) FROM government_services.employees GROUP BY department"}, {"role": "user", "content": "Only show departments with more than 5 employees."}, {"role": "assistant", "content": "SELECT department, COUNT(*) FROM government_services.employees GROUP BY department HAVING COUNT(*) > 5"}, {"role": "user", "content": "For these departments, also list the job titles present."}, {"role": "assistant", "content": "SELECT department, COUNT(*), STRING_AGG(DISTINCT job_title, ', ') FROM government_services.employees GROUP BY department HAVING COUNT(*) > 5"}, {"role": "user", "content": "Add the total number of employees hired in 2023 for each of these departments."}, {"role": "assistant", "content": "SELECT department, COUNT(*), STRING_AGG(DISTINCT job_title, ', '), SUM(CASE WHEN EXTRACT(YEAR FROM hire_date) = 2023 THEN 1 ELSE 0 END) AS employees_hired_in_2023 FROM government_services.employees GROUP BY department HAVING COUNT(*) > 5"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id text, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.services (\n service_id character varying(64) NOT NULL, -- unique identifier for the service\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n description text,\n category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n eligibility_criteria text, -- description of who is eligible\n standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n average_processing_time_days integer, -- estimated processing time\n is_active boolean DEFAULT true, -- whether the service is currently offered\n online_application_url character varying(255),\n PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.employees ( employee_id text, agency_id text, first_name text, last_name text, job_title text, department text, work_email text, work_phone text, hire_date date, termination_date date, access_level text, manager_employee_id text )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\nCREATE TABLE government_services.appointments ( appointment_id.text, citizen_id.text, employee_id.text, location_id.text, service_id.text, scheduled_start_time.timestamp, scheduled_end_time.timestamp, purpose.text, status.text, booking_method.text, created_at.timestamp, notes.text )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 users who have interacted with DApps, along with the count of distinct DApps they interacted with and their wallet addresses."}, {"role": "assistant", "content": "SELECT w.user_id, COUNT(DISTINCT d.dapp_id) AS dapp_count, w.address FROM trading_platform.wallets w JOIN trading_platform.dapps d ON 1=1 GROUP BY w.user_id, w.address ORDER BY dapp_count DESC LIMIT 5;"}, {"role": "user", "content": "This query doesn't properly show DApp interactions. Please modify it to correctly join with a table that records user-DApp interactions."}, {"role": "assistant", "content": "I notice there's no interaction table in the provided schema. Without a table recording user-DApp interactions, I cannot generate this query accurately. Would you like to see users who have wallets and DApps separately instead?"}, {"role": "user", "content": "You're right. Instead, show me users who have wallets but have never interacted with any DApps, along with their wallet addresses."}, {"role": "assistant", "content": "SELECT w.user_id, w.address FROM trading_platform.wallets w WHERE NOT EXISTS (SELECT 1 FROM trading_platform.dapps d WHERE 1=1) GROUP BY w.user_id, w.address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.wallets ( wallet_id.text, user_id.text, address.text, private_key.text, created_at.timestamp )\nCREATE TABLE trading_platform.trades ( trade_id character varying(64) NOT NULL, order_id character varying(64) NOT NULL, buyer_id character varying(64) NOT NULL, seller_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, traded_at timestamp NOT NULL, PRIMARY KEY (trade_id) )\nCREATE TABLE trading_platform.assets ( asset_id.text, name.text, symbol.text, type.text )\nCREATE TABLE trading_platform.dapps (\n dapp_id character varying(64) NOT NULL, -- unique identifier for the DApp\n name character varying(128) NOT NULL, -- name of the DApp\n description text NOT NULL, -- description of the DApp\n url character varying(256) NOT NULL, -- URL of the DApp\n PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\n"} {"conversations": [{"role": "user", "content": "Show me all guests from 'CA' along with their full name and email address."}, {"role": "assistant", "content": "SELECT guest_id, CONCAT(first_name, ' ', last_name) AS full_name, email FROM hospitality_technology.guests WHERE country_code = 'CA';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.guests ( guest_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\n"} {"conversations": [{"role": "user", "content": "List each patient's first_name, last_name, and the plan_name and policy_number of their primary insurance plan."}, {"role": "assistant", "content": "SELECT p.first_name,\n p.last_name,\n ip.plan_name,\n pi.policy_number\nFROM healthcare.patients p\nJOIN healthcare.patient_insurance pi ON p.patient_id = pi.patient_id AND pi.is_primary = TRUE\nJOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id.text, record_id.text, patient_id.text, doctor_id.text, diagnosis_code.text, code_type.text, description.text, diagnosis_date.date, status.text, is_chronic.boolean )\nCREATE TABLE healthcare.prescriptions ( prescription_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, medication_id character varying(64) NOT NULL, dosage character varying(100) NOT NULL, frequency character varying(100) NOT NULL, route character varying(50), start_date date NOT NULL, end_date date, quantity_dispensed numeric(10,2), refills_allowed integer NOT NULL DEFAULT 0, prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (prescription_id) )\nCREATE TABLE healthcare.insurance_plans (\n plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n plan_name character varying(200) NOT NULL, -- name of the insurance plan\n insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n plan_type character varying(50), -- e.g., PPO, HMO, EPO\n contact_phone character varying(20), -- provider contact number\n website character varying(255), -- provider website\n PRIMARY KEY (plan_id)\n)\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text PRIMARY KEY, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"} {"conversations": [{"role": "user", "content": "How many reviews does each staff member respond to, along with their full name and the average response time in hours?"}, {"role": "assistant", "content": "SELECT st.staff_id,\n st.first_name || ' ' || st.last_name AS staff_full_name,\n COUNT(*) AS response_count,\n AVG(EXTRACT(EPOCH FROM (r.response_date - r.review_date)) / 3600) AS avg_response_time_hours\nFROM hospitality_technology.reviews r\nJOIN hospitality_technology.staff st\n ON r.response_staff_id = st.staff_id\nWHERE r.response_date IS NOT NULL\nGROUP BY st.staff_id, st.first_name, st.last_name;"}, {"role": "user", "content": "Filter to only include staff who responded to at least 5 reviews."}, {"role": "assistant", "content": "SELECT sub.staff_id,\n sub.staff_full_name,\n sub.response_count,\n sub.avg_response_time_hours\nFROM (\n SELECT st.staff_id,\n st.first_name || ' ' || st.last_name AS staff_full_name,\n COUNT(*) AS response_count,\n AVG(EXTRACT(EPOCH FROM (r.response_date - r.review_date)) / 3600) AS avg_response_time_hours\n FROM hospitality_technology.reviews r\n JOIN hospitality_technology.staff st\n ON r.response_staff_id = st.staff_id\n WHERE r.response_date IS NOT NULL\n GROUP BY st.staff_id, st.first_name, st.last_name\n) sub\nWHERE sub.response_count >= 5;"}, {"role": "user", "content": "Also order the result by average response time ascending."}, {"role": "assistant", "content": "SELECT sub.staff_id,\n sub.staff_full_name,\n sub.response_count,\n sub.avg_response_time_hours\nFROM (\n SELECT st.staff_id,\n st.first_name || ' ' || st.last_name AS staff_full_name,\n COUNT(*) AS response_count,\n AVG(EXTRACT(EPOCH FROM (r.response_date - r.review_date)) / 3600) AS avg_response_time_hours\n FROM hospitality_technology.reviews r\n JOIN hospitality_technology.staff st\n ON r.response_staff_id = st.staff_id\n WHERE r.response_date IS NOT NULL\n GROUP BY st.staff_id, st.first_name, st.last_name\n) sub\nWHERE sub.response_count >= 5\nORDER BY sub.avg_response_time_hours ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text PRIMARY KEY, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.rooms (\n room_id character varying(64) NOT NULL, -- unique identifier for the room\n property_id character varying(64) NOT NULL, -- FK to properties table\n room_number character varying(10) NOT NULL, -- room number identifier (e.g., '101', 'Suite 2B')\n room_type_id character varying(64) NOT NULL, -- FK to room_types table\n floor integer, -- floor number the room is on\n status character varying(50) NOT NULL, -- e.g., Available, Occupied, Cleaning, OutOfOrder, Maintenance\n is_smoking boolean NOT NULL DEFAULT false, -- smoking allowed flag\n features text, -- description of features (e.g., Balcony, Sea View, Jacuzzi)\n current_condition text, -- notes on room condition\n last_cleaned_at timestamp with time zone, -- timestamp of last cleaning\n PRIMARY KEY (room_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.room_types ( room_type_id text, property_id text, type_name text, description text, base_rate numeric, max_occupancy integer, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.guests ( guest_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id text, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level integer, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.services (\n service_id character varying(64) NOT NULL, -- unique identifier for a chargeable service\n property_id character varying(64) NOT NULL, -- FK to properties table\n service_name character varying(150) NOT NULL, -- e.g., Room Service - Burger, Spa - Massage 60min, Laundry - Shirt\n description text,\n category character varying(100), -- e.g., Food & Beverage, Wellness, Business Center, Activities\n price numeric(10, 2) NOT NULL, -- price per unit/instance\n unit character varying(30), -- e.g., Per Item, Per Hour, Per Day\n is_available boolean NOT NULL DEFAULT true, -- is the service currently offered?\n department character varying(100), -- department responsible (e.g., F&B, Spa, Housekeeping)\n PRIMARY KEY (service_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\nCREATE TABLE hospitality_technology.payments (\n payment_id character varying(64) NOT NULL, -- unique identifier for the payment transaction\n reservation_id character varying(64), -- FK to reservations (if payment is for a stay)\n guest_id character varying(64) NOT NULL, -- FK to guests (who paid)\n bill_id character varying(64), -- FK to bills/invoices this payment applies to\n amount numeric(12,2) NOT NULL, -- amount of the payment\n currency_code character varying(3) NOT NULL, -- ISO currency code (e.g., USD, EUR)\n payment_method character varying(50) NOT NULL, -- e.g., CreditCard, Cash, BankTransfer, Points, Voucher\n card_type character varying(50), -- e.g., Visa, MasterCard, Amex (if CC)\n card_last_four character varying(4), -- last 4 digits of CC (if CC)\n transaction_ref character varying(128), -- reference ID from payment gateway or processor\n payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the payment occurred\n status character varying(50) NOT NULL, -- e.g., Pending, Succeeded, Failed, Refunded, Disputed\n staff_id_processed character varying(64), -- FK to staff (who processed the payment)\n notes text, -- notes about the payment\n PRIMARY KEY (payment_id),\n FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "Show me the username and email of all users who own at least one wallet."}, {"role": "assistant", "content": "SELECT DISTINCT T1.username, T1.email FROM blockchain.users AS T1 JOIN blockchain.wallets AS T2 ON T1.user_id = T2.user_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.wallets ( wallet_id.text, user_id.text, address_id.text, private_key.text )\nCREATE TABLE blockchain.users ( user_id.text, username.text, email.text, password_hash.text )\n"} {"conversations": [{"role": "user", "content": "List the full name (first name and last name) of all citizens who have uploaded documents whose expiry date is in the past."}, {"role": "assistant", "content": "SELECT DISTINCT T1.first_name, T1.last_name FROM government_services.citizens AS T1 INNER JOIN government_services.documents AS T2 ON T1.citizen_id = T2.citizen_id WHERE T2.expiry_date < CURRENT_DATE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id text PRIMARY KEY, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.service_locations ( location_id text PRIMARY KEY, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.appointments ( appointment_id text PRIMARY KEY, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\n"} {"conversations": [{"role": "user", "content": "Show smart money addresses with an ROI greater than 3 and a realized ratio greater than 0.7. Display the address, chain, ROI, realized ratio, and most profitable token."}, {"role": "assistant", "content": "SELECT address, chain, roi, realized_ratio, most_profit_token FROM smart_money_profit WHERE roi > 3 AND realized_ratio > 0.7;"}, {"role": "user", "content": "For these tokens (`most_profit_token` from the previous result), what is the total USD value held by CEXes across all chains? Show the token symbol and the total CEX USD value."}, {"role": "assistant", "content": "WITH HighlyPerformingTokens AS (SELECT DISTINCT most_profit_token FROM smart_money_profit WHERE roi > 3 AND realized_ratio > 0.7 AND most_profit_token IS NOT NULL) SELECT c.token_symbol, SUM(c.usd_value) AS total_cex_usd_value FROM cex_token_balance c JOIN HighlyPerformingTokens h ON c.token_symbol = h.most_profit_token WHERE c.usd_value IS NOT NULL GROUP BY c.token_symbol ORDER BY total_cex_usd_value DESC;"}, {"role": "user", "content": "Filter the previous results to only include tokens where the `average_smart_money_roi` is greater than 10 (1000%) and the `average_smart_money_realized_ratio` is greater than 0.8."}, {"role": "assistant", "content": "WITH CexHeldTokens AS (SELECT DISTINCT token_symbol FROM cex_token_balance WHERE token_symbol IS NOT NULL AND token_symbol != ''), TokenPerformance AS (SELECT s.most_profit_token AS token_symbol, AVG(s.roi) AS average_smart_money_roi, AVG(s.realized_ratio) AS average_smart_money_realized_ratio FROM smart_money_profit s JOIN CexHeldTokens c ON s.most_profit_token = c.token_symbol WHERE s.roi IS NOT NULL AND s.realized_ratio IS NOT NULL GROUP BY s.most_profit_token) SELECT token_symbol, average_smart_money_roi, average_smart_money_realized_ratio FROM TokenPerformance WHERE average_smart_money_roi > 10 AND average_smart_money_realized_ratio > 0.8 ORDER BY average_smart_money_roi DESC;"}, {"role": "user", "content": "For these filtered tokens, add the total USD value held by CEXes (`usd_value` from `cex_token_balance`) to the results. Show token symbol, total CEX USD value, average ROI, and average realized ratio."}, {"role": "assistant", "content": "WITH CexHeldTokens AS (SELECT DISTINCT token_symbol FROM cex_token_balance WHERE token_symbol IS NOT NULL AND token_symbol != ''), TokenPerformance AS (SELECT s.most_profit_token AS token_symbol, AVG(s.roi) AS average_smart_money_roi, AVG(s.realized_ratio) AS average_smart_money_realized_ratio FROM smart_money_profit s JOIN CexHeldTokens c ON s.most_profit_token = c.token_symbol WHERE s.roi IS NOT NULL AND s.realized_ratio IS NOT NULL GROUP BY s.most_profit_token), FilteredPerformance AS (SELECT token_symbol, average_smart_money_roi, average_smart_money_realized_ratio FROM TokenPerformance WHERE average_smart_money_roi > 10 AND average_smart_money_realized_ratio > 0.8) SELECT fp.token_symbol, SUM(c.usd_value) AS total_cex_usd_value, fp.average_smart_money_roi, fp.average_smart_money_realized_ratio FROM FilteredPerformance fp JOIN cex_token_balance c ON fp.token_symbol = c.token_symbol WHERE c.usd_value IS NOT NULL GROUP BY fp.token_symbol, fp.average_smart_money_roi, fp.average_smart_money_realized_ratio ORDER BY fp.average_smart_money_roi DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\n \"CREATE TABLE cex_token_balance (\",\n \"snapshot_time character varying(32) NOT NULL, -- the snapshot time of record, converted from original timestamp\",\n \"chain character varying(128) NOT NULL, -- the chain that the token resides\",\n \"address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX\",\n \"exchange character varying(512) NOT NULL, -- a centralized exchange name\",\n \"token_address character varying(128) NOT NULL, -- token contract address\",\n \"token_symbol character varying(512), --token symbol\",\n \"balance numeric(38,10), -- token balance\",\n \"usd_value numeric(38,14), -- value of the token held in USD\",\n \"price double precision, --price of the token in USD\",\n \",PRIMARY KEY (snapshot_time, exchange, address, chain, token_address));\"\n\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\n"} {"conversations": [{"role": "user", "content": "Show the number of policies sold by each agent, including the agent's first and last name, specifically for policies related to 'auto' products."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, count(T2.policy_id) FROM insurance.agents AS T1 JOIN insurance.policies AS T2 ON T1.agent_id = T2.agent_id JOIN insurance.insurance_products AS T3 ON T2.product_id = T3.product_id WHERE T3.product_type = 'auto' GROUP BY T1.agent_id, T1.first_name, T1.last_name;"}, {"role": "user", "content": "Can you also include agents who haven't sold any policies for 'auto' products, showing 0 for their policy count?"}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, count(T2.policy_id) FROM insurance.agents AS T1 LEFT JOIN insurance.policies AS T2 ON T1.agent_id = T2.agent_id LEFT JOIN insurance.insurance_products AS T3 ON T2.product_id = T3.product_id AND T3.product_type = 'auto' GROUP BY T1.agent_id, T1.first_name, T1.last_name;"}, {"role": "user", "content": "Now, only include agents who are currently 'active' and have sold at least one policy for 'auto' products."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, count(T2.policy_id) FROM insurance.agents AS T1 JOIN insurance.policies AS T2 ON T1.agent_id = T2.agent_id JOIN insurance.insurance_products AS T3 ON T2.product_id = T3.product_id WHERE T3.product_type = 'auto' AND T1.status = 'active' GROUP BY T1.agent_id, T1.first_name, T1.last_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies (\n policy_id character varying(64) NOT NULL, -- unique identifier for the policy\n customer_id character varying(64) NOT NULL, -- identifier for the policyholder (FK to customers)\n product_id character varying(64) NOT NULL, -- identifier for the insurance product (FK to insurance_products)\n agent_id character varying(64), -- identifier for the agent who sold the policy (FK to agents)\n policy_number character varying(100) NOT NULL UNIQUE, -- customer-facing policy number\n start_date date NOT NULL, -- date the policy coverage begins\n end_date date NOT NULL, -- date the policy coverage ends\n premium_amount numeric(12, 2) NOT NULL, -- total premium for the policy term\n coverage_limit numeric(15, 2) NOT NULL, -- maximum amount covered\n deductible numeric(10, 2) NOT NULL, -- amount customer pays before coverage kicks in\n status character varying(30) NOT NULL, -- e.g., Active, Expired, Cancelled, Pending\n issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the policy was issued\n cancellation_date date,\n cancellation_reason text,\n PRIMARY KEY (policy_id)\n)\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\nCREATE TABLE insurance.insurance_products ( product_id.text, product_name.text, product_type.text, description.text, base_premium.numeric, coverage_details.text, underwriting_rules.text, is_active.boolean, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE insurance.agents ( agent_id.text, first_name.text, last_name.text, agency_name.text, license_number.text, license_state.text, contact_email.text, contact_phone.text, hire_date.date, termination_date.date, status.text, commission_rate.numeric, manager_id.text )\nCREATE TABLE insurance.premium_payments ( payment_id text, policy_id text, customer_id text, payment_date timestamp, amount_paid numeric, payment_method text, transaction_reference text, due_date date, payment_period_start date, payment_period_end date, status text )\n"} {"conversations": [{"role": "user", "content": "Show me all events emitted by contracts where the event name contains 'Approval', along with the contract ID and transaction ID, sorted by emitted timestamp in descending order."}, {"role": "assistant", "content": "SELECT event_id, contract_id, event_name, transaction_id, emitted_at FROM web3.events WHERE event_name LIKE '%Approval%' ORDER BY emitted_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.events (\n event_id character varying(64) NOT NULL, -- unique identifier for the event\n contract_id character varying(64) NOT NULL, -- identifier of the contract emitting the event\n event_name character varying(128) NOT NULL, -- name of the event\n data text NOT NULL, -- data payload of the event\n emitted_at timestamp NOT NULL, -- time when the event was emitted\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction that triggered the event\n log_index integer NOT NULL, -- index of the event log in the transaction\n PRIMARY KEY (event_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all the appointments that overlap in time for the same location, showing both appointment IDs, their start and end times, and the location."}, {"role": "assistant", "content": "SELECT a1.appointment_id AS appointment_id_1, a2.appointment_id AS appointment_id_2,\n a1.start_time AS start_1, a1.end_time AS end_1,\n a2.start_time AS start_2, a2.end_time AS end_2,\n a1.location\nFROM legal_services.appointments a1\nJOIN legal_services.appointments a2\n ON a1.location = a2.location\n AND a1.appointment_id < a2.appointment_id\n AND a1.start_time < a2.end_time\n AND a2.start_time < a1.end_time;"}, {"role": "user", "content": "Can you narrow this to only show overlapping appointments that are both in 'Scheduled' status?"}, {"role": "assistant", "content": "SELECT a1.appointment_id AS appointment_id_1, a2.appointment_id AS appointment_id_2,\n a1.start_time AS start_1, a1.end_time AS end_1,\n a2.start_time AS start_2, a2.end_time AS end_2,\n a1.location\nFROM legal_services.appointments a1\nJOIN legal_services.appointments a2\n ON a1.location = a2.location\n AND a1.appointment_id < a2.appointment_id\n AND a1.start_time < a2.end_time\n AND a2.start_time < a1.end_time\nWHERE a1.status = 'Scheduled' AND a2.status = 'Scheduled';"}, {"role": "user", "content": "Also, please only show overlaps that last longer than 10 minutes."}, {"role": "assistant", "content": "SELECT a1.appointment_id AS appointment_id_1, a2.appointment_id AS appointment_id_2,\n a1.start_time AS start_1, a1.end_time AS end_1,\n a2.start_time AS start_2, a2.end_time AS end_2,\n a1.location\nFROM legal_services.appointments a1\nJOIN legal_services.appointments a2\n ON a1.location = a2.location\n AND a1.appointment_id < a2.appointment_id\n AND a1.start_time < a2.end_time\n AND a2.start_time < a1.end_time\nWHERE a1.status = 'Scheduled' AND a2.status = 'Scheduled'\n AND EXTRACT(EPOCH FROM (LEAST(a1.end_time, a2.end_time) - GREATEST(a1.start_time, a2.start_time))) > 600;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.appointments ( appointment_id.text, client_id.text, lawyer_id.text, case_id.text, start_time.timestamp, end_time.timestamp, location.text, subject.text, notes.text, status.text, created_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "What are the safety ratings or crash statistics for the Boeing 787 Dreamliner?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to safety ratings or crash statistics for specific aircraft models like the Boeing 787 Dreamliner. My data is limited to the information in the aircraft_models table, which includes details such as model name, manufacturer, passenger capacity, and technical specifications. For safety-related information, I recommend consulting official aviation authorities or safety reports."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models ( model_id text, model_name text, manufacturer text, passenger_capacity integer, max_range_km integer, engine_type text, wingspan_m numeric, status text, first_flight_date date )\n"} {"conversations": [{"role": "user", "content": "Show me all trips that were delayed by more than 30 minutes, along with their vehicle and driver details, and include the origin and destination city names."}, {"role": "assistant", "content": "SELECT t.trip_id, t.vehicle_id, t.driver_id, t.scheduled_departure, t.actual_departure, EXTRACT(EPOCH FROM (t.actual_departure - t.scheduled_departure))/60 AS delay_minutes, lo.city AS origin_city, ld.city AS destination_city FROM transportation.trips t JOIN transportation.locations lo ON t.origin_location_id = lo.location_id JOIN transportation.locations ld ON t.destination_location_id = ld.location_id WHERE EXTRACT(EPOCH FROM (t.actual_departure - t.scheduled_departure))/60 > 30 AND t.status = 'completed'"}, {"role": "user", "content": "Now filter these results to only show trips where the origin city is 'San Francisco' and order them by delay time in descending order."}, {"role": "assistant", "content": "SELECT t.trip_id, t.vehicle_id, t.driver_id, t.scheduled_departure, t.actual_departure, EXTRACT(EPOCH FROM (t.actual_departure - t.scheduled_departure))/60 AS delay_minutes, lo.city AS origin_city, ld.city AS destination_city FROM transportation.trips t JOIN transportation.locations lo ON t.origin_location_id = lo.location_id JOIN transportation.locations ld ON t.destination_location_id = ld.location_id WHERE EXTRACT(EPOCH FROM (t.actual_departure - t.scheduled_departure))/60 > 30 AND t.status = 'completed' AND lo.city = 'San Francisco' ORDER BY delay_minutes DESC"}, {"role": "user", "content": "Can you also include the passenger count for these trips and limit the results to the top 10 longest delays?"}, {"role": "assistant", "content": "SELECT t.trip_id, t.vehicle_id, t.driver_id, t.scheduled_departure, t.actual_departure, EXTRACT(EPOCH FROM (t.actual_departure - t.scheduled_departure))/60 AS delay_minutes, t.passenger_count, lo.city AS origin_city, ld.city AS destination_city FROM transportation.trips t JOIN transportation.locations lo ON t.origin_location_id = lo.location_id JOIN transportation.locations ld ON t.destination_location_id = ld.location_id WHERE EXTRACT(EPOCH FROM (t.actual_departure - t.scheduled_departure))/60 > 30 AND t.status = 'completed' AND lo.city = 'San Francisco' ORDER BY delay_minutes DESC LIMIT 10"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.trips ( trip_id character varying(64) NOT NULL, route_id character varying(64), vehicle_id character varying(64) NOT NULL, driver_id character varying(64) NOT NULL, scheduled_departure timestamp with time zone NOT NULL, actual_departure timestamp with time zone, scheduled_arrival timestamp with time zone NOT NULL, actual_arrival timestamp with time zone, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, status character varying(32) NOT NULL, passenger_count integer, cargo_manifest_id character varying(64), PRIMARY KEY (trip_id) )\nCREATE TABLE transportation.locations ( location_id text, name text, type text, address_line1 text, city text, state_province text, postal_code text, country text, latitude numeric, longitude numeric, timezone text )\nCREATE TABLE transportation.maintenance_logs (\n log_id character varying(64) NOT NULL, -- unique identifier for the maintenance record\n vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle serviced\n service_date date NOT NULL, -- date the service was performed\n odometer_reading integer, -- vehicle mileage at time of service\n service_type character varying(128) NOT NULL, -- type of service (e.g., Oil Change, Tire Rotation, Engine Repair)\n description text NOT NULL, -- detailed description of work done\n cost numeric(10, 2), -- cost of the service\n mechanic_name character varying(128), -- name or ID of the mechanic/shop\n next_service_due_date date, -- recommended date for next service\n PRIMARY KEY (log_id)\n)\nCREATE TABLE transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\nCREATE TABLE transportation.passengers (\n passenger_id character varying(64) NOT NULL, -- unique identifier for the passenger\n first_name character varying(128) NOT NULL, -- passenger's first name\n last_name character varying(128) NOT NULL, -- passenger's last name\n email character varying(128) UNIQUE, -- email address\n phone_number character varying(32) UNIQUE, -- phone number\n date_of_birth date, -- passenger's date of birth\n loyalty_program_id character varying(64), -- identifier for loyalty program membership\n created_at timestamp with time zone NOT NULL, -- time when the passenger record was created\n PRIMARY KEY (passenger_id)\n)\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"} {"conversations": [{"role": "user", "content": "Find all nodes that were last seen in the last 30 days and have port numbers between 8000 and 9000."}, {"role": "assistant", "content": "SELECT node_id, ip_address, port FROM blockchain.nodes WHERE last_seen >= NOW() - INTERVAL '30 days' AND port BETWEEN 8000 AND 9000"}, {"role": "user", "content": "Can you also show the count of transactions sent from wallet addresses that share the same IP as these nodes?"}, {"role": "assistant", "content": "This query isn't possible with the current schema as there's no relationship between nodes IP addresses and wallet addresses."}, {"role": "user", "content": "Then just show me nodes that share the same IP address along with how many nodes share each IP."}, {"role": "assistant", "content": "SELECT ip_address, COUNT(*) as node_count FROM blockchain.nodes GROUP BY ip_address HAVING COUNT(*) > 1"}, {"role": "user", "content": "Now filter this to only show IP addresses with more than 3 nodes and include the earliest and latest last_seen timestamps."}, {"role": "assistant", "content": "SELECT ip_address, COUNT(*) as node_count, MIN(last_seen) as earliest_seen, MAX(last_seen) as latest_seen FROM blockchain.nodes GROUP BY ip_address HAVING COUNT(*) > 3"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.transactions ( transaction_id text, block_id text, sender_address text, receiver_address text, amount numeric, timestamp timestamp, signature text )\nCREATE TABLE blockchain.nodes ( node_id text, ip_address text, port integer, last_seen timestamp )\nCREATE TABLE blockchain.wallets ( wallet_id text, user_id text, address_id text, private_key text )\nCREATE TABLE blockchain.smart_contracts ( contract_id text, creator_address text, code text, timestamp timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me all users who have unread notifications about DApp updates, along with the notification message and DApp name."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, n.message, d.name AS dapp_name FROM trading_platform.users u JOIN trading_platform.notifications n ON u.user_id = n.user_id JOIN trading_platform.dapps d ON n.message LIKE CONCAT('%', d.name, '%') WHERE n.read_at IS NULL AND n.message LIKE '%DApp update%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.trades (\n trade_id character varying(64) NOT NULL, -- unique identifier for the trade\n order_id character varying(64) NOT NULL, -- identifier of the order that led to the trade\n buyer_id character varying(64) NOT NULL, -- identifier of the buyer\n seller_id character varying(64) NOT NULL, -- identifier of the seller\n asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n quantity numeric(38,14) NOT NULL, -- quantity of the asset in the trade\n price numeric(38,14) NOT NULL, -- price per unit of the asset\n traded_at timestamp NOT NULL, -- time when the trade was executed\n PRIMARY KEY (trade_id)\n)\nCREATE TABLE trading_platform.assets (\n asset_id character varying(64) NOT NULL, -- unique identifier for the asset\n name character varying(128) NOT NULL, -- name of the asset\n symbol character varying(32) NOT NULL, -- symbol of the asset\n type character varying(32) NOT NULL, -- type of the asset (e.g., cryptocurrency, stock)\n PRIMARY KEY (asset_id)\n)\nCREATE TABLE trading_platform.dapps (\n dapp_id character varying(64) NOT NULL, -- unique identifier for the DApp\n name character varying(128) NOT NULL, -- name of the DApp\n description text NOT NULL, -- description of the DApp\n url character varying(256) NOT NULL, -- URL of the DApp\n PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n user_id character varying(64) NOT NULL, -- identifier of the user receiving the notification\n message text NOT NULL, -- message of the notification\n sent_at timestamp NOT NULL, -- time when the notification was sent\n read_at timestamp, -- time when the notification was read\n PRIMARY KEY (notification_id)\n)\n"} {"conversations": [{"role": "user", "content": "List the first name and last name of the driver and the license plate of the vehicle used for each trip."}, {"role": "assistant", "content": "SELECT T1.first_name , T1.last_name , T3.license_plate FROM transportation.drivers AS T1 JOIN transportation.trips AS T2 ON T1.driver_id = T2.driver_id JOIN transportation.vehicles AS T3 ON T2.vehicle_id = T3.vehicle_id"}, {"role": "user", "content": "Now, restrict this list to only include trips where the vehicle's fuel type is 'Electric'."}, {"role": "assistant", "content": "SELECT T1.first_name , T1.last_name , T3.license_plate FROM transportation.drivers AS T1 JOIN transportation.trips AS T2 ON T1.driver_id = T2.driver_id JOIN transportation.vehicles AS T3 ON T2.vehicle_id = T3.vehicle_id WHERE T3.fuel_type = 'Electric'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id.text, license_plate.text, vin.text, make.text, model.text, year.integer, type.text, capacity.integer, fuel_type.text, status.text, depot_id.text, acquisition_date.date )\nCREATE TABLE transportation.drivers ( driver_id.text, employee_id.text, first_name.text, last_name.text, license_number.text, license_expiry_date.date, contact_number.text, email.text, hire_date.date, status.text )\nCREATE TABLE transportation.routes ( route_id.text, route_number.text, description.text, origin_location_id.text, destination_location_id.text, distance_km.numeric, estimated_duration_minutes.integer, type.text )\nCREATE TABLE transportation.trips ( trip_id.text, route_id.text, vehicle_id.text, driver_id.text, scheduled_departure.timestamp, actual_departure.timestamp, scheduled_arrival.timestamp, actual_arrival.timestamp, origin_location_id.text, destination_location_id.text, status.text, passenger_count.integer, cargo_manifest_id.text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\nCREATE TABLE transportation.passengers ( passenger_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, loyalty_program_id.text, created_at.timestamp )\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"} {"conversations": [{"role": "user", "content": "List pairs of citizens who share the same email domain."}, {"role": "assistant", "content": "SELECT c1.first_name AS first1,\n c1.last_name AS last1,\n c2.first_name AS first2,\n c2.last_name AS last2,\n SPLIT_PART(c1.contact_email, '@', 2) AS domain\nFROM government_services.citizens c1\nJOIN government_services.citizens c2\n ON SPLIT_PART(c1.contact_email, '@', 2) = SPLIT_PART(c2.contact_email, '@', 2)\n AND c1.citizen_id < c2.citizen_id\nWHERE c1.contact_email IS NOT NULL\n AND c2.contact_email IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n citizen_id character varying(64) NOT NULL, -- unique identifier for the citizen\n national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n date_of_birth date NOT NULL,\n gender character varying(20),\n primary_address text NOT NULL, -- full primary residential address\n contact_email character varying(128) UNIQUE,\n contact_phone character varying(32),\n registration_date timestamp NOT NULL, -- when the citizen profile was created\n is_verified boolean DEFAULT false, -- whether identity has been officially verified\n PRIMARY KEY (citizen_id)\n)\n"} {"conversations": [{"role": "user", "content": "For each lawyer, show their first name, last name, and the total number of documents they have uploaded, along with the names of the law firms they belong to."}, {"role": "assistant", "content": "SELECT l.first_name, l.last_name, f.firm_name, COUNT(d.document_id) AS document_count\nFROM legal_services.lawyers l\nLEFT JOIN legal_services.law_firms f ON l.firm_id = f.firm_id\nLEFT JOIN legal_services.documents d ON l.lawyer_id = d.uploaded_by_lawyer_id\nGROUP BY l.lawyer_id, l.first_name, l.last_name, f.firm_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text PRIMARY KEY, first_name text, last_name text, company_name text, email text UNIQUE, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.lawyers (\n lawyer_id character varying(64) NOT NULL, -- unique identifier for the lawyer\n first_name character varying(100) NOT NULL, -- lawyer's first name\n last_name character varying(100) NOT NULL, -- lawyer's last name\n bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n firm_id character varying(64), -- FK to law_firms table\n email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n phone character varying(32), -- lawyer's contact phone number\n specialization text, -- areas of legal expertise\n hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n PRIMARY KEY (lawyer_id)\n)\nCREATE TABLE legal_services.law_firms ( firm_id text PRIMARY KEY, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.documents (\n document_id character varying(64) NOT NULL, -- unique identifier for the document\n case_id character varying(64) NOT NULL, -- FK to cases table\n document_name character varying(255) NOT NULL, -- name of the document file\n document_type character varying(100), -- e.g., Pleading, Contract, Evidence, Correspondence\n storage_path text NOT NULL, -- path or reference to the document storage location\n uploaded_by_lawyer_id character varying(64), -- FK to lawyers table (who uploaded it)\n upload_timestamp timestamp NOT NULL, -- time the document was uploaded\n version integer DEFAULT 1, -- document version number\n description text, -- brief description or notes about the document\n PRIMARY KEY (document_id)\n)\nCREATE TABLE legal_services.time_entries (\n entry_id character varying(64) NOT NULL, -- unique identifier for the time entry\n case_id character varying(64) NOT NULL, -- FK to cases table\n lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (who performed the work)\n date_worked date NOT NULL, -- date the work was performed\n hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), -- duration of work in hours (e.g., 1.5 for 1h 30m)\n billing_rate numeric(10, 2) NOT NULL, -- hourly rate applied for this entry\n description text NOT NULL, -- detailed description of the work performed\n is_billable boolean DEFAULT true, -- whether this time entry is billable to the client\n is_billed boolean DEFAULT false, -- whether this entry has been included in an invoice\n invoice_id character varying(64), -- FK to invoices table (once billed)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the entry was recorded\n PRIMARY KEY (entry_id)\n)\nCREATE TABLE legal_services.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n client_id character varying(64) NOT NULL, -- FK to clients table\n lawyer_id character varying(64) NOT NULL, -- FK to lawyers table\n case_id character varying(64), -- FK to cases table (optional, if related to a specific case)\n start_time timestamp NOT NULL, -- scheduled start date and time\n end_time timestamp NOT NULL, -- scheduled end date and time\n location text, -- location of the meeting (address or virtual link)\n subject character varying(255), -- subject or purpose of the appointment\n notes text, -- additional notes for the appointment\n status character varying(50) NOT NULL, -- e.g., Scheduled, Completed, Canceled, Rescheduled\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (appointment_id)\n)\n"} {"conversations": [{"role": "user", "content": "Find appointments that are longer than 30 minutes."}, {"role": "assistant", "content": "SELECT * FROM legal_services.appointments WHERE end_time IS NOT NULL AND start_time IS NOT NULL AND end_time > start_time + INTERVAL '30 minutes'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.appointments ( appointment_id.text, client_id.text, lawyer_id.text, case_id.text, start_time.timestamp, end_time.timestamp, location.text, subject.text, notes.text, status.text, created_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "List all active SUI coins with status 'exists' in metadata, showing coin_type, symbol, name, balance, and description."}, {"role": "assistant", "content": "SELECT sc.coin_type, sm.symbol, sm.name, sc.balance, sm.description\nFROM sui_coins sc\nJOIN sui_coins_metadata sm ON sc.coin_type = sm.coin_type\nWHERE sm.status = 'exists';"}, {"role": "user", "content": "Limit to coins where balance > 1000000 and order by balance descending."}, {"role": "assistant", "content": "SELECT sc.coin_type, sm.symbol, sm.name, sc.balance, sm.description\nFROM sui_coins sc\nJOIN sui_coins_metadata sm ON sc.coin_type = sm.coin_type\nWHERE sm.status = 'exists'\n AND CAST(sc.balance AS numeric) > 1000000\nORDER BY CAST(sc.balance AS numeric) DESC;"}, {"role": "user", "content": "Also include the number of distinct owners per coin_type."}, {"role": "assistant", "content": "SELECT sc.coin_type, sm.symbol, sm.name, sm.description,\n SUM(CAST(sc.balance AS numeric)) AS total_balance,\n COUNT(DISTINCT sc.owner) AS owner_count\nFROM sui_coins sc\nJOIN sui_coins_metadata sm ON sc.coin_type = sm.coin_type\nWHERE sm.status = 'exists'\n AND CAST(sc.balance AS numeric) > 1000000\nGROUP BY sc.coin_type, sm.symbol, sm.name, sm.description\nORDER BY total_balance DESC;"}, {"role": "user", "content": "Only show the top 3 coins by total_balance."}, {"role": "assistant", "content": "SELECT sc.coin_type, sm.symbol, sm.name, sm.description,\n SUM(CAST(sc.balance AS numeric)) AS total_balance,\n COUNT(DISTINCT sc.owner) AS owner_count\nFROM sui_coins sc\nJOIN sui_coins_metadata sm ON sc.coin_type = sm.coin_type\nWHERE sm.status = 'exists'\n AND CAST(sc.balance AS numeric) > 1000000\nGROUP BY sc.coin_type, sm.symbol, sm.name, sm.description\nORDER BY total_balance DESC\nLIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n object_id varchar NOT NULL, -- object id of the coin metadata object\n coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n status varchar NOT NULL, -- coin status, eg. exists, deleted\n decimals bigint NOT NULL, -- decimals of the coin\n description varchar NOT NULL, -- description of the coin\n icon_url varchar NOT NULL, -- icon url of the coin\n symbol varchar NOT NULL, -- symbol of the coin\n name varchar NOT NULL -- name of the coin\n)\nCREATE TABLE token_prices_latest ( blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE erc20_approval ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text, pk.integer )\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_bitcoin (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply varchar NOT NULL, -- Max supply: Set max supply of the inscription\n amount varchar NOT NULL -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"} {"conversations": [{"role": "user", "content": "Find all contracts where the deployer address is the same as the contract address, indicating self-deployed contracts."}, {"role": "assistant", "content": "SELECT address, deployer_address FROM web3.contracts WHERE address = deployer_address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id text, address text, abi text, bytecode text, deployer_address text, deployed_at timestamp, network_id text, status text )\n"} {"conversations": [{"role": "user", "content": "How many messages in total have been sent that do not contain any media attachment?"}, {"role": "assistant", "content": "SELECT COUNT(*) AS non_media_message_count\nFROM social_media.messages\nWHERE media_url IS NULL OR media_url = '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.messages ( message_id text PRIMARY KEY, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Find pairs of citizens who share the same gender but registered in different years. Show each citizen's first and last name along with their registration year."}, {"role": "assistant", "content": "SELECT c1.first_name AS first_name_1,\n c1.last_name AS last_name_1,\n EXTRACT(YEAR FROM c1.registration_date) AS reg_year_1,\n c2.first_name AS first_name_2,\n c2.last_name AS last_name_2,\n EXTRACT(YEAR FROM c2.registration_date) AS reg_year_2\nFROM government_services.citizens c1\nJOIN government_services.citizens c2\n ON c1.gender = c2.gender\n AND EXTRACT(YEAR FROM c1.registration_date) <> EXTRACT(YEAR FROM c2.registration_date)\n AND c1.citizen_id < c2.citizen_id;"}, {"role": "user", "content": "Exclude any pairs where either citizen is not verified."}, {"role": "assistant", "content": "SELECT c1.first_name AS first_name_1,\n c1.last_name AS last_name_1,\n EXTRACT(YEAR FROM c1.registration_date) AS reg_year_1,\n c2.first_name AS first_name_2,\n c2.last_name AS last_name_2,\n EXTRACT(YEAR FROM c2.registration_date) AS reg_year_2\nFROM government_services.citizens c1\nJOIN government_services.citizens c2\n ON c1.gender = c2.gender\n AND EXTRACT(YEAR FROM c1.registration_date) <> EXTRACT(YEAR FROM c2.registration_date)\n AND c1.citizen_id < c2.citizen_id\nWHERE c1.is_verified = TRUE\n AND c2.is_verified = TRUE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\n"} {"conversations": [{"role": "user", "content": "Show me all reservations with their guest IDs and room IDs where the total amount is greater than $500 and the status is 'Confirmed', ordered by check-in date."}, {"role": "assistant", "content": "SELECT reservation_id, guest_id, room_id, check_in_date, total_amount FROM hospitality_technology.reservations WHERE total_amount > 500 AND status = 'Confirmed' ORDER BY check_in_date;"}, {"role": "user", "content": "Now, join this with the service_orders table to include the total price of all services ordered for each reservation."}, {"role": "assistant", "content": "SELECT r.reservation_id, r.guest_id, r.room_id, r.check_in_date, r.total_amount, SUM(so.total_price) AS total_service_price FROM hospitality_technology.reservations r LEFT JOIN hospitality_technology.service_orders so ON r.reservation_id = so.reservation_id WHERE r.total_amount > 500 AND r.status = 'Confirmed' GROUP BY r.reservation_id, r.guest_id, r.room_id, r.check_in_date, r.total_amount ORDER BY r.check_in_date;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.reservations ( reservation_id.text, property_id.text, guest_id.text, room_id.text, room_type_id.text, check_in_date.date, check_out_date.date, actual_check_in_ts.timestamp, actual_check_out_ts.timestamp, num_adults.integer, num_children.integer, status.text, booking_source.text, rate_plan_id.text, total_amount.numeric, amount_paid.numeric, special_requests.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "List the claim_id and the total number of documents uploaded for each claim, but only include claims with between 3 and 7 documents."}, {"role": "assistant", "content": "SELECT claim_id, COUNT(*) AS document_count FROM insurance.claim_documents GROUP BY claim_id HAVING COUNT(*) BETWEEN 3 AND 7;"}, {"role": "user", "content": "Can you also show the upload time of the most recent document for each claim in this list?"}, {"role": "assistant", "content": "SELECT cd.claim_id, COUNT(*) AS document_count, MAX(cd.uploaded_at) AS latest_uploaded_at FROM insurance.claim_documents cd GROUP BY cd.claim_id HAVING COUNT(*) BETWEEN 3 AND 7;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claim_documents ( document_id.text, claim_id.text, document_type.text, file_name.text, file_path.text, file_size_bytes.integer, mime_type.text, uploaded_by.text, uploaded_at.timestamp, description.text )\n"} {"conversations": [{"role": "user", "content": "List all claims along with the first and last names of the agent who is currently handling each claim."}, {"role": "assistant", "content": "SELECT c.claim_id, c.policy_id, c.incident_date, a.first_name AS agent_first_name, a.last_name AS agent_last_name\nFROM insurance.claims c\nJOIN insurance.agents a ON c.claim_handler_id = a.agent_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims (\n claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n description text NOT NULL, -- detailed description of the incident and claim\n estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n settlement_amount numeric(15, 2), -- final amount paid out\n settlement_date date,\n claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n police_report_number character varying(100),\n PRIMARY KEY (claim_id)\n)\nCREATE TABLE insurance.agents ( agent_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, agency_name character varying(150), license_number character varying(100) NOT NULL UNIQUE, license_state character varying(50) NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(30), hire_date date, termination_date date, status character varying(20) NOT NULL DEFAULT 'Active', commission_rate numeric(5, 4) NOT NULL DEFAULT 0.05, manager_id character varying(64), PRIMARY KEY (agent_id) )\n"} {"conversations": [{"role": "user", "content": "Show me all messages sent after July 1, 2024, including the sender_user_id, content, and sent_at."}, {"role": "assistant", "content": "SELECT message_id, sender_user_id, content, sent_at\nFROM social_media.messages\nWHERE sent_at > '2024-07-01';"}, {"role": "user", "content": "Can you also include the conversation_id and only show messages that have not been read yet?"}, {"role": "assistant", "content": "SELECT message_id, sender_user_id, conversation_id, content, sent_at\nFROM social_media.messages\nWHERE sent_at > '2024-07-01' AND read_at IS NULL;"}, {"role": "user", "content": "Now only show results where the message contains a media attachment and order the results by sent_at descending."}, {"role": "assistant", "content": "SELECT message_id, sender_user_id, conversation_id, content, sent_at\nFROM social_media.messages\nWHERE sent_at > '2024-07-01' AND read_at IS NULL AND media_url IS NOT NULL AND media_url <> ''\nORDER BY sent_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.messages ( message_id text PRIMARY KEY, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Show each policy number and the total amount paid for it across all premium payments received so far."}, {"role": "assistant", "content": "SELECT T1.policy_number, SUM(T2.amount_paid) FROM insurance.policies AS T1 JOIN insurance.premium_payments AS T2 ON T1.policy_id = T2.policy_id GROUP BY T1.policy_number;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\nCREATE TABLE insurance.claims (\n claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n description text NOT NULL, -- detailed description of the incident and claim\n estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n settlement_amount numeric(15, 2), -- final amount paid out\n settlement_date date,\n claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n police_report_number character varying(100),\n PRIMARY KEY (claim_id)\n)\nCREATE TABLE insurance.insurance_products ( product_id text PRIMARY KEY, product_name text, product_type text, description text, base_premium numeric, coverage_details text, underwriting_rules text, is_active boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE insurance.agents ( agent_id text, first_name text, last_name text, agency_name text, license_number text, license_state text, contact_email text, contact_phone text, hire_date date, termination_date date, status text, commission_rate numeric, manager_id text )\nCREATE TABLE insurance.premium_payments (\n payment_id character varying(64) NOT NULL, -- unique identifier for the payment\n policy_id character varying(64) NOT NULL, -- identifier of the policy the payment is for (FK to policies)\n customer_id character varying(64) NOT NULL, -- identifier of the customer making the payment (FK to customers)\n payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the payment was received\n amount_paid numeric(12, 2) NOT NULL, -- amount of the payment\n payment_method character varying(50), -- e.g., Credit Card, Bank Transfer, Check\n transaction_reference character varying(128) UNIQUE, -- reference from payment processor\n due_date date, -- due date for this payment installment\n payment_period_start date, -- start date of the period this payment covers\n payment_period_end date, -- end date of the period this payment covers\n status character varying(30) NOT NULL DEFAULT 'Completed', -- e.g., Completed, Pending, Failed, Refunded\n PRIMARY KEY (payment_id)\n)\nCREATE TABLE insurance.claim_documents ( document_id character varying(64) NOT NULL, claim_id character varying(64) NOT NULL, document_type character varying(50) NOT NULL, file_name character varying(255) NOT NULL, file_path character varying(512) NOT NULL, file_size_bytes integer, mime_type character varying(100), uploaded_by character varying(64), uploaded_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text, PRIMARY KEY (document_id) )\n"} {"conversations": [{"role": "user", "content": "How many documents are there for each document_type? Show document_type and count ordered by the count in descending order."}, {"role": "assistant", "content": "SELECT document_type,\n COUNT(*) AS count\nFROM legal_services.documents\nGROUP BY document_type\nORDER BY count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.documents ( document_id.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\n"} {"conversations": [{"role": "user", "content": "Can you give me the list of server names and their regions, along with the total number of players currently online in each region?"}, {"role": "assistant", "content": "SELECT region, SUM(current_players) AS total_current_players, STRING_AGG(server_name, ', ') AS server_names\nFROM gaming_technology.servers\nWHERE status = 'online'\nGROUP BY region;"}, {"role": "user", "content": "I want to include the count of servers in each region as well. Can you modify the query?"}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, SUM(current_players) AS total_current_players, STRING_AGG(server_name, ', ') AS server_names\nFROM gaming_technology.servers\nWHERE status = 'online'\nGROUP BY region;"}, {"role": "user", "content": "Add only those regions where the server count is more than 2."}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, SUM(current_players) AS total_current_players, STRING_AGG(server_name, ', ') AS server_names\nFROM gaming_technology.servers\nWHERE status = 'online'\nGROUP BY region\nHAVING COUNT(server_id) > 2;"}, {"role": "user", "content": "Can you also sort the results by total_current_players in descending order?"}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, SUM(current_players) AS total_current_players, STRING_AGG(server_name, ', ') AS server_names\nFROM gaming_technology.servers\nWHERE status = 'online'\nGROUP BY region\nHAVING COUNT(server_id) > 2\nORDER BY total_current_players DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.servers ( server_id.uuid, game_id.uuid, server_name.text, region.text, ip_address.text, port.integer, current_players.integer, max_players.integer, status.text, last_heartbeat.timestamptz )\n"} {"conversations": [{"role": "user", "content": "Find the average percentage share among all beneficiaries for each distinct relationship type."}, {"role": "assistant", "content": "SELECT relationship, AVG(percentage_share) FROM insurance.policy_beneficiaries GROUP BY relationship ORDER BY relationship;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.insurance_products ( product_id.text, product_name.text, product_type.text, description.text, base_premium.numeric, coverage_details.text, underwriting_rules.text, is_active.boolean, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id text PRIMARY KEY, policy_id text, customer_id text, first_name text, last_name text, relationship text, percentage_share numeric, contact_info text, added_at timestamp )\n"} {"conversations": [{"role": "user", "content": "List all appointments scheduled in the next 30 days with appointment_id, client_id, case_id, and any invoice_id linked to that case."}, {"role": "assistant", "content": "SELECT\n a.appointment_id,\n a.client_id,\n a.case_id,\n i.invoice_id\nFROM legal_services.appointments AS a\nLEFT JOIN legal_services.invoices AS i\n ON a.case_id = i.case_id\nWHERE a.start_time BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '30 days';"}, {"role": "user", "content": "Change to include only appointments with status 'Scheduled' and invoices that are not fully paid."}, {"role": "assistant", "content": "SELECT\n a.appointment_id,\n a.client_id,\n a.case_id,\n i.invoice_id\nFROM legal_services.appointments AS a\nLEFT JOIN legal_services.invoices AS i\n ON a.case_id = i.case_id\nWHERE a.start_time BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '30 days'\n AND a.status = 'Scheduled'\n AND (i.status IS NULL OR i.status <> 'Paid');"}, {"role": "user", "content": "Also include only those where the case_type is 'Corporate'."}, {"role": "assistant", "content": "SELECT\n a.appointment_id,\n a.client_id,\n a.case_id,\n i.invoice_id\nFROM legal_services.appointments AS a\nJOIN legal_services.cases AS c\n ON a.case_id = c.case_id\nLEFT JOIN legal_services.invoices AS i\n ON a.case_id = i.case_id\nWHERE a.start_time BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '30 days'\n AND a.status = 'Scheduled'\n AND (i.status IS NULL OR i.status <> 'Paid')\n AND c.case_type = 'Corporate';"}, {"role": "user", "content": "Finally, order by start_time ascending and return only the first 10 rows."}, {"role": "assistant", "content": "SELECT\n a.appointment_id,\n a.client_id,\n a.case_id,\n i.invoice_id\nFROM legal_services.appointments AS a\nJOIN legal_services.cases AS c\n ON a.case_id = c.case_id\nLEFT JOIN legal_services.invoices AS i\n ON a.case_id = i.case_id\nWHERE a.start_time BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '30 days'\n AND a.status = 'Scheduled'\n AND (i.status IS NULL OR i.status <> 'Paid')\n AND c.case_type = 'Corporate'\nORDER BY a.start_time ASC\nLIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.law_firms (\n firm_id character varying(64) NOT NULL, -- unique identifier for the law firm\n firm_name character varying(200) NOT NULL, -- official name of the law firm\n address text NOT NULL, -- primary address of the firm\n phone character varying(32), -- firm's main phone number\n website character varying(255), -- firm's website URL\n founded_date date, -- date the firm was established\n managing_partner_id character varying(64), -- FK to lawyers table (optional)\n PRIMARY KEY (firm_id)\n)\nCREATE TABLE legal_services.cases (\n case_id character varying(64) NOT NULL, -- unique identifier for the case/matter\n case_number character varying(100) UNIQUE, -- official case number (court or internal)\n case_name text NOT NULL, -- descriptive name or title for the case\n client_id character varying(64) NOT NULL, -- FK to clients table\n lead_lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (primary lawyer responsible)\n case_type character varying(100) NOT NULL, -- e.g., Litigation, Corporate, Family Law, IP\n status character varying(50) NOT NULL, -- e.g., Open, Closed, Pending, On Hold, Appealed\n date_opened timestamp NOT NULL, -- date the case was formally opened\n date_closed timestamp, -- date the case was closed (nullable)\n description text, -- detailed description of the case\n court_jurisdiction character varying(128), -- court or jurisdiction if applicable\n PRIMARY KEY (case_id)\n)\nCREATE TABLE legal_services.time_entries (\n entry_id character varying(64) NOT NULL, -- unique identifier for the time entry\n case_id character varying(64) NOT NULL, -- FK to cases table\n lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (who performed the work)\n date_worked date NOT NULL, -- date the work was performed\n hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), -- duration of work in hours (e.g., 1.5 for 1h 30m)\n billing_rate numeric(10, 2) NOT NULL, -- hourly rate applied for this entry\n description text NOT NULL, -- detailed description of the work performed\n is_billable boolean DEFAULT true, -- whether this time entry is billable to the client\n is_billed boolean DEFAULT false, -- whether this entry has been included in an invoice\n invoice_id character varying(64), -- FK to invoices table (once billed)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the entry was recorded\n PRIMARY KEY (entry_id)\n)\nCREATE TABLE legal_services.invoices (\n invoice_id character varying(64) NOT NULL, -- unique identifier for the invoice\n invoice_number character varying(100) UNIQUE NOT NULL, -- user-facing invoice number\n client_id character varying(64) NOT NULL, -- FK to clients table\n case_id character varying(64), -- FK to cases table (optional, could be general retainer)\n issue_date date NOT NULL, -- date the invoice was generated\n due_date date NOT NULL, -- date the payment is due\n total_amount numeric(12, 2) NOT NULL, -- total amount due on the invoice\n amount_paid numeric(12, 2) DEFAULT 0.00, -- amount already paid\n status character varying(50) NOT NULL, -- e.g., Draft, Sent, Paid, Partially Paid, Overdue, Void\n payment_date timestamp, -- date the invoice was fully paid (nullable)\n notes text, -- additional notes or terms on the invoice\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (invoice_id)\n)\nCREATE TABLE legal_services.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n client_id character varying(64) NOT NULL, -- FK to clients table\n lawyer_id character varying(64) NOT NULL, -- FK to lawyers table\n case_id character varying(64), -- FK to cases table (optional, if related to a specific case)\n start_time timestamp NOT NULL, -- scheduled start date and time\n end_time timestamp NOT NULL, -- scheduled end date and time\n location text, -- location of the meeting (address or virtual link)\n subject character varying(255), -- subject or purpose of the appointment\n notes text, -- additional notes for the appointment\n status character varying(50) NOT NULL, -- e.g., Scheduled, Completed, Canceled, Rescheduled\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (appointment_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me all policies that expired in the last 60 days, along with their product IDs and premium amounts."}, {"role": "assistant", "content": "SELECT policy_id, product_id, premium_amount FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE;"}, {"role": "user", "content": "Now include only policies that had a deductible of $1000 or more."}, {"role": "assistant", "content": "SELECT policy_id, product_id, premium_amount, deductible FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE AND deductible >= 1000;"}, {"role": "user", "content": "I also want to see the count of such expired policies per product ID."}, {"role": "assistant", "content": "SELECT product_id, COUNT(*) as policy_count FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE AND deductible >= 1000 GROUP BY product_id ORDER BY policy_count DESC;"}, {"role": "user", "content": "Finally, show me the average premium amount for these expired high-deductible policies grouped by product ID."}, {"role": "assistant", "content": "SELECT product_id, AVG(premium_amount) as avg_premium FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE AND deductible >= 1000 GROUP BY product_id ORDER BY avg_premium DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text PRIMARY KEY, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\n"} {"conversations": [{"role": "user", "content": "What is the average ROI for smart money addresses on the Ethereum chain?"}, {"role": "assistant", "content": "SELECT AVG(roi) FROM smart_money_token_performance WHERE chain = 'Ethereum';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\n \"CREATE TABLE project_fundraising_record (\",\n \"id character varying(32) NOT NULL, -- fundraising record id\",\n \"project_id character varying(32) NOT NULL, -- the invested project's id\",\n \"project_name character varying(128) NOT NULL, -- name of the invested project\",\n \"rounds_name character varying(32), -- name of the fundraising round\",\n \"investment_value numeric(38,14), -- amount of the fundraising in USD\",\n \"investment_date character varying(128), -- the date of the investment happened\",\n \"introduction character varying(128), -- the introduction of the invested project\",\n \"valuation numeric(38,14), -- the valuation of the project in USD when invested\",\n\n \"CREATE TABLE token_basic_info (\",\n \"coin_id character varying(100) NOT NULL, -- the id of the token\",\n \"token_name character varying(100) NOT NULL, -- the token's name\",\n \"token_symbol character varying(100) NOT NULL, -- the token's symbol\",\n \"token_address character varying(100) NOT NULL, -- the token's address\",\n \"chain text, -- the chain that the token resides\",\n \"price double precision, -- the current price of the token\",\n \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour\",\n \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours\",\n \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days\",\n \"highest_price_24h double precision, -- the highest price of the token in 24 hours\",\n \"lowest_price_24h double precision, -- the lowest price of the token in 24 hours\",\n \"market_cap double precision, -- the market cap of the token\",\n \"market_cap_rank bigint, -- the rank of the token market cap in desc\",\n \"market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours\",\n \"total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX)\", \n \"narrative text, -- the category or narrative of the token\",\n \"trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token.\",\n \",PRIMARY KEY (coin_id, chain));\",\n\n \"CREATE TABLE narrative_info (\",\n \"narrative character varying(512) NOT NULL, -- the id of narrative\",\n \"top_3_coins text, -- the top 3 tokens in the narrative\",\n \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative\",\n \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative\",\n \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative\",\n \"market_cap double precision, -- the market cap of the narrative\",\n \"volume_24h double precision, -- the trade volume of the narrative\",\n \"trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative\",\n \"token_num bigint, -- total token number in the narrative\",\n \",PRIMARY KEY (narrative));\"\n\n \"CREATE TABLE cex_token_balance (\",\n \"snapshot_time character varying(32) NOT NULL, -- the snapshot time of record, converted from original timestamp\",\n \"chain character varying(128) NOT NULL, -- the chain that the token resides\",\n \"address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX\",\n \"exchange character varying(512) NOT NULL, -- a centralized exchange name\",\n \"token_address character varying(128) NOT NULL, -- token contract address\",\n \"token_symbol character varying(512), --token symbol\",\n \"balance numeric(38,10), -- token balance\",\n \"usd_value numeric(38,14), -- value of the token held in USD\",\n \"price double precision, --price of the token in USD\",\n \",PRIMARY KEY (snapshot_time, exchange, address, chain, token_address));\"\n\n \"CREATE TABLE smart_money_token_performance (\",\n \"token_address character varying(100) NOT NULL, -- the token's address\",\n \"token_symbol character varying(100), -- the tokens's symbol\",\n \"pnl numeric(38,2), -- the profit users made on this token\",\n \"net_flow numeric(38,2), -- the netflow of the token, means the money user spent minus the the money user sold of this token\",\n \"avg_cost numeric(38,16), -- the average cost price of user spent on this token\",\n \"price double precision, -- the current price of the token\",\n \"realized_ratio numeric(10,2), -- the ratio user sold of the token\",\n \"roi numeric(10,2), -- the roi users made of this token\",\n \"chain character varying(100), -- the chain that the token resides\",\n \"PRIMARY KEY (token_address, chain));\",\n\n"} {"conversations": [{"role": "user", "content": "Show me wallet addresses that hold more than 1000 of any ERC20 token, along with the token symbol and amount, sorted by amount in descending order."}, {"role": "assistant", "content": "SELECT b.wallet_address, t.symbol, b.amount FROM erc20_balances b JOIN sui_coins_metadata t ON b.contract_address = t.coin_type WHERE CAST(b.amount AS decimal) > 1000 ORDER BY CAST(b.amount AS decimal) DESC;"}, {"role": "user", "content": "Can you also include the current price of each token from the token_prices_latest table?"}, {"role": "assistant", "content": "SELECT b.wallet_address, t.symbol, b.amount, p.price FROM erc20_balances b JOIN sui_coins_metadata t ON b.contract_address = t.coin_type JOIN token_prices_latest p ON b.contract_address = p.address WHERE CAST(b.amount AS decimal) > 1000 ORDER BY CAST(b.amount AS decimal) DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.text )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk varchar )\nCREATE TABLE sui_coins_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\nCREATE TABLE nft_metadata (\n blockchain varchar NOT NULL, -- blockchain fields for the functionType in contract\n contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n token_id varchar NOT NULL, -- The number of the token\n contract_name varchar NOT NULL, -- contract_name fields for the functionType in contract\n erc_type varchar NOT NULL, -- The type of token\n amount bigint NOT NULL, -- amount fields for the functionType in contract\n minter varchar NOT NULL, -- minter fields for the functionType in contract\n owner varchar NOT NULL, -- owner fields for the functionType in contract\n mint_block_number bigint NOT NULL, -- mint_block_number fields for the functionType in contract\n mint_time bigint NOT NULL, -- mint_time fields for the functionType in contract\n mint_transaction_hash varchar NOT NULL, -- mint_transaction_hash fields for the functionType in contract\n mint_price varchar NOT NULL, -- mint_price fields for the functionType in contract\n token_uri varchar NOT NULL, -- token_uri fields for the functionType in contract\n metadata varchar NOT NULL, -- metadata fields for the functionType in contract\n name varchar NOT NULL, -- name fields for the functionType in contract\n image_uri varchar NOT NULL, -- image_uri fields for the functionType in contract\n traits varchar NOT NULL, -- traits fields for the functionType in contract\n updated_at bigint NOT NULL, -- updated_at fields for the functionType in contract\n status varchar NOT NULL, -- status fields for the functionType in contract\n rarity_score real NOT NULL, -- rarity_score fields for the functionType in contract\n rarity_rank integer NOT NULL, -- rarity_rank fields for the functionType in contract\n unique_attribute_count integer NOT NULL, -- unique_attribute_count fields for the functionType in contract\n pk integer NOT NULL -- Partition key for the table(floor(mint_time / 1000 / 86400 / 30))\n)\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone (\n address varchar NOT NULL, -- address fields for the functionType in contract\n table_id varchar NOT NULL, -- table_id fields for the functionType in contract\n key_bytes varchar NOT NULL, -- key_bytes fields for the functionType in contract\n key0 varchar NOT NULL, -- key0 fields for the functionType in contract\n key1 varchar NOT NULL, -- key1 fields for the functionType in contract\n static_data varchar NOT NULL, -- static_data fields for the functionType in contract\n encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType in contract\n dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType in contract\n is_deleted boolean NOT NULL, -- is_deleted fields for the functionType in contract\n block_number bigint NOT NULL, -- Block number uniquely identifying the block\n log_index bigint NOT NULL -- Index of the log within the transaction\n)\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_balances_avalanche (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n amount decimal(38,0) NOT NULL -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"} {"conversations": [{"role": "user", "content": "Give a list of all policies where the deductible is less than 1000. Show policy_id, policy_number, start_date, and deductible."}, {"role": "assistant", "content": "SELECT policy_id, policy_number, start_date, deductible\nFROM insurance.policies\nWHERE deductible < 1000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers (\n customer_id character varying(64) NOT NULL, -- unique identifier for the customer\n first_name character varying(100) NOT NULL, -- customer's first name\n last_name character varying(100) NOT NULL, -- customer's last name\n date_of_birth date NOT NULL, -- customer's date of birth\n ssn_hash character varying(128), -- Hashed social security number (or national ID)\n address_line1 character varying(255) NOT NULL,\n address_line2 character varying(255),\n city character varying(100) NOT NULL,\n state character varying(50) NOT NULL,\n zip_code character varying(20) NOT NULL,\n country character varying(50) NOT NULL DEFAULT 'USA',\n phone_number character varying(30),\n email character varying(128) UNIQUE, -- unique email address\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the customer record was created\n updated_at timestamp, -- when the customer record was last updated\n status character varying(20) NOT NULL DEFAULT 'Active', -- e.g., Active, Inactive, Prospect\n PRIMARY KEY (customer_id)\n)\nCREATE TABLE insurance.policies ( policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, product_id character varying(64) NOT NULL, agent_id character varying(64), policy_number character varying(100) NOT NULL UNIQUE, start_date date NOT NULL, end_date date NOT NULL, premium_amount numeric(12, 2) NOT NULL, coverage_limit numeric(15, 2) NOT NULL, deductible numeric(10, 2) NOT NULL, status character varying(30) NOT NULL, issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, cancellation_date date, cancellation_reason text, PRIMARY KEY (policy_id) )\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\nCREATE TABLE insurance.insurance_products ( product_id.text, product_name.text, product_type.text, description.text, base_premium.numeric, coverage_details.text, underwriting_rules.text, is_active.boolean, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE insurance.premium_payments ( payment_id text, policy_id text, customer_id text, payment_date timestamp, amount_paid numeric, payment_method text, transaction_reference text, due_date date, payment_period_start date, payment_period_end date, status text )\nCREATE TABLE insurance.claim_documents ( document_id.text, claim_id.text, document_type.text, file_name.text, file_path.text, file_size_bytes.integer, mime_type.text, uploaded_by.text, uploaded_at.timestamp, description.text )\n"} {"conversations": [{"role": "user", "content": "List all medical records, showing the record ID, record date, and the full name of the doctor who created the record. Include the patient ID as well."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, mr.patient_id, d.first_name, d.last_name FROM healthcare.medical_records mr JOIN doctors d ON mr.doctor_id = d.doctor_id;"}, {"role": "user", "content": "Refine this to only include records where the chief_complaint is not null or empty and the doctor's specialty is 'Cardiology'."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, mr.patient_id, d.first_name, d.last_name FROM healthcare.medical_records mr JOIN doctors d ON mr.doctor_id = d.doctor_id WHERE (mr.chief_complaint IS NOT NULL AND mr.chief_complaint != '') AND d.specialty = 'Cardiology';"}, {"role": "user", "content": "Also, sort the results by record_date in descending order and limit the output to the top 10 records."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, mr.patient_id, d.first_name, d.last_name FROM healthcare.medical_records mr JOIN doctors d ON mr.doctor_id = d.doctor_id WHERE (mr.chief_complaint IS NOT NULL AND mr.chief_complaint != '') AND d.specialty = 'Cardiology' ORDER BY mr.record_date DESC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.medical_records (\n record_id character varying(64) NOT NULL, -- unique identifier for the medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n chief_complaint text, -- patient's primary reason for visit\n present_illness_history text, -- detailed history of the current issue\n past_medical_history text, -- relevant past conditions/surgeries\n physical_examination_notes text, -- findings from the physical exam\n assessment text, -- doctor's assessment/diagnosis summary\n treatment_plan text, -- planned course of action\n vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (record_id)\n)\n"} {"conversations": [{"role": "user", "content": "Provide a count of appointments grouped by the booking method."}, {"role": "assistant", "content": "SELECT booking_method, COUNT(*) AS appointment_count FROM government_services.appointments GROUP BY booking_method;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.documents (\n document_id character varying(64) NOT NULL, -- unique identifier for the document instance\n application_id character varying(64), -- FK to applications table (optional, could be linked to citizen directly)\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n document_type character varying(100) NOT NULL, -- e.g., Passport Scan, Proof of Address, Birth Certificate\n file_reference text NOT NULL, -- reference to the stored file (e.g., S3 URL, internal path)\n upload_timestamp timestamp NOT NULL,\n expiry_date date,\n verification_status character varying(30) DEFAULT 'Pending', -- e.g., Pending, Verified, Rejected\n verified_by_employee_id character varying(64), -- FK to employees table\n verification_timestamp timestamp,\n PRIMARY KEY (document_id)\n)\nCREATE TABLE government_services.employees (\n employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n job_title character varying(150) NOT NULL,\n department character varying(100),\n work_email character varying(128) NOT NULL UNIQUE,\n work_phone character varying(32),\n hire_date date NOT NULL,\n termination_date date, -- null if currently employed\n access_level character varying(50), -- Role or permission level\n manager_employee_id character varying(64), -- FK to self for reporting structure\n PRIMARY KEY (employee_id)\n)\nCREATE TABLE government_services.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n employee_id character varying(64), -- FK to employees table (optional, if assigned)\n location_id character varying(64), -- FK to service_locations table (if physical)\n service_id character varying(64), -- FK to services table (optional, if related to specific service)\n scheduled_start_time timestamp NOT NULL,\n scheduled_end_time timestamp,\n purpose text NOT NULL, -- reason for the appointment\n status character varying(30) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-Show\n booking_method character varying(50), -- e.g., Online, Phone, In-Person\n created_at timestamp NOT NULL, -- when the appointment was booked\n notes text,\n PRIMARY KEY (appointment_id)\n)\nCREATE TABLE government_services.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n application_id character varying(64), -- FK to applications table (optional)\n message_subject character varying(255),\n message_body text NOT NULL,\n channel character varying(30) NOT NULL, -- e.g., Email, SMS, Portal Message, Mail\n sent_at timestamp NOT NULL,\n status character varying(30) NOT NULL, -- e.g., Queued, Sent, Delivered, Failed, Read\n related_entity_type character varying(50), -- e.g., Application, Appointment, Document Request\n related_entity_id character varying(64), -- ID of the related entity\n PRIMARY KEY (notification_id)\n)\n"} {"conversations": [{"role": "user", "content": "Retrieve the number of drivers grouped by their status."}, {"role": "assistant", "content": "SELECT status,\n COUNT(*) AS driver_count\nFROM transportation.drivers\nGROUP BY status;"}, {"role": "user", "content": "Now, only show statuses where the driver_count is greater than 5 and order the results by driver_count descending."}, {"role": "assistant", "content": "SELECT status,\n COUNT(*) AS driver_count\nFROM transportation.drivers\nGROUP BY status\nHAVING COUNT(*) > 5\nORDER BY driver_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.drivers ( driver_id text, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\n"} {"conversations": [{"role": "user", "content": "For each ERC1155 NFT contract on Ethereum, show the `contract_address`, `token_id`, total amount held across all wallets, and number of unique holders."}, {"role": "assistant", "content": "SELECT nh.contract_address,\n nh.token_id,\n SUM(CAST(nh.amount AS bigint)) AS total_amount,\n COUNT(DISTINCT nh.wallet_address) AS holder_count\nFROM nft_holders nh\nJOIN nft_metadata nm\n ON nh.contract_address = nm.contract_address\n AND nh.token_id = nm.token_id\nWHERE nm.blockchain = 'Ethereum'\n AND nm.erc_type = 'ERC1155'\nGROUP BY nh.contract_address, nh.token_id;"}, {"role": "user", "content": "Only include NFTs where the `total_amount` is greater than 1000."}, {"role": "assistant", "content": "SELECT nh.contract_address,\n nh.token_id,\n SUM(CAST(nh.amount AS bigint)) AS total_amount,\n COUNT(DISTINCT nh.wallet_address) AS holder_count\nFROM nft_holders nh\nJOIN nft_metadata nm\n ON nh.contract_address = nm.contract_address\n AND nh.token_id = nm.token_id\nWHERE nm.blockchain = 'Ethereum'\n AND nm.erc_type = 'ERC1155'\nGROUP BY nh.contract_address, nh.token_id\nHAVING SUM(CAST(nh.amount AS bigint)) > 1000;"}, {"role": "user", "content": "Add the NFT `name` from `nft_metadata` in the result."}, {"role": "assistant", "content": "SELECT nh.contract_address,\n nh.token_id,\n nm.name,\n SUM(CAST(nh.amount AS bigint)) AS total_amount,\n COUNT(DISTINCT nh.wallet_address) AS holder_count\nFROM nft_holders nh\nJOIN nft_metadata nm\n ON nh.contract_address = nm.contract_address\n AND nh.token_id = nm.token_id\nWHERE nm.blockchain = 'Ethereum'\n AND nm.erc_type = 'ERC1155'\nGROUP BY nh.contract_address, nh.token_id, nm.name\nHAVING SUM(CAST(nh.amount AS bigint)) > 1000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp.timestamp, block_number.bigint, transaction_hash.text, transaction_index.bigint, from_address.text, contract_address.text, symbol.text, total_supply.text, name.text, decimals.bigint, is_erc20.integer, is_erc721.integer, is_erc1155.integer, is_proxy.integer, extra_info.text, pk.integer )\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n object_id varchar NOT NULL, -- object id of the coin metadata object\n coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n status varchar NOT NULL, -- coin status, eg. exists, deleted\n decimals bigint NOT NULL, -- decimals of the coin\n description varchar NOT NULL, -- description of the coin\n icon_url varchar NOT NULL, -- icon url of the coin\n symbol varchar NOT NULL, -- symbol of the coin\n name varchar NOT NULL -- name of the coin\n)\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.decimal, amount.decimal )\nCREATE TABLE token_info (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar NOT NULL, -- Token tick\n max_supply decimal(38,0) NOT NULL, -- Max supply\n lim decimal(38,0) NOT NULL, -- Limit of each mint\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE mud_holesky_redstone (\n address varchar NOT NULL, -- address fields for the functionType in contract\n table_id varchar NOT NULL, -- table_id fields for the functionType in contract\n key_bytes varchar NOT NULL, -- key_bytes fields for the functionType in contract\n key0 varchar NOT NULL, -- key0 fields for the functionType in contract\n key1 varchar NOT NULL, -- key1 fields for the functionType in contract\n static_data varchar NOT NULL, -- static_data fields for the functionType in contract\n encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType in contract\n dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType in contract\n is_deleted boolean NOT NULL, -- is_deleted fields for the functionType in contract\n block_number bigint NOT NULL, -- Block number uniquely identifying the block\n log_index bigint NOT NULL -- Index of the log within the transaction\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\n"} {"conversations": [{"role": "user", "content": "List all wallets that were created during the hour of the day which saw the highest number of wallet creations. Show the wallet ID, user ID, address, and creation timestamp."}, {"role": "assistant", "content": "WITH HourlyCounts AS (\n SELECT EXTRACT(HOUR FROM created_at) AS hour, COUNT(*) AS wallet_count\n FROM web3.wallets\n GROUP BY 1\n),\nMaxHour AS (\n SELECT hour\n FROM HourlyCounts\n ORDER BY wallet_count DESC\n LIMIT 1\n)\nSELECT wallet_id, user_id, address, created_at\nFROM web3.wallets\nWHERE EXTRACT(HOUR FROM created_at) = (SELECT hour FROM MaxHour);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.wallets ( wallet_id text PRIMARY KEY, user_id text, address text, private_key text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me all time entries from the last 90 days, including the entry description, hours spent, the name of the case, and the name of the client."}, {"role": "assistant", "content": "SELECT T1.description, T1.hours_spent, T2.case_name, T3.first_name, T3.last_name FROM legal_services.time_entries AS T1 JOIN cases AS T2 ON T1.case_id = T2.case_id JOIN clients AS T3 ON T2.client_id = T3.client_id WHERE T1.date_worked >= CURRENT_DATE - INTERVAL '90 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.time_entries (\n entry_id character varying(64) NOT NULL, -- unique identifier for the time entry\n case_id character varying(64) NOT NULL, -- FK to cases table\n lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (who performed the work)\n date_worked date NOT NULL, -- date the work was performed\n hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), -- duration of work in hours (e.g., 1.5 for 1h 30m)\n billing_rate numeric(10, 2) NOT NULL, -- hourly rate applied for this entry\n description text NOT NULL, -- detailed description of the work performed\n is_billable boolean DEFAULT true, -- whether this time entry is billable to the client\n is_billed boolean DEFAULT false, -- whether this entry has been included in an invoice\n invoice_id character varying(64), -- FK to invoices table (once billed)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the entry was recorded\n PRIMARY KEY (entry_id)\n)\n"} {"conversations": [{"role": "user", "content": "Can you show me the total number of passengers registered in the database?"}, {"role": "assistant", "content": "db.passengers.countDocuments({})"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// db.createCollection('passengers')\n// Optional: db.passengers.createIndex({ passenger_id: 1 }, { unique: true })\n// Optional: db.passengers.createIndex({ email: 1 }, { unique: true, sparse: true })\n// Optional: db.passengers.createIndex({ phone_number: 1 }, { unique: true, sparse: true })\n{\n _id: ObjectId(),\n passenger_id: \"pass_pqr\", // String (unique)\n first_name: \"Alice\", // String\n last_name: \"Smith\", // String\n email: \"alice.smith@example.com\", // String (unique, sparse)\n phone_number: \"+15551234567\", // String (unique, sparse)\n date_of_birth: ISODate(\"1990-03-20\"), // Date\n loyalty_program_id: \"LOYALTY123\", // String\n created_at: ISODate(\"2023-02-01T11:00:00Z\") // Date\n}\n"} {"conversations": [{"role": "user", "content": "Show for each developer and inventory item combination the number of times that item appears in player inventories."}, {"role": "assistant", "content": "SELECT d.developer_id, d.name AS developer_name, pi.item_id, COUNT(pi.inventory_id) AS inventory_count FROM gaming_technology.developers d JOIN gaming_technology.player_inventory pi ON d.developer_id = pi.item_id GROUP BY d.developer_id, d.name, pi.item_id;"}, {"role": "user", "content": "The query failed because developer_id and item_id are not the same. Can you count, for each developer, how many player inventory records exist for items created in that developer's country?"}, {"role": "assistant", "content": "SELECT d.name AS developer_name, COUNT(pi.inventory_id) AS inventory_count FROM gaming_technology.developers d JOIN gaming_technology.player_inventory pi ON d.country IS NOT NULL GROUP BY d.name;"}, {"role": "user", "content": "Can you instead show the number of player inventory records per developer, grouped by country?"}, {"role": "assistant", "content": "SELECT d.country, COUNT(pi.inventory_id) AS inventory_count FROM gaming_technology.developers d LEFT JOIN gaming_technology.player_inventory pi ON TRUE WHERE d.country IS NOT NULL GROUP BY d.country;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.developers (\n developer_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the developer studio\n name character varying(150) NOT NULL UNIQUE, -- name of the development studio\n country character varying(100), -- country where the studio is based\n founded_year integer, -- year the studio was founded\n website character varying(255), -- developer's official website\n created_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (developer_id)\n)\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, item_id uuid NOT NULL, quantity integer NOT NULL DEFAULT 1, acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, instance_data jsonb, PRIMARY KEY (inventory_id) )\n"} {"conversations": [{"role": "user", "content": "Count the number of posts that have a media URL but no textual content."}, {"role": "assistant", "content": "SELECT COUNT(*) FROM social_media.posts AS T1 WHERE T1.media_url IS NOT NULL AND (T1.content IS NULL OR T1.content = '');"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(50) NOT NULL UNIQUE, -- user's unique handle\n email character varying(128) NOT NULL UNIQUE, -- user's email address\n password_hash text NOT NULL, -- hashed password\n full_name character varying(100), -- user's full name\n profile_picture_url text, -- URL to the profile picture\n bio text, -- short user biography\n location character varying(100), -- user's location\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of account creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last profile update\n is_verified boolean NOT NULL DEFAULT false, -- verification status\n PRIMARY KEY (user_id)\n)\nCREATE TABLE social_media.posts (\n post_id character varying(64) NOT NULL, -- unique identifier for the post\n user_id character varying(64) NOT NULL, -- identifier of the user who created the post (FK to users.user_id)\n content text, -- textual content of the post\n media_url text, -- URL to attached media (image/video)\n media_type character varying(20), -- type of media ('image', 'video', null)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of post creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last post edit\n visibility character varying(20) NOT NULL DEFAULT 'public', -- visibility ('public', 'friends', 'private')\n location_lat numeric(9,6), -- latitude of post location\n location_lon numeric(9,6), -- longitude of post location\n PRIMARY KEY (post_id)\n)\nCREATE TABLE social_media.comments (\n comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n content text NOT NULL, -- textual content of the comment\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n PRIMARY KEY (comment_id)\n)\nCREATE TABLE social_media.likes (\n like_id character varying(64) NOT NULL, -- unique identifier for the like\n user_id character varying(64) NOT NULL, -- identifier of the user who liked (FK to users.user_id)\n post_id character varying(64), -- identifier of the post being liked (FK to posts.post_id, nullable)\n comment_id character varying(64), -- identifier of the comment being liked (FK to comments.comment_id, nullable)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the like occurred\n PRIMARY KEY (like_id),\n CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), -- prevent duplicate likes\n CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) -- ensure it likes something\n)\nCREATE TABLE social_media.follows (\n follow_id character varying(64) NOT NULL, -- unique identifier for the follow relationship\n follower_user_id character varying(64) NOT NULL, -- identifier of the user who is following (FK to users.user_id)\n following_user_id character varying(64) NOT NULL, -- identifier of the user being followed (FK to users.user_id)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the follow started\n PRIMARY KEY (follow_id),\n CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) -- prevent duplicate follows\n)\nCREATE TABLE social_media.hashtags (\n hashtag_id character varying(64) NOT NULL, -- unique identifier for the hashtag\n tag_name character varying(100) NOT NULL UNIQUE, -- the actual hashtag text (without '#')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when the hashtag was first used\n PRIMARY KEY (hashtag_id)\n)\nCREATE TABLE social_media.messages (\n message_id character varying(64) NOT NULL, -- unique identifier for the message\n conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n content text, -- textual content of the message\n media_url text, -- URL to attached media (image/video)\n media_type character varying(20), -- type of media ('image', 'video', null)\n sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n read_at timestamp, -- timestamp when message was read by recipient(s)\n PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversations (\n conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated\n last_message_at timestamp, -- timestamp of the last message in the conversation\n is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message\n group_name character varying(100), -- name of the group chat (if applicable)\n PRIMARY KEY (conversation_id)\n)\nCREATE TABLE social_media.conversation_participants (\n participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n PRIMARY KEY (participant_id),\n CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n read_at timestamp, -- timestamp notification was marked as read\n PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings (\n setting_id character varying(64) NOT NULL, -- unique identifier for the setting entry\n user_id character varying(64) NOT NULL UNIQUE, -- user the settings belong to (FK to users.user_id)\n theme character varying(20) DEFAULT 'light', -- UI theme ('light', 'dark')\n email_notifications_enabled boolean DEFAULT true, -- enable/disable email notifications\n push_notifications_enabled boolean DEFAULT true, -- enable/disable push notifications\n private_profile boolean DEFAULT false, -- is the user profile private\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last setting change\n PRIMARY KEY (setting_id)\n)\n"} {"conversations": [{"role": "user", "content": "For citizens who registered before January 1, 2023, show the total number of notifications sent to them for each channel. List the citizen's first name, last name, the channel, and the count of notifications."}, {"role": "assistant", "content": "SELECT\n T1.first_name,\n T1.last_name,\n T2.channel,\n COUNT(T2.notification_id) AS notification_count\nFROM government_services.citizens AS T1\nINNER JOIN government_services.notifications AS T2\n ON T1.citizen_id = T2.citizen_id\nWHERE\n T1.registration_date < '2023-01-01'\nGROUP BY\n T1.citizen_id,\n T1.first_name,\n T1.last_name,\n T2.channel;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n citizen_id character varying(64) NOT NULL, -- unique identifier for the citizen\n national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n date_of_birth date NOT NULL,\n gender character varying(20),\n primary_address text NOT NULL, -- full primary residential address\n contact_email character varying(128) UNIQUE,\n contact_phone character varying(32),\n registration_date timestamp NOT NULL, -- when the citizen profile was created\n is_verified boolean DEFAULT false, -- whether identity has been officially verified\n PRIMARY KEY (citizen_id)\n)\nCREATE TABLE government_services.agencies (\n agency_id character varying(64) NOT NULL, -- unique identifier for the agency\n agency_name character varying(255) NOT NULL, -- full name of the government agency\n jurisdiction_level character varying(50) NOT NULL, -- e.g., Federal, State, County, City\n primary_contact_email character varying(128),\n main_phone_number character varying(32),\n website_url character varying(255),\n established_date date,\n parent_agency_id character varying(64), -- FK to self for hierarchical structure\n PRIMARY KEY (agency_id)\n)\nCREATE TABLE government_services.services (\n service_id character varying(64) NOT NULL, -- unique identifier for the service\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n description text,\n category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n eligibility_criteria text, -- description of who is eligible\n standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n average_processing_time_days integer, -- estimated processing time\n is_active boolean DEFAULT true, -- whether the service is currently offered\n online_application_url character varying(255),\n PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.documents (\n document_id character varying(64) NOT NULL, -- unique identifier for the document instance\n application_id character varying(64), -- FK to applications table (optional, could be linked to citizen directly)\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n document_type character varying(100) NOT NULL, -- e.g., Passport Scan, Proof of Address, Birth Certificate\n file_reference text NOT NULL, -- reference to the stored file (e.g., S3 URL, internal path)\n upload_timestamp timestamp NOT NULL,\n expiry_date date,\n verification_status character varying(30) DEFAULT 'Pending', -- e.g., Pending, Verified, Rejected\n verified_by_employee_id character varying(64), -- FK to employees table\n verification_timestamp timestamp,\n PRIMARY KEY (document_id)\n)\nCREATE TABLE government_services.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n employee_id character varying(64), -- FK to employees table (optional, if assigned)\n location_id character varying(64), -- FK to service_locations table (if physical)\n service_id character varying(64), -- FK to services table (optional, if related to specific service)\n scheduled_start_time timestamp NOT NULL,\n scheduled_end_time timestamp,\n purpose text NOT NULL, -- reason for the appointment\n status character varying(30) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-Show\n booking_method character varying(50), -- e.g., Online, Phone, In-Person\n created_at timestamp NOT NULL, -- when the appointment was booked\n notes text,\n PRIMARY KEY (appointment_id)\n)\nCREATE TABLE government_services.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n application_id character varying(64), -- FK to applications table (optional)\n message_subject character varying(255),\n message_body text NOT NULL,\n channel character varying(30) NOT NULL, -- e.g., Email, SMS, Portal Message, Mail\n sent_at timestamp NOT NULL,\n status character varying(30) NOT NULL, -- e.g., Queued, Sent, Delivered, Failed, Read\n related_entity_type character varying(50), -- e.g., Application, Appointment, Document Request\n related_entity_id character varying(64), -- ID of the related entity\n PRIMARY KEY (notification_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me all insurance plans that cover more than 10 patients as their primary insurance, along with the provider name and contact information."}, {"role": "assistant", "content": "SELECT ip.plan_name, ip.insurance_provider, ip.contact_phone, ip.website, COUNT(pi.patient_id) AS patient_count FROM healthcare.insurance_plans ip JOIN healthcare.patient_insurance pi ON ip.plan_id = pi.plan_id WHERE pi.is_primary = true GROUP BY ip.plan_id HAVING COUNT(pi.patient_id) > 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients (\n patient_id character varying(64) NOT NULL, -- unique identifier for the patient\n first_name character varying(100) NOT NULL, -- patient's first name\n last_name character varying(100) NOT NULL, -- patient's last name\n date_of_birth date NOT NULL, -- patient's date of birth\n gender character varying(10), -- patient's gender (e.g., Male, Female, Other)\n address text, -- patient's home address\n phone_number character varying(20), -- patient's phone number\n email character varying(128) UNIQUE, -- patient's email address\n emergency_contact_name character varying(200), -- name of emergency contact\n emergency_contact_phone character varying(20), -- phone number of emergency contact\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n PRIMARY KEY (patient_id)\n)\nCREATE TABLE healthcare.doctors (\n doctor_id character varying(64) NOT NULL, -- unique identifier for the doctor\n first_name character varying(100) NOT NULL, -- doctor's first name\n last_name character varying(100) NOT NULL, -- doctor's last name\n specialty character varying(100) NOT NULL, -- doctor's medical specialty\n license_number character varying(50) UNIQUE NOT NULL, -- doctor's medical license number\n phone_number character varying(20), -- doctor's contact phone\n email character varying(128) UNIQUE, -- doctor's contact email\n hospital_affiliation_id character varying(64), -- FK to hospitals table (optional)\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (doctor_id)\n)\nCREATE TABLE healthcare.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table\n appointment_time timestamp with time zone NOT NULL, -- date and time of the appointment\n duration_minutes integer NOT NULL, -- expected duration in minutes\n reason text, -- reason for the visit\n status character varying(32) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-show\n location_id character varying(64), -- FK to a potential locations/clinics table\n notes text, -- notes related to scheduling\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (appointment_id)\n)\nCREATE TABLE healthcare.diagnoses (\n diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n description text, -- textual description of the diagnosis\n diagnosis_date date NOT NULL, -- date the diagnosis was made\n status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n is_chronic boolean DEFAULT false, -- flag for chronic conditions\n PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.medications (\n medication_id character varying(64) NOT NULL, -- unique identifier for the medication type\n medication_name character varying(255) NOT NULL, -- common or brand name\n generic_name character varying(255), -- generic chemical name\n manufacturer character varying(100), -- drug manufacturer\n ndc_code character varying(20) UNIQUE, -- National Drug Code (optional but useful)\n description text, -- description of the medication\n PRIMARY KEY (medication_id)\n)\nCREATE TABLE healthcare.prescriptions (\n prescription_id character varying(64) NOT NULL, -- unique identifier for the prescription\n record_id character varying(64) NOT NULL, -- FK linking to the medical record where it was prescribed\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to prescribing doctor\n medication_id character varying(64) NOT NULL, -- FK to medications table\n dosage character varying(100) NOT NULL, -- e.g., '100mg', '1 tablet'\n frequency character varying(100) NOT NULL, -- e.g., 'Once daily', 'Twice a day with meals'\n route character varying(50), -- e.g., 'Oral', 'Topical', 'Intravenous'\n start_date date NOT NULL, -- date prescription begins\n end_date date, -- date prescription ends (if applicable)\n quantity_dispensed numeric(10,2), -- amount dispensed (e.g., number of tablets)\n refills_allowed integer NOT NULL DEFAULT 0, -- number of allowed refills\n prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (prescription_id)\n)\nCREATE TABLE healthcare.insurance_plans (\n plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n plan_name character varying(200) NOT NULL, -- name of the insurance plan\n insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n plan_type character varying(50), -- e.g., PPO, HMO, EPO\n contact_phone character varying(20), -- provider contact number\n website character varying(255), -- provider website\n PRIMARY KEY (plan_id)\n)\nCREATE TABLE healthcare.patient_insurance (\n patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n patient_id character varying(64) NOT NULL, -- FK to patients table\n plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n policy_number character varying(100) NOT NULL, -- patient's policy number\n group_number character varying(100), -- group number, if applicable\n subscriber_name character varying(200), -- name of the primary policy holder\n effective_date date NOT NULL, -- date the coverage begins\n expiration_date date, -- date the coverage ends (if known)\n is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n PRIMARY KEY (patient_insurance_id),\n UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"} {"conversations": [{"role": "user", "content": "List each guest’s full name and the total number of service orders they have placed, ordered by order count descending."}, {"role": "assistant", "content": "SELECT g.guest_id,\n g.first_name || ' ' || g.last_name AS full_name,\n COUNT(so.order_id) AS order_count\nFROM hospitality_technology.guests g\nLEFT JOIN hospitality_technology.service_orders so\n ON g.guest_id = so.guest_id\nGROUP BY g.guest_id, full_name\nORDER BY order_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.guests ( guest_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.reservations ( reservation_id text, property_id text, guest_id text, room_id text, room_type_id text, check_in_date date, check_out_date date, actual_check_in_ts timestamp, actual_check_out_ts timestamp, num_adults integer, num_children integer, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "Find all contracts where the deployer address is the same as the contract address, indicating self-deployed contracts, and show their network IDs and deployment timestamps."}, {"role": "assistant", "content": "SELECT address, network_id, deployed_at FROM web3.contracts WHERE address = deployer_address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id character varying(64) NOT NULL, address character varying(128) NOT NULL, abi text NOT NULL, bytecode text NOT NULL, deployer_address character varying(128) NOT NULL, deployed_at timestamp NOT NULL, network_id character varying(64) NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (contract_id) )\n"} {"conversations": [{"role": "user", "content": "List all pairs of achievements in the same game where the difference in their points is greater than 50."}, {"role": "assistant", "content": "SELECT a1.game_id,\n a1.name AS achv1,\n a2.name AS achv2,\n ABS(a1.points - a2.points) AS point_diff\nFROM gaming_technology.achievements a1\nJOIN gaming_technology.achievements a2\n ON a1.game_id = a2.game_id\n WHERE ABS(a1.points - a2.points) > 50;"}, {"role": "user", "content": "Can you ensure each pair appears only once with achv1 having fewer points than achv2?"}, {"role": "assistant", "content": "SELECT a1.game_id,\n a1.name AS achv1,\n a2.name AS achv2,\n (a2.points - a1.points) AS point_diff\nFROM gaming_technology.achievements a1\nJOIN gaming_technology.achievements a2\n ON a1.game_id = a2.game_id\n AND a1.points < a2.points\nWHERE (a2.points - a1.points) > 50;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id uuid NOT NULL DEFAULT gen_random_uuid(), username character varying(100) NOT NULL UNIQUE, email character varying(255) NOT NULL UNIQUE, password_hash text NOT NULL, registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, last_login timestamp with time zone, country_code character(2), status character varying(20) NOT NULL DEFAULT 'active', profile_data jsonb, PRIMARY KEY (player_id) )\nCREATE TABLE gaming_technology.developers ( developer_id uuid NOT NULL DEFAULT gen_random_uuid(), name character varying(150) NOT NULL UNIQUE, country character varying(100), founded_year integer, website character varying(255), created_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (developer_id) )\nCREATE TABLE gaming_technology.servers ( server_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, server_name character varying(150), region character varying(50) NOT NULL, ip_address character varying(45), port integer, current_players integer NOT NULL DEFAULT 0, max_players integer NOT NULL, status character varying(30) NOT NULL DEFAULT 'offline', last_heartbeat timestamp with time zone, PRIMARY KEY (server_id) )\nCREATE TABLE gaming_technology.achievements ( achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, name character varying(150) NOT NULL, description text NOT NULL, icon_url character varying(255), points integer DEFAULT 0, hidden boolean DEFAULT false, PRIMARY KEY (achievement_id) )\n"} {"conversations": [{"role": "user", "content": "List all rooms, including their room number, the name of the property they belong to, and their room type name, specifically for rooms with 'Maintenance' status."}, {"role": "assistant", "content": "SELECT T1.room_number, T2.property_name, T3.type_name FROM rooms AS T1 JOIN properties AS T2 ON T1.property_id = T2.property_id JOIN room_types AS T3 ON T1.room_type_id = T3.room_type_id WHERE T1.status = 'Maintenance'"}, {"role": "user", "content": "Also include the floor number and filter to only show rooms located on floors 5 or higher. Sort the results by property name and then by floor."}, {"role": "assistant", "content": "SELECT T1.room_number, T2.property_name, T3.type_name, T1.floor FROM rooms AS T1 JOIN properties AS T2 ON T1.property_id = T2.property_id JOIN room_types AS T3 ON T1.room_type_id = T3.room_type_id WHERE T1.status = 'Maintenance' AND T1.floor >= 5 ORDER BY T2.property_name, T1.floor"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.rooms (\n room_id character varying(64) NOT NULL, -- unique identifier for the room\n property_id character varying(64) NOT NULL, -- FK to properties table\n room_number character varying(10) NOT NULL, -- room number identifier (e.g., '101', 'Suite 2B')\n room_type_id character varying(64) NOT NULL, -- FK to room_types table\n floor integer, -- floor number the room is on\n status character varying(50) NOT NULL, -- e.g., Available, Occupied, Cleaning, OutOfOrder, Maintenance\n is_smoking boolean NOT NULL DEFAULT false, -- smoking allowed flag\n features text, -- description of features (e.g., Balcony, Sea View, Jacuzzi)\n current_condition text, -- notes on room condition\n last_cleaned_at timestamp with time zone, -- timestamp of last cleaning\n PRIMARY KEY (room_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\n"} {"conversations": [{"role": "user", "content": "How many distinct users have sent messages in each conversation? Return conversation_id and user_count."}, {"role": "assistant", "content": "SELECT conversation_id,\n COUNT(DISTINCT sender_user_id) AS user_count\nFROM social_media.messages\nGROUP BY conversation_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.posts ( post_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, content text, media_url text, media_type character varying(20), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, visibility character varying(20) NOT NULL DEFAULT 'public', location_lat numeric(9,6), location_lon numeric(9,6), PRIMARY KEY (post_id) )\nCREATE TABLE social_media.likes ( like_id text PRIMARY KEY, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.messages (\n message_id character varying(64) NOT NULL, -- unique identifier for the message\n conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n content text, -- textual content of the message\n media_url text, -- URL to attached media (image/video)\n media_type character varying(20), -- type of media ('image', 'video', null)\n sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n read_at timestamp, -- timestamp when message was read by recipient(s)\n PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversation_participants ( participant_id.text, conversation_id.text, user_id.text, joined_at.timestamp, last_read_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "Find the most recent verified document for each application, showing application_id, document_id, and verification_timestamp."}, {"role": "assistant", "content": "SELECT d.document_id, d.application_id, d.verification_timestamp\nFROM government_services.documents d\nJOIN (\n SELECT application_id, MAX(verification_timestamp) AS latest_ts\n FROM government_services.documents\n WHERE verification_status = 'Verified'\n GROUP BY application_id\n) m ON d.application_id = m.application_id\n AND d.verification_timestamp = m.latest_ts;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\n"} {"conversations": [{"role": "user", "content": "Which users have received both a comment notification and a like notification? List the recipient_user_id and the total number of such users."}, {"role": "assistant", "content": "SELECT COUNT(DISTINCT recipient_user_id) AS user_count\nFROM (\n SELECT recipient_user_id\n FROM social_media.notifications\n WHERE notification_type = 'comment'\n INTERSECT\n SELECT recipient_user_id\n FROM social_media.notifications\n WHERE notification_type = 'like'\n) AS users_with_both;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.likes (\n like_id character varying(64) NOT NULL, -- unique identifier for the like\n user_id character varying(64) NOT NULL, -- identifier of the user who liked (FK to users.user_id)\n post_id character varying(64), -- identifier of the post being liked (FK to posts.post_id, nullable)\n comment_id character varying(64), -- identifier of the comment being liked (FK to comments.comment_id, nullable)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the like occurred\n PRIMARY KEY (like_id),\n CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), -- prevent duplicate likes\n CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) -- ensure it likes something\n)\nCREATE TABLE social_media.conversations (\n conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated\n last_message_at timestamp, -- timestamp of the last message in the conversation\n is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message\n group_name character varying(100), -- name of the group chat (if applicable)\n PRIMARY KEY (conversation_id)\n)\nCREATE TABLE social_media.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n read_at timestamp, -- timestamp notification was marked as read\n PRIMARY KEY (notification_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me the invoice number and total amount for each invoice, along with the number and name of the case it belongs to."}, {"role": "assistant", "content": "SELECT T1.invoice_number, T1.total_amount, T2.case_number, T2.case_name FROM invoices AS T1 JOIN cases AS T2 ON T1.case_id = T2.case_id;"}, {"role": "user", "content": "Refine this to only include invoices with a status of 'Overdue' or 'Unpaid'."}, {"role": "assistant", "content": "SELECT T1.invoice_number, T1.total_amount, T2.case_number, T2.case_name FROM invoices AS T1 JOIN cases AS T2 ON T1.case_id = T2.case_id WHERE T1.status = 'Overdue' OR T1.status = 'Unpaid';"}, {"role": "user", "content": "Also include the invoice due date and order the results by due date ascending."}, {"role": "assistant", "content": "SELECT T1.invoice_number, T1.total_amount, T1.due_date, T2.case_number, T2.case_name FROM invoices AS T1 JOIN cases AS T2 ON T1.case_id = T2.case_id WHERE T1.status = 'Overdue' OR T1.status = 'Unpaid' ORDER BY T1.due_date ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.law_firms ( firm_id text, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.cases ( case_id character varying(64) NOT NULL, case_number character varying(100) UNIQUE, case_name text NOT NULL, client_id character varying(64) NOT NULL, lead_lawyer_id character varying(64) NOT NULL, case_type character varying(100) NOT NULL, status character varying(50) NOT NULL, date_opened timestamp NOT NULL, date_closed timestamp, description text, court_jurisdiction character varying(128), PRIMARY KEY (case_id) )\nCREATE TABLE legal_services.invoices ( invoice_id text PRIMARY KEY, invoice_number text UNIQUE, client_id text, case_id text, issue_date date, due_date date, total_amount numeric, amount_paid numeric, status text, payment_date timestamp, notes text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Find all patients who have both a primary insurance plan and at least one completed appointment, along with their insurance policy numbers and the count of appointments."}, {"role": "assistant", "content": "SELECT p.first_name, p.last_name, pi.policy_number, COUNT(a.appointment_id) AS appointment_count FROM healthcare.patients p JOIN healthcare.patient_insurance pi ON p.patient_id = pi.patient_id JOIN healthcare.appointments a ON p.patient_id = a.patient_id WHERE pi.is_primary = true AND a.status = 'Completed' GROUP BY p.patient_id, p.first_name, p.last_name, pi.policy_number HAVING COUNT(a.appointment_id) >= 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.doctors ( doctor_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, specialty character varying(100) NOT NULL, license_number character varying(50) UNIQUE NOT NULL, phone_number character varying(20), email character varying(128) UNIQUE, hospital_affiliation_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (doctor_id) )\nCREATE TABLE healthcare.appointments ( appointment_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, appointment_time timestamp with time zone NOT NULL, duration_minutes integer NOT NULL, reason text, status character varying(32) NOT NULL, location_id character varying(64), notes text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (appointment_id) )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, diagnosis_code character varying(20) NOT NULL, code_type character varying(10) NOT NULL DEFAULT 'ICD-10', description text, diagnosis_date date NOT NULL, status character varying(32) NOT NULL, is_chronic boolean DEFAULT false, PRIMARY KEY (diagnosis_id) )\nCREATE TABLE healthcare.prescriptions ( prescription_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, medication_id character varying(64) NOT NULL, dosage character varying(100) NOT NULL, frequency character varying(100) NOT NULL, route character varying(50), start_date date NOT NULL, end_date date, quantity_dispensed numeric(10,2), refills_allowed integer NOT NULL DEFAULT 0, prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (prescription_id) )\nCREATE TABLE healthcare.insurance_plans ( plan_id character varying(64) NOT NULL, plan_name character varying(200) NOT NULL, insurance_provider character varying(100) NOT NULL, plan_type character varying(50), contact_phone character varying(20), website character varying(255), PRIMARY KEY (plan_id) )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n"} {"conversations": [{"role": "user", "content": "Provide a count of notifications, separated by whether they have been read or not."}, {"role": "assistant", "content": "SELECT CASE WHEN T1.read_at IS NULL THEN 'Unread' ELSE 'Read' END, count(T1.notification_id) FROM trading_platform.notifications AS T1 GROUP BY CASE WHEN T1.read_at IS NULL THEN 'Unread' ELSE 'Read' END"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "What is the maintenance schedule for platform 3 at station DEF for the next month?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to the maintenance schedule for platforms. The data I have only includes static information about platform details such as ID, station, number, track, status, length, and accessibility. For maintenance schedules, you may need to consult the station management or relevant department."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.platforms ( platform_id text, station_id text, platform_number text, track_number text, status text, length_meters numeric, accessible boolean )\n"} {"conversations": [{"role": "user", "content": "List each group conversation with its group name and the number of verified users who have posted in it."}, {"role": "assistant", "content": "SELECT c.conversation_id, c.group_name, COUNT(DISTINCT u.user_id) AS verified_posters\nFROM social_media.conversations c\nJOIN social_media.posts p ON p.location_lat IS NOT NULL -- Simulate posts linked to conversation (since no mapping, using location as a proxy)\nJOIN social_media.users u ON p.user_id = u.user_id AND u.is_verified = true\nWHERE c.is_group_chat = true\nGROUP BY c.conversation_id, c.group_name;"}, {"role": "user", "content": "Actually, only show groups created after May 1, 2024."}, {"role": "assistant", "content": "SELECT c.conversation_id, c.group_name, COUNT(DISTINCT u.user_id) AS verified_posters\nFROM social_media.conversations c\nJOIN social_media.posts p ON p.location_lat IS NOT NULL -- Simulate posts linked to conversation (since no mapping, using location as a proxy)\nJOIN social_media.users u ON p.user_id = u.user_id AND u.is_verified = true\nWHERE c.is_group_chat = true AND c.created_at > '2024-05-01'\nGROUP BY c.conversation_id, c.group_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.hashtags ( hashtag_id text PRIMARY KEY, tag_name text, created_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id.text, created_at.timestamp, last_message_at.timestamp, is_group_chat.boolean, group_name.text )\nCREATE TABLE social_media.user_settings ( setting_id text PRIMARY KEY, user_id text, theme text, email_notifications_enabled bool, push_notifications_enabled bool, private_profile bool, updated_at timestamp )\n"} {"conversations": [{"role": "user", "content": "How many documents were uploaded in the year 2023?"}, {"role": "assistant", "content": "SELECT count(*) FROM government_services.documents WHERE date_part('year', upload_timestamp) = 2023;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.documents ( document_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, document_type character varying(100) NOT NULL, file_reference text NOT NULL, upload_timestamp timestamp NOT NULL, expiry_date date, verification_status character varying(30) DEFAULT 'Pending', verified_by_employee_id character varying(64), verification_timestamp timestamp, PRIMARY KEY (document_id) )\n"} {"conversations": [{"role": "user", "content": "Show me all pairs of patients who share the same emergency contact phone, including both patient IDs, their names, and the shared emergency contact phone."}, {"role": "assistant", "content": "SELECT p1.patient_id,\n p1.first_name,\n p1.last_name,\n p2.patient_id AS other_patient_id,\n p2.first_name AS other_first_name,\n p2.last_name AS other_last_name,\n p1.emergency_contact_phone\nFROM healthcare.patients p1\nJOIN healthcare.patients p2\n ON p1.emergency_contact_phone = p2.emergency_contact_phone\n AND p1.patient_id < p2.patient_id;"}, {"role": "user", "content": "Only include those pairs where both emergency_contact_name values are not null."}, {"role": "assistant", "content": "SELECT p1.patient_id,\n p1.first_name,\n p1.last_name,\n p2.patient_id AS other_patient_id,\n p2.first_name AS other_first_name,\n p2.last_name AS other_last_name,\n p1.emergency_contact_phone\nFROM healthcare.patients p1\nJOIN healthcare.patients p2\n ON p1.emergency_contact_phone = p2.emergency_contact_phone\n AND p1.patient_id < p2.patient_id\nWHERE p1.emergency_contact_name IS NOT NULL\n AND p2.emergency_contact_name IS NOT NULL;"}, {"role": "user", "content": "Also exclude any pairs where the shared emergency contact phone matches the patient's own phone_number."}, {"role": "assistant", "content": "SELECT p1.patient_id,\n p1.first_name,\n p1.last_name,\n p2.patient_id AS other_patient_id,\n p2.first_name AS other_first_name,\n p2.last_name AS other_last_name,\n p1.emergency_contact_phone\nFROM healthcare.patients p1\nJOIN healthcare.patients p2\n ON p1.emergency_contact_phone = p2.emergency_contact_phone\n AND p1.patient_id < p2.patient_id\nWHERE p1.emergency_contact_name IS NOT NULL\n AND p2.emergency_contact_name IS NOT NULL\n AND p1.emergency_contact_phone <> p1.phone_number\n AND p2.emergency_contact_phone <> p2.phone_number;"}, {"role": "user", "content": "Finally, order the results by the shared emergency contact phone ascending and limit to the first 50 pairs."}, {"role": "assistant", "content": "SELECT p1.patient_id,\n p1.first_name,\n p1.last_name,\n p2.patient_id AS other_patient_id,\n p2.first_name AS other_first_name,\n p2.last_name AS other_last_name,\n p1.emergency_contact_phone\nFROM healthcare.patients p1\nJOIN healthcare.patients p2\n ON p1.emergency_contact_phone = p2.emergency_contact_phone\n AND p1.patient_id < p2.patient_id\nWHERE p1.emergency_contact_name IS NOT NULL\n AND p2.emergency_contact_name IS NOT NULL\n AND p1.emergency_contact_phone <> p1.phone_number\n AND p2.emergency_contact_phone <> p2.phone_number\nORDER BY p1.emergency_contact_phone ASC\nLIMIT 50;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\n"} {"conversations": [{"role": "user", "content": "List pairs of wallet IDs owned by the same user where the creation dates are more than one year apart. Show the user ID and the wallet IDs of both wallets."}, {"role": "assistant", "content": "SELECT w1.user_id, w1.wallet_id AS wallet_id_1, w2.wallet_id AS wallet_id_2 FROM web3.wallets w1 JOIN web3.wallets w2 ON w1.user_id = w2.user_id AND w2.created_at > w1.created_at + INTERVAL '1 year' ORDER BY w1.user_id, w1.created_at;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.wallets ( wallet_id text PRIMARY KEY, user_id text, address text, private_key text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me the earliest created smart contract for each creator address."}, {"role": "assistant", "content": "SELECT sc1.contract_id, sc1.creator_address, sc1.timestamp FROM blockchain.smart_contracts sc1 WHERE sc1.timestamp = (SELECT MIN(sc2.timestamp) FROM blockchain.smart_contracts sc2 WHERE sc2.creator_address = sc1.creator_address);"}, {"role": "user", "content": "Now include the total number of contracts each creator has made alongside this information."}, {"role": "assistant", "content": "SELECT sc1.contract_id, sc1.creator_address, sc1.timestamp, (SELECT COUNT(*) FROM blockchain.smart_contracts sc2 WHERE sc2.creator_address = sc1.creator_address) AS total_contracts FROM blockchain.smart_contracts sc1 WHERE sc1.timestamp = (SELECT MIN(sc3.timestamp) FROM blockchain.smart_contracts sc3 WHERE sc3.creator_address = sc1.creator_address);"}, {"role": "user", "content": "Filter this to only show creators who have made at least 10 contracts."}, {"role": "assistant", "content": "SELECT sc1.contract_id, sc1.creator_address, sc1.timestamp, (SELECT COUNT(*) FROM blockchain.smart_contracts sc2 WHERE sc2.creator_address = sc1.creator_address) AS total_contracts FROM blockchain.smart_contracts sc1 WHERE sc1.timestamp = (SELECT MIN(sc3.timestamp) FROM blockchain.smart_contracts sc3 WHERE sc3.creator_address = sc1.creator_address) AND (SELECT COUNT(*) FROM blockchain.smart_contracts sc4 WHERE sc4.creator_address = sc1.creator_address) >= 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.smart_contracts ( contract_id.text, creator_address.text, code.text, timestamp.timestamp )\n"} {"conversations": [{"role": "user", "content": "List the block ID, timestamp, and difficulty for all blocks created before '2024-01-01', ordered by timestamp in descending order."}, {"role": "assistant", "content": "SELECT block_id, timestamp, difficulty FROM blockchain.blocks WHERE timestamp < '2024-01-01' ORDER BY timestamp DESC;"}, {"role": "user", "content": "Now, filter those results to only show blocks with a difficulty between 8000 and 12000."}, {"role": "assistant", "content": "SELECT block_id, timestamp, difficulty FROM blockchain.blocks WHERE timestamp < '2024-01-01' AND difficulty BETWEEN 8000 AND 12000 ORDER BY timestamp DESC;"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE blockchain.blocks ( block_id.text, previous_block_id.text, timestamp.timestamp, nonce.integer, merkle_root.text, difficulty.integer )\nCREATE TABLE blockchain.wallets ( wallet_id.text, user_id.text, address_id.text, private_key.text )\nCREATE TABLE blockchain.smart_contracts ( contract_id.text, creator_address.text, code.text, timestamp.timestamp )\n"} {"conversations": [{"role": "user", "content": "List the full name of each lawyer along with the location and status of their appointments."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T2.location, T2.status FROM legal_services.lawyers AS T1 JOIN legal_services.appointments AS T2 ON T1.lawyer_id = T2.lawyer_id"}, {"role": "user", "content": "Please only show appointments with a status of 'completed' or 'cancelled', and sort by lawyer's last name."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T2.location, T2.status FROM legal_services.lawyers AS T1 JOIN legal_services.appointments AS T2 ON T1.lawyer_id = T2.lawyer_id WHERE T2.status IN ('completed', 'cancelled') ORDER BY T1.last_name"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers ( lawyer_id text PRIMARY KEY, first_name text, last_name text, bar_number text UNIQUE, firm_id text, email text UNIQUE, phone text, specialization text, hire_date timestamp, is_partner bool )\nCREATE TABLE legal_services.time_entries (\n entry_id character varying(64) NOT NULL, -- unique identifier for the time entry\n case_id character varying(64) NOT NULL, -- FK to cases table\n lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (who performed the work)\n date_worked date NOT NULL, -- date the work was performed\n hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), -- duration of work in hours (e.g., 1.5 for 1h 30m)\n billing_rate numeric(10, 2) NOT NULL, -- hourly rate applied for this entry\n description text NOT NULL, -- detailed description of the work performed\n is_billable boolean DEFAULT true, -- whether this time entry is billable to the client\n is_billed boolean DEFAULT false, -- whether this entry has been included in an invoice\n invoice_id character varying(64), -- FK to invoices table (once billed)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the entry was recorded\n PRIMARY KEY (entry_id)\n)\nCREATE TABLE legal_services.appointments ( appointment_id text PRIMARY KEY, client_id text, lawyer_id text, case_id text, start_time timestamp, end_time timestamp, location text, subject text, notes text, status text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "List all node pairs that operate on the same port and were last_seen within 30 minutes of each other, showing both node_ids, the port, and the time difference in minutes."}, {"role": "assistant", "content": "SELECT n1.node_id AS node1_id, n2.node_id AS node2_id, n1.port,\n ABS(EXTRACT(EPOCH FROM (n1.last_seen - n2.last_seen))) / 60 AS minutes_diff\nFROM blockchain.nodes n1\nJOIN blockchain.nodes n2\n ON n1.port = n2.port\n AND n1.node_id < n2.node_id\nWHERE ABS(EXTRACT(EPOCH FROM (n1.last_seen - n2.last_seen))) <= 1800;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.nodes ( node_id text PRIMARY KEY, ip_address text, port int, last_seen timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me document_id, application_id, and verification_status for all documents submitted by citizen 'cit123'."}, {"role": "assistant", "content": "SELECT document_id,\n application_id,\n verification_status\nFROM documents\nWHERE citizen_id = 'cit123';"}, {"role": "user", "content": "I got an error: relation 'documents' does not exist."}, {"role": "assistant", "content": "SELECT document_id,\n application_id,\n verification_status\nFROM government_services.documents\nWHERE citizen_id = 'cit123';"}, {"role": "user", "content": "Now, only include documents where verification_status = 'Pending'."}, {"role": "assistant", "content": "SELECT document_id,\n application_id,\n verification_status\nFROM government_services.documents\nWHERE citizen_id = 'cit123'\n AND verification_status = 'Pending';"}, {"role": "user", "content": "Also, limit the results to files uploaded in 2024."}, {"role": "assistant", "content": "SELECT document_id,\n application_id,\n verification_status\nFROM government_services.documents\nWHERE citizen_id = 'cit123'\n AND verification_status = 'Pending'\n AND upload_timestamp >= '2024-01-01'\n AND upload_timestamp < '2025-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.applications ( application_id text, citizen_id text, service_id text, submitted_at timestamp, status text, last_updated_at timestamp, assigned_employee_id text, decision_date date, notes text, reference_number text )\nCREATE TABLE government_services.documents ( document_id text, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.employees ( employee_id text, agency_id text, first_name text, last_name text, job_title text, department text, work_email text, work_phone text, hire_date date, termination_date date, access_level text, manager_employee_id text )\nCREATE TABLE government_services.service_locations ( location_id text, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.appointments ( appointment_id text, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\n"} {"conversations": [{"role": "user", "content": "For each event recorded, list its ID, name, and the status and value of the transaction in which it occurred."}, {"role": "assistant", "content": "SELECT E.event_id, E.event_name, E.transaction_id, T.status, T.value FROM web3.events AS E JOIN web3.transactions AS T ON E.transaction_id = T.transaction_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.events (\n event_id character varying(64) NOT NULL, -- unique identifier for the event\n contract_id character varying(64) NOT NULL, -- identifier of the contract emitting the event\n event_name character varying(128) NOT NULL, -- name of the event\n data text NOT NULL, -- data payload of the event\n emitted_at timestamp NOT NULL, -- time when the event was emitted\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction that triggered the event\n log_index integer NOT NULL, -- index of the event log in the transaction\n PRIMARY KEY (event_id)\n)\nCREATE TABLE web3.transactions ( transaction_id character varying(64) NOT NULL, from_address character varying(128) NOT NULL, to_address character varying(128), value numeric(38,14) NOT NULL, gas_used integer NOT NULL, gas_price numeric(38,14) NOT NULL, block_number integer NOT NULL, timestamp timestamp NOT NULL, input_data text, status character varying(32) NOT NULL, nonce integer NOT NULL, PRIMARY KEY (transaction_id) )\nCREATE TABLE web3.tokens ( token_id text PRIMARY KEY, contract_address text, token_name text, token_symbol text, decimals int, total_supply numeric )\nCREATE TABLE web3.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\nCREATE TABLE web3.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "List all agencies that do not have a website URL specified. Return their agency_id, agency_name, and main_phone_number."}, {"role": "assistant", "content": "SELECT agency_id, agency_name, main_phone_number FROM government_services.agencies WHERE website_url IS NULL OR website_url = '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\n"} {"conversations": [{"role": "user", "content": "List all medical record entries where the treatment_plan mentions a medication name. Return patient_id, record_id, and the matching medication_name."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n mr.record_id,\n m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n ON mr.treatment_plan ILIKE '%' || m.medication_name || '%';"}, {"role": "user", "content": "Actually, only include medications manufactured by 'Pfizer'."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n mr.record_id,\n m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n ON mr.treatment_plan ILIKE '%' || m.medication_name || '%'\nWHERE m.manufacturer = 'Pfizer';"}, {"role": "user", "content": "Also sort the results by record_date descending."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n mr.record_id,\n m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n ON mr.treatment_plan ILIKE '%' || m.medication_name || '%'\nWHERE m.manufacturer = 'Pfizer'\nORDER BY mr.record_date DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients (\n patient_id character varying(64) NOT NULL, -- unique identifier for the patient\n first_name character varying(100) NOT NULL, -- patient's first name\n last_name character varying(100) NOT NULL, -- patient's last name\n date_of_birth date NOT NULL, -- patient's date of birth\n gender character varying(10), -- patient's gender (e.g., Male, Female, Other)\n address text, -- patient's home address\n phone_number character varying(20), -- patient's phone number\n email character varying(128) UNIQUE, -- patient's email address\n emergency_contact_name character varying(200), -- name of emergency contact\n emergency_contact_phone character varying(20), -- phone number of emergency contact\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n PRIMARY KEY (patient_id)\n)\nCREATE TABLE healthcare.doctors (\n doctor_id character varying(64) NOT NULL, -- unique identifier for the doctor\n first_name character varying(100) NOT NULL, -- doctor's first name\n last_name character varying(100) NOT NULL, -- doctor's last name\n specialty character varying(100) NOT NULL, -- doctor's medical specialty\n license_number character varying(50) UNIQUE NOT NULL, -- doctor's medical license number\n phone_number character varying(20), -- doctor's contact phone\n email character varying(128) UNIQUE, -- doctor's contact email\n hospital_affiliation_id character varying(64), -- FK to hospitals table (optional)\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (doctor_id)\n)\nCREATE TABLE healthcare.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table\n appointment_time timestamp with time zone NOT NULL, -- date and time of the appointment\n duration_minutes integer NOT NULL, -- expected duration in minutes\n reason text, -- reason for the visit\n status character varying(32) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-show\n location_id character varying(64), -- FK to a potential locations/clinics table\n notes text, -- notes related to scheduling\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (appointment_id)\n)\nCREATE TABLE healthcare.medical_records (\n record_id character varying(64) NOT NULL, -- unique identifier for the medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n chief_complaint text, -- patient's primary reason for visit\n present_illness_history text, -- detailed history of the current issue\n past_medical_history text, -- relevant past conditions/surgeries\n physical_examination_notes text, -- findings from the physical exam\n assessment text, -- doctor's assessment/diagnosis summary\n treatment_plan text, -- planned course of action\n vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (record_id)\n)\nCREATE TABLE healthcare.medications (\n medication_id character varying(64) NOT NULL, -- unique identifier for the medication type\n medication_name character varying(255) NOT NULL, -- common or brand name\n generic_name character varying(255), -- generic chemical name\n manufacturer character varying(100), -- drug manufacturer\n ndc_code character varying(20) UNIQUE, -- National Drug Code (optional but useful)\n description text, -- description of the medication\n PRIMARY KEY (medication_id)\n)\nCREATE TABLE healthcare.insurance_plans (\n plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n plan_name character varying(200) NOT NULL, -- name of the insurance plan\n insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n plan_type character varying(50), -- e.g., PPO, HMO, EPO\n contact_phone character varying(20), -- provider contact number\n website character varying(255), -- provider website\n PRIMARY KEY (plan_id)\n)\nCREATE TABLE healthcare.patient_insurance (\n patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n patient_id character varying(64) NOT NULL, -- FK to patients table\n plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n policy_number character varying(100) NOT NULL, -- patient's policy number\n group_number character varying(100), -- group number, if applicable\n subscriber_name character varying(200), -- name of the primary policy holder\n effective_date date NOT NULL, -- date the coverage begins\n expiration_date date, -- date the coverage ends (if known)\n is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n PRIMARY KEY (patient_insurance_id),\n UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"} {"conversations": [{"role": "user", "content": "For each guest, list reservation_id, guest_id, check_in_date, and the next reservation_id and its check_in_date."}, {"role": "assistant", "content": "SELECT r1.reservation_id,\n r1.guest_id,\n r1.check_in_date,\n r2.reservation_id AS next_reservation_id,\n r2.check_in_date AS next_check_in_date\nFROM reservations r1\nLEFT JOIN reservations r2\n ON r1.guest_id = r2.guest_id\n AND r2.check_in_date = (\n SELECT MIN(check_in_date)\n FROM reservations\n WHERE guest_id = r1.guest_id\n AND check_in_date > r1.check_in_date\n );"}, {"role": "user", "content": "Only include guests who have at least two reservations."}, {"role": "assistant", "content": "SELECT r1.reservation_id,\n r1.guest_id,\n r1.check_in_date,\n r2.reservation_id AS next_reservation_id,\n r2.check_in_date AS next_check_in_date\nFROM reservations r1\nLEFT JOIN reservations r2\n ON r1.guest_id = r2.guest_id\n AND r2.check_in_date = (\n SELECT MIN(check_in_date)\n FROM reservations\n WHERE guest_id = r1.guest_id\n AND check_in_date > r1.check_in_date\n )\nWHERE r1.guest_id IN (\n SELECT guest_id\n FROM reservations\n GROUP BY guest_id\n HAVING COUNT(*) >= 2\n);"}, {"role": "user", "content": "Also, only show next reservations that occur within 30 days of the current reservation."}, {"role": "assistant", "content": "SELECT r1.reservation_id,\n r1.guest_id,\n r1.check_in_date,\n r2.reservation_id AS next_reservation_id,\n r2.check_in_date AS next_check_in_date\nFROM reservations r1\nLEFT JOIN reservations r2\n ON r1.guest_id = r2.guest_id\n AND r2.check_in_date = (\n SELECT MIN(check_in_date)\n FROM reservations\n WHERE guest_id = r1.guest_id\n AND check_in_date > r1.check_in_date\n )\n AND r2.check_in_date <= r1.check_in_date + INTERVAL '30 days'\nWHERE r1.guest_id IN (\n SELECT guest_id\n FROM reservations\n GROUP BY guest_id\n HAVING COUNT(*) >= 2\n);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.reservations ( reservation_id text, property_id text, guest_id text, room_id text, room_type_id text, check_in_date date, check_out_date date, actual_check_in_ts timestamp, actual_check_out_ts timestamp, num_adults integer, num_children integer, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Find the top 5 employees who have verified the most documents. Display the employee full name and the count of verified documents, ordered by count descending."}, {"role": "assistant", "content": "SELECT e.first_name || ' ' || e.last_name AS full_name,\n COUNT(*) AS verified_count\nFROM government_services.documents d\nJOIN government_services.employees e\n ON d.verified_by_employee_id = e.employee_id\nWHERE d.verification_status = 'Verified'\nGROUP BY e.first_name, e.last_name\nORDER BY verified_count DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n citizen_id character varying(64) NOT NULL, -- unique identifier for the citizen\n national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n date_of_birth date NOT NULL,\n gender character varying(20),\n primary_address text NOT NULL, -- full primary residential address\n contact_email character varying(128) UNIQUE,\n contact_phone character varying(32),\n registration_date timestamp NOT NULL, -- when the citizen profile was created\n is_verified boolean DEFAULT false, -- whether identity has been officially verified\n PRIMARY KEY (citizen_id)\n)\nCREATE TABLE government_services.agencies ( agency_id text, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.applications ( application_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, submitted_at timestamp NOT NULL, status character varying(50) NOT NULL, last_updated_at timestamp NOT NULL, assigned_employee_id character varying(64), decision_date date, notes text, reference_number character varying(100) UNIQUE, PRIMARY KEY (application_id) )\nCREATE TABLE government_services.documents ( document_id text, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.payments ( payment_id text, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_id) )\nCREATE TABLE government_services.service_locations (\n location_id character varying(64) NOT NULL, -- unique identifier for the physical location\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n location_name character varying(200), -- e.g., Downtown DMV Office\n address text NOT NULL,\n city character varying(100),\n state character varying(50),\n postal_code character varying(20),\n latitude numeric(9, 6),\n longitude numeric(9, 6),\n operating_hours text, -- description of opening times\n contact_phone character varying(32),\n is_accessible boolean, -- accessibility information (e.g., wheelchair access)\n PRIMARY KEY (location_id)\n)\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "How many group chats have been created since January 1, 2024?"}, {"role": "assistant", "content": "SELECT COUNT(*) AS group_chat_count\nFROM social_media.conversations\nWHERE is_group_chat = TRUE\n AND created_at >= '2024-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.likes ( like_id text, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id text, tag_name text, created_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id text, created_at timestamp, last_message_at timestamp, is_group_chat boolean, group_name text )\n"} {"conversations": [{"role": "user", "content": "Find transactions that triggered events and whose to_address matches the contract_id of the emitted event. List the transaction ID, the to_address, and the count of such events for that transaction."}, {"role": "assistant", "content": "SELECT t.transaction_id, t.to_address, COUNT(e.event_id) AS matching_event_count FROM web3.transactions t JOIN web3.events e ON t.transaction_id = e.transaction_id WHERE t.to_address IS NOT NULL AND t.to_address = e.contract_id GROUP BY t.transaction_id, t.to_address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.events (\n event_id character varying(64) NOT NULL, -- unique identifier for the event\n contract_id character varying(64) NOT NULL, -- identifier of the contract emitting the event\n event_name character varying(128) NOT NULL, -- name of the event\n data text NOT NULL, -- data payload of the event\n emitted_at timestamp NOT NULL, -- time when the event was emitted\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction that triggered the event\n log_index integer NOT NULL, -- index of the event log in the transaction\n PRIMARY KEY (event_id)\n)\nCREATE TABLE web3.transactions ( transaction_id character varying(64) NOT NULL, from_address character varying(128) NOT NULL, to_address character varying(128), value numeric(38,14) NOT NULL, gas_used integer NOT NULL, gas_price numeric(38,14) NOT NULL, block_number integer NOT NULL, timestamp timestamp NOT NULL, input_data text, status character varying(32) NOT NULL, nonce integer NOT NULL, PRIMARY KEY (transaction_id) )\nCREATE TABLE web3.token_transfers ( transfer_id text, token_id text, from_address text, to_address text, value numeric, transaction_id text, log_index integer )\n"} {"conversations": [{"role": "user", "content": "Show the number of employees in each department."}, {"role": "assistant", "content": "SELECT department, COUNT(*) AS employee_count\nFROM financial_services.employees\ngroup BY department;"}, {"role": "user", "content": "Exclude departments that have less than 3 employees."}, {"role": "assistant", "content": "SELECT department, COUNT(*) AS employee_count\nFROM financial_services.employees\ngroup BY department\nHAVING COUNT(*) >= 3;"}, {"role": "user", "content": "Can you also show the average hire_date for employees in each department?"}, {"role": "assistant", "content": "SELECT department, COUNT(*) AS employee_count, AVG(hire_date) AS average_hire_date\nFROM financial_services.employees\ngroup BY department\nHAVING COUNT(*) >= 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.accounts ( account_id text PRIMARY KEY, customer_id text, account_number text, account_type text, balance numeric, currency text, opened_date date, status text, interest_rate numeric, last_updated_at timestamp )\nCREATE TABLE financial_services.transactions ( transaction_id text PRIMARY KEY, account_id text, related_account_id text, transaction_type text, amount numeric, currency text, transaction_date timestamp, effective_date date, description text, status text, reference_number text )\nCREATE TABLE financial_services.trades ( trade_id text PRIMARY KEY, account_id text, security_id text, order_id text, trade_type text, quantity numeric, price_per_unit numeric, total_amount numeric, commission numeric, trade_timestamp timestamp, settlement_date date, status text, execution_venue text )\nCREATE TABLE financial_services.market_data ( data_point_id bigserial PRIMARY KEY, security_id text, data_timestamp timestamp, open_price numeric, high_price numeric, low_price numeric, close_price numeric, adjusted_close_price numeric, volume bigint, source text )\nCREATE TABLE financial_services.employees ( employee_id text PRIMARY KEY, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\n"} {"conversations": [{"role": "user", "content": "I need the total traded value (quantity * price) for each buyer and asset symbol for trades after '2024-06-01'. List buyer_id, asset symbol, and total_value."}, {"role": "assistant", "content": "SELECT t.buyer_id, m.value AS asset_symbol, SUM(t.quantity * t.price) AS total_value\nFROM trading_platform.trades t\nJOIN trading_platform.metadata m ON t.asset_id = m.asset_id AND m.key = 'symbol'\nWHERE t.traded_at > '2024-06-01'\nGROUP BY t.buyer_id, m.value;"}, {"role": "user", "content": "Only include results where total_value > 10000, and order by total_value descending."}, {"role": "assistant", "content": "SELECT t.buyer_id, m.value AS asset_symbol, SUM(t.quantity * t.price) AS total_value\nFROM trading_platform.trades t\nJOIN trading_platform.metadata m ON t.asset_id = m.asset_id AND m.key = 'symbol'\nWHERE t.traded_at > '2024-06-01'\nGROUP BY t.buyer_id, m.value\nHAVING SUM(t.quantity * t.price) > 10000\nORDER BY total_value DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.orders ( order_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, wallet_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, order_type character varying(32) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, status character varying(32) NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (order_id) )\nCREATE TABLE trading_platform.trades ( trade_id character varying(64) NOT NULL, order_id character varying(64) NOT NULL, buyer_id character varying(64) NOT NULL, seller_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, traded_at timestamp NOT NULL, PRIMARY KEY (trade_id) )\nCREATE TABLE trading_platform.peers ( peer_id character varying(64) NOT NULL, ip_address character varying(15) NOT NULL, port integer NOT NULL, last_seen timestamp NOT NULL, PRIMARY KEY (peer_id) )\nCREATE TABLE trading_platform.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, status character varying(32) NOT NULL, reviewed_at timestamp NOT NULL, PRIMARY KEY (kyc_audit_id) )\nCREATE TABLE trading_platform.logs ( log_id character varying(64) NOT NULL, user_id character varying(64), action character varying(128) NOT NULL, details text NOT NULL, logged_at timestamp NOT NULL, PRIMARY KEY (log_id) )\nCREATE TABLE trading_platform.notifications ( notification_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, message text NOT NULL, sent_at timestamp NOT NULL, read_at timestamp, PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "List all pairs of tokens (show token_id for both) that share the same contract address, excluding pairs where the token_id is the same."}, {"role": "assistant", "content": "SELECT t1.token_id AS token_id1, t2.token_id AS token_id2, t1.contract_address FROM web3.tokens AS t1 JOIN web3.tokens AS t2 ON t1.contract_address = t2.contract_address WHERE t1.token_id < t2.token_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.tokens ( token_id character varying(64) NOT NULL, contract_address character varying(128) NOT NULL, token_name character varying(128) NOT NULL, token_symbol character varying(32) NOT NULL, decimals integer NOT NULL, total_supply numeric(38,14) NOT NULL, PRIMARY KEY (token_id) )\n"} {"conversations": [{"role": "user", "content": "Show me all completed trips with their driver's full name and the route description, ordered by actual arrival time in descending order."}, {"role": "assistant", "content": "SELECT t.trip_id, CONCAT(d.first_name, ' ', d.last_name) AS driver_name, r.description AS route_description, t.actual_arrival FROM transportation.trips t JOIN transportation.drivers d ON t.driver_id = d.driver_id LEFT JOIN transportation.routes r ON t.route_id = r.route_id WHERE t.status = 'Completed' ORDER BY t.actual_arrival DESC;"}, {"role": "user", "content": "Now include the vehicle_id and filter to only show trips that had more than 10 passengers."}, {"role": "assistant", "content": "SELECT t.trip_id, t.vehicle_id, CONCAT(d.first_name, ' ', d.last_name) AS driver_name, r.description AS route_description, t.actual_arrival FROM transportation.trips t JOIN transportation.drivers d ON t.driver_id = d.driver_id LEFT JOIN transportation.routes r ON t.route_id = r.route_id WHERE t.status = 'Completed' AND t.passenger_count > 10 ORDER BY t.actual_arrival DESC;"}, {"role": "user", "content": "Instead of route description, show me the distance_km and estimated_duration_minutes for each route."}, {"role": "assistant", "content": "SELECT t.trip_id, t.vehicle_id, CONCAT(d.first_name, ' ', d.last_name) AS driver_name, r.distance_km, r.estimated_duration_minutes, t.actual_arrival FROM transportation.trips t JOIN transportation.drivers d ON t.driver_id = d.driver_id LEFT JOIN transportation.routes r ON t.route_id = r.route_id WHERE t.status = 'Completed' AND t.passenger_count > 10 ORDER BY t.actual_arrival DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.drivers ( driver_id text PRIMARY KEY, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.trips (\n trip_id character varying(64) NOT NULL, -- unique identifier for a specific trip instance\n route_id character varying(64), -- identifier of the route being followed (can be null for ad-hoc trips)\n vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle used\n driver_id character varying(64) NOT NULL, -- identifier of the driver operating\n scheduled_departure timestamp with time zone NOT NULL, -- planned departure time\n actual_departure timestamp with time zone, -- actual departure time\n scheduled_arrival timestamp with time zone NOT NULL, -- planned arrival time\n actual_arrival timestamp with time zone, -- actual arrival time\n origin_location_id character varying(64) NOT NULL, -- actual starting location (could differ from route origin)\n destination_location_id character varying(64) NOT NULL, -- actual ending location (could differ from route destination)\n status character varying(32) NOT NULL, -- e.g., Scheduled, In Progress, Completed, Delayed, Cancelled\n passenger_count integer, -- number of passengers (if applicable)\n cargo_manifest_id character varying(64), -- link to cargo details (if applicable)\n PRIMARY KEY (trip_id)\n)\nCREATE TABLE transportation.maintenance_logs (\n log_id character varying(64) NOT NULL, -- unique identifier for the maintenance record\n vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle serviced\n service_date date NOT NULL, -- date the service was performed\n odometer_reading integer, -- vehicle mileage at time of service\n service_type character varying(128) NOT NULL, -- type of service (e.g., Oil Change, Tire Rotation, Engine Repair)\n description text NOT NULL, -- detailed description of work done\n cost numeric(10, 2), -- cost of the service\n mechanic_name character varying(128), -- name or ID of the mechanic/shop\n next_service_due_date date, -- recommended date for next service\n PRIMARY KEY (log_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all pairs of clients who registered on the same day, showing each client's first_name, last_name, and the registration date."}, {"role": "assistant", "content": "SELECT c1.first_name AS first_name_1, c1.last_name AS last_name_1, c2.first_name AS first_name_2, c2.last_name AS last_name_2, DATE(c1.date_registered) AS registration_date FROM legal_services.clients c1 JOIN legal_services.clients c2 ON DATE(c1.date_registered) = DATE(c2.date_registered) AND c1.client_id < c2.client_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text, first_name text, last_name text, company_name text, email text, phone text, address text, date_registered timestamp, status text )\n"} {"conversations": [{"role": "user", "content": "Show a list of all DApps together with the total number of unique assets linked to each via the metadata table."}, {"role": "assistant", "content": "SELECT d.dapp_id, d.name, d.url, COUNT(DISTINCT m.asset_id) AS unique_asset_count\nFROM trading_platform.dapps d\nLEFT JOIN trading_platform.metadata m ON m.asset_id IS NOT NULL\nGROUP BY d.dapp_id, d.name, d.url;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.orders ( order_id text PRIMARY KEY, user_id text, wallet_id text, asset_id text, order_type text, quantity numeric, price numeric, status text, created_at timestamp )\nCREATE TABLE trading_platform.trades ( trade_id text PRIMARY KEY, order_id text, buyer_id text, seller_id text, asset_id text, quantity numeric, price numeric, traded_at timestamp )\nCREATE TABLE trading_platform.utxos ( utxo_id text PRIMARY KEY, transaction_id text, output_index int, address text, amount numeric, spent boolean )\nCREATE TABLE trading_platform.dapps ( dapp_id text PRIMARY KEY, name text, description text, url text )\nCREATE TABLE trading_platform.peers ( peer_id text PRIMARY KEY, ip_address text, port int, last_seen timestamp )\nCREATE TABLE trading_platform.metadata ( metadata_id text PRIMARY KEY, asset_id text, key text, value text )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id text PRIMARY KEY, user_id text, status text, reviewed_at timestamp )\nCREATE TABLE trading_platform.logs ( log_id text PRIMARY KEY, user_id text, action text, details text, logged_at timestamp )\n"} {"conversations": [{"role": "user", "content": "List tokens with trend rank 5 or better and a price below $1. Show symbol, price, and trend rank."}, {"role": "assistant", "content": "SELECT token_symbol, price, trend_rank FROM token_dexpool_info WHERE trend_rank IS NOT NULL AND trend_rank <= 5 AND price < 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, -- the id of dexpool token_name character varying(100) NOT NULL, -- the name of the token in the dexpool token_symbol character varying(100) NOT NULL, -- the token's symbol chain text, -- the chain that the dexpool resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_6h double precision, -- change in value divided by the absolute price value of the original token price in 6 hours price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours makers_24h double precision, -- the makers of the dex pool in 24 hours volume_24h double precision, -- the trade volume of the dex pool in 24 hours liquidity double precision, -- the liquidity of the dex pool market_cap double precision, -- the market cap of the token trend_rank bigint, -- the rank of token in the dex pool of recent trending, value 1 expresses the most popular token. ,PRIMARY KEY (pair_address, chain) )\n"} {"conversations": [{"role": "user", "content": "Show each service's name along with the total number of appointments scheduled and the number of unique locations these appointments are scheduled at."}, {"role": "assistant", "content": "SELECT s.service_name, COUNT(a.application_id) AS appointment_count, COUNT(DISTINCT ap.location_id) AS unique_location_count\nFROM government_services.services s\nJOIN government_services.applications a ON s.service_id = a.service_id\nJOIN government_services.appointments ap ON a.application_id = ap.application_id\nGROUP BY s.service_name;"}, {"role": "user", "content": "I got an error: relation 'appointments' does not exist."}, {"role": "assistant", "content": "-- The appointments table is not present in the provided schema. If you want to count by another join, perhaps by documents or payments, please specify.\n-- Alternatively, do you want appointment information replaced with application submissions per service and their associated location from service_locations?\nSELECT s.service_name, COUNT(a.application_id) AS application_count, COUNT(DISTINCT sl.location_id) AS unique_location_count\nFROM government_services.services s\nJOIN government_services.applications a ON s.service_id = a.service_id\nJOIN government_services.service_locations sl ON s.agency_id = sl.agency_id\nGROUP BY s.service_name;"}, {"role": "user", "content": "Show only those services where application_count is greater than 50."}, {"role": "assistant", "content": "SELECT s.service_name, COUNT(a.application_id) AS application_count, COUNT(DISTINCT sl.location_id) AS unique_location_count\nFROM government_services.services s\nJOIN government_services.applications a ON s.service_id = a.service_id\nJOIN government_services.service_locations sl ON s.agency_id = sl.agency_id\nGROUP BY s.service_name\nHAVING COUNT(a.application_id) > 50;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n citizen_id character varying(64) NOT NULL, -- unique identifier for the citizen\n national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n date_of_birth date NOT NULL,\n gender character varying(20),\n primary_address text NOT NULL, -- full primary residential address\n contact_email character varying(128) UNIQUE,\n contact_phone character varying(32),\n registration_date timestamp NOT NULL, -- when the citizen profile was created\n is_verified boolean DEFAULT false, -- whether identity has been officially verified\n PRIMARY KEY (citizen_id)\n)\nCREATE TABLE government_services.agencies ( agency_id.text, agency_name.text, jurisdiction_level.text, primary_contact_email.text, main_phone_number.text, website_url.text, established_date.date, parent_agency_id.text )\nCREATE TABLE government_services.services ( service_id text PRIMARY KEY, agency_id text, service_name text, description text, category text, eligibility_criteria text, standard_fee numeric, average_processing_time_days int, is_active boolean, online_application_url text )\nCREATE TABLE government_services.applications ( application_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, submitted_at timestamp NOT NULL, status character varying(50) NOT NULL, last_updated_at timestamp NOT NULL, assigned_employee_id character varying(64), decision_date date, notes text, reference_number character varying(100) UNIQUE, PRIMARY KEY (application_id) )\nCREATE TABLE government_services.documents ( document_id.text, application_id.text, citizen_id.text, document_type.text, file_reference.text, upload_timestamp.timestamp, expiry_date.date, verification_status.text, verified_by_employee_id.text, verification_timestamp.timestamp )\nCREATE TABLE government_services.payments ( payment_id text, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.service_locations (\n location_id character varying(64) NOT NULL, -- unique identifier for the physical location\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n location_name character varying(200), -- e.g., Downtown DMV Office\n address text NOT NULL,\n city character varying(100),\n state character varying(50),\n postal_code character varying(20),\n latitude numeric(9, 6),\n longitude numeric(9, 6),\n operating_hours text, -- description of opening times\n contact_phone character varying(32),\n is_accessible boolean, -- accessibility information (e.g., wheelchair access)\n PRIMARY KEY (location_id)\n)\nCREATE TABLE government_services.notifications ( notification_id text PRIMARY KEY, citizen_id text, application_id text, message_subject text, message_body text, channel text, sent_at timestamp, status text, related_entity_type text, related_entity_id text )\n"} {"conversations": [{"role": "user", "content": "Find all pairs of different insurance records that share the same group_number, and show group_number, the patient_insurance_id of both records, and their corresponding patient_ids."}, {"role": "assistant", "content": "SELECT a.group_number,\n a.patient_insurance_id AS pi_id1,\n a.patient_id AS patient1_id,\n b.patient_insurance_id AS pi_id2,\n b.patient_id AS patient2_id\nFROM healthcare.patient_insurance a\nJOIN healthcare.patient_insurance b\n ON a.group_number = b.group_number\n AND a.patient_insurance_id < b.patient_insurance_id\nWHERE a.group_number IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"} {"conversations": [{"role": "user", "content": "List all claim IDs that have both an 'Accident Report' and a 'Damage Assessment' document, and show the earliest upload timestamp for each type."}, {"role": "assistant", "content": "SELECT a.claim_id,\n MIN(a.uploaded_at) AS accident_report_date,\n MIN(d.uploaded_at) AS damage_assessment_date\nFROM insurance.claim_documents AS a\nJOIN insurance.claim_documents AS d\n ON a.claim_id = d.claim_id\nWHERE a.document_type = 'Accident Report'\n AND d.document_type = 'Damage Assessment'\nGROUP BY a.claim_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claim_documents ( document_id.text, claim_id.text, document_type.text, file_name.text, file_path.text, file_size_bytes.integer, mime_type.text, uploaded_by.text, uploaded_at.timestamp, description.text )\n"} {"conversations": [{"role": "user", "content": "Find all documents of type 'Correspondence' uploaded in 2023. Show the document name, upload timestamp, and the name of the case it belongs to."}, {"role": "assistant", "content": "SELECT T1.document_name, T1.upload_timestamp, T2.case_name FROM legal_services.documents AS T1 JOIN legal_services.cases AS T2 ON T1.case_id = T2.case_id WHERE T1.document_type = 'Correspondence' AND EXTRACT(YEAR FROM T1.upload_timestamp) = 2023;"}, {"role": "user", "content": "Now, only show the documents for cases handled by lawyer with ID 'lawyer_001'."}, {"role": "assistant", "content": "SELECT T1.document_name, T1.upload_timestamp, T2.case_name FROM legal_services.documents AS T1 JOIN legal_services.cases AS T2 ON T1.case_id = T2.case_id WHERE T1.document_type = 'Correspondence' AND EXTRACT(YEAR FROM T1.upload_timestamp) = 2023 AND T2.lead_lawyer_id = 'lawyer_001';"}, {"role": "user", "content": "Additionally, include the first and last name of the lawyer who actually uploaded the document, and sort the results by upload timestamp descending."}, {"role": "assistant", "content": "SELECT T1.document_name, T1.upload_timestamp, T2.case_name, T3.first_name, T3.last_name FROM legal_services.documents AS T1 JOIN legal_services.cases AS T2 ON T1.case_id = T2.case_id JOIN legal_services.lawyers AS T3 ON T1.uploaded_by_lawyer_id = T3.lawyer_id WHERE T1.document_type = 'Correspondence' AND EXTRACT(YEAR FROM T1.upload_timestamp) = 2023 AND T2.lead_lawyer_id = 'lawyer_001' ORDER BY T1.upload_timestamp DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text PRIMARY KEY, first_name text, last_name text, company_name text, email text UNIQUE, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.law_firms ( firm_id text PRIMARY KEY, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.cases ( case_id.text, case_number.text, case_name.text, client_id.text, lead_lawyer_id.text, case_type.text, status.text, date_opened.timestamp, date_closed.timestamp, description.text, court_jurisdiction.text )\nCREATE TABLE legal_services.documents (\n document_id character varying(64) NOT NULL, -- unique identifier for the document\n case_id character varying(64) NOT NULL, -- FK to cases table\n document_name character varying(255) NOT NULL, -- name of the document file\n document_type character varying(100), -- e.g., Pleading, Contract, Evidence, Correspondence\n storage_path text NOT NULL, -- path or reference to the document storage location\n uploaded_by_lawyer_id character varying(64), -- FK to lawyers table (who uploaded it)\n upload_timestamp timestamp NOT NULL, -- time the document was uploaded\n version integer DEFAULT 1, -- document version number\n description text, -- brief description or notes about the document\n PRIMARY KEY (document_id)\n)\nCREATE TABLE legal_services.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n client_id character varying(64) NOT NULL, -- FK to clients table\n lawyer_id character varying(64) NOT NULL, -- FK to lawyers table\n case_id character varying(64), -- FK to cases table (optional, if related to a specific case)\n start_time timestamp NOT NULL, -- scheduled start date and time\n end_time timestamp NOT NULL, -- scheduled end date and time\n location text, -- location of the meeting (address or virtual link)\n subject character varying(255), -- subject or purpose of the appointment\n notes text, -- additional notes for the appointment\n status character varying(50) NOT NULL, -- e.g., Scheduled, Completed, Canceled, Rescheduled\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (appointment_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all users whose email contains the word 'block', along with their username and registration timestamp."}, {"role": "assistant", "content": "SELECT user_id, username, email, created_at\nFROM web3.users\nWHERE email ILIKE '%block%';"}, {"role": "user", "content": "Can you also include the total number of such users in the result?"}, {"role": "assistant", "content": "SELECT user_id, username, email, created_at, COUNT(*) OVER() AS total_matching_users\nFROM web3.users\nWHERE email ILIKE '%block%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 NFT collections with the highest token count on Ethereum, along with their names, symbols, and floor prices."}, {"role": "assistant", "content": "SELECT n.name, n.symbol, n.floor_price, n.token_count FROM nft_collections n WHERE n.blockchain = 'ethereum' ORDER BY n.token_count DESC LIMIT 5;"}, {"role": "user", "content": "Now, join this with the nft_metadata table to include the average rarity score for each collection."}, {"role": "assistant", "content": "SELECT n.name, n.symbol, n.floor_price, n.token_count, AVG(m.rarity_score) as avg_rarity_score FROM nft_collections n JOIN nft_metadata m ON n.contract_address = m.contract_address WHERE n.blockchain = 'ethereum' GROUP BY n.name, n.symbol, n.floor_price, n.token_count ORDER BY n.token_count DESC LIMIT 5;"}, {"role": "user", "content": "Can you filter these results to only show collections with an average rarity score greater than 80?"}, {"role": "assistant", "content": "SELECT n.name, n.symbol, n.floor_price, n.token_count, AVG(m.rarity_score) as avg_rarity_score FROM nft_collections n JOIN nft_metadata m ON n.contract_address = m.contract_address WHERE n.blockchain = 'ethereum' GROUP BY n.name, n.symbol, n.floor_price, n.token_count HAVING AVG(m.rarity_score) > 80 ORDER BY n.token_count DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash text, transaction_index bigint, from_address text, contract_address text, symbol text, total_supply text, name text, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info text, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address text, wallet_address text, amount text, pk text )\nCREATE TABLE sui_coins ( object_id text, status text, coin_type text, balance text, owner text )\nCREATE TABLE sui_coins_metadata ( object_id text, coin_type text, status text, decimals bigint, description text, icon_url text, symbol text, name text )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain text, contract_address text, name text, symbol text, deploy_block_number bigint, deploy_block_time bigint, erc_type text, owner text, traits text, description text, slug text, media_info text, image_url text, banner_image_url text, updated_at bigint, banner text, token_count bigint, floor_price text, floor_price_symbol text, floor_price_contract text, pk integer )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest ( blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply text, amount text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"} {"conversations": [{"role": "user", "content": "Show me all cryptocurrency assets that have been traded more than 50 times but have never been traded in quantities greater than 100, along with their average trade price."}, {"role": "assistant", "content": "SELECT a.asset_id, a.name, a.symbol, COUNT(t.trade_id) AS trade_count, AVG(t.price) AS avg_price FROM trading_platform.assets a JOIN trading_platform.trades t ON a.asset_id = t.asset_id WHERE a.type = 'cryptocurrency' GROUP BY a.asset_id, a.name, a.symbol HAVING COUNT(t.trade_id) > 50 AND MAX(t.quantity) <= 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id character varying(64) NOT NULL, username character varying(128) NOT NULL, email character varying(128) NOT NULL, password_hash text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (user_id) )\nCREATE TABLE trading_platform.wallets ( wallet_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, address character varying(128) NOT NULL, private_key text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (wallet_id) )\nCREATE TABLE trading_platform.orders ( order_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, wallet_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, order_type character varying(32) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, status character varying(32) NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (order_id) )\nCREATE TABLE trading_platform.trades ( trade_id character varying(64) NOT NULL, order_id character varying(64) NOT NULL, buyer_id character varying(64) NOT NULL, seller_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, traded_at timestamp NOT NULL, PRIMARY KEY (trade_id) )\nCREATE TABLE trading_platform.assets ( asset_id character varying(64) NOT NULL, name character varying(128) NOT NULL, symbol character varying(32) NOT NULL, type character varying(32) NOT NULL, PRIMARY KEY (asset_id) )\nCREATE TABLE trading_platform.utxos ( utxo_id character varying(64) NOT NULL, transaction_id character varying(64) NOT NULL, output_index integer NOT NULL, address character varying(128) NOT NULL, amount numeric(38,14) NOT NULL, spent boolean NOT NULL, PRIMARY KEY (utxo_id) )\nCREATE TABLE trading_platform.dapps ( dapp_id character varying(64) NOT NULL, name character varying(128) NOT NULL, description text NOT NULL, url character varying(256) NOT NULL, PRIMARY KEY (dapp_id) )\nCREATE TABLE trading_platform.peers ( peer_id character varying(64) NOT NULL, ip_address character varying(15) NOT NULL, port integer NOT NULL, last_seen timestamp NOT NULL, PRIMARY KEY (peer_id) )\nCREATE TABLE trading_platform.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, status character varying(32) NOT NULL, reviewed_at timestamp NOT NULL, PRIMARY KEY (kyc_audit_id) )\nCREATE TABLE trading_platform.notifications ( notification_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, message text NOT NULL, sent_at timestamp NOT NULL, read_at timestamp, PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "List all fuel refueling events with the refueled vehicle's make and model, the fuel type used, and the fueling location ID."}, {"role": "assistant", "content": "SELECT fl.fuel_log_id, fl.log_timestamp, v.make, v.model, fl.fuel_type, fl.quantity, fl.unit, fl.total_cost, fl.location_id\nFROM transportation.fuel_logs fl\nJOIN transportation.vehicles v ON fl.vehicle_id = v.vehicle_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id.text, employee_id.text, first_name.text, last_name.text, license_number.text, license_expiry_date.date, contact_number.text, email.text, hire_date.date, status.text )\nCREATE TABLE transportation.routes ( route_id text, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes integer, type text )\nCREATE TABLE transportation.trips ( trip_id text, route_id text, vehicle_id text, driver_id text, scheduled_departure timestamp, actual_departure timestamp, scheduled_arrival timestamp, actual_arrival timestamp, origin_location_id text, destination_location_id text, status text, passenger_count integer, cargo_manifest_id text )\nCREATE TABLE transportation.maintenance_logs (\n log_id character varying(64) NOT NULL, -- unique identifier for the maintenance record\n vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle serviced\n service_date date NOT NULL, -- date the service was performed\n odometer_reading integer, -- vehicle mileage at time of service\n service_type character varying(128) NOT NULL, -- type of service (e.g., Oil Change, Tire Rotation, Engine Repair)\n description text NOT NULL, -- detailed description of work done\n cost numeric(10, 2), -- cost of the service\n mechanic_name character varying(128), -- name or ID of the mechanic/shop\n next_service_due_date date, -- recommended date for next service\n PRIMARY KEY (log_id)\n)\nCREATE TABLE transportation.fuel_logs (\n fuel_log_id character varying(64) NOT NULL, -- unique identifier for the fuel log entry\n vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle fueled\n trip_id character varying(64), -- optional: identifier of the trip during which fueling occurred\n log_timestamp timestamp with time zone NOT NULL, -- time when fueling occurred\n fuel_type character varying(32) NOT NULL, -- type of fuel added (matches vehicle's fuel type)\n quantity numeric(10, 3) NOT NULL, -- amount of fuel added (e.g., Liters, Gallons, kWh)\n unit character varying(16) NOT NULL, -- unit of quantity (e.g., L, gal, kWh)\n cost_per_unit numeric(8, 4), -- price per unit of fuel\n total_cost numeric(10, 2) NOT NULL, -- total cost of the fuel purchase\n odometer_reading integer, -- vehicle mileage at time of fueling\n location_id character varying(64), -- identifier of the fueling station/location\n PRIMARY KEY (fuel_log_id)\n)\nCREATE TABLE transportation.bookings ( booking_id character varying(64) NOT NULL, passenger_id character varying(64) NOT NULL, trip_id character varying(64) NOT NULL, seat_number character varying(16), booking_time timestamp with time zone NOT NULL, status character varying(32) NOT NULL, fare numeric(10, 2) NOT NULL, payment_transaction_id character varying(128), special_requests text, PRIMARY KEY (booking_id) )\n"} {"conversations": [{"role": "user", "content": "For each route that originates from a location of type 'Port', list the route number, the name of the origin location, and the total distance accumulated from all completed trips on this route."}, {"role": "assistant", "content": "SELECT\n r.route_number,\n l_origin.name AS origin_location_name,\n SUM(t.distance_km) AS total_accumulated_distance\nFROM transportation.routes AS r\nJOIN transportation.locations AS l_origin\n ON r.origin_location_id = l_origin.location_id\nJOIN transportation.trips AS t\n ON r.route_id = t.route_id\nWHERE\n l_origin.type = 'Port' AND t.status = 'Completed'\nGROUP BY\n r.route_id,\n r.route_number,\n l_origin.name;"}, {"role": "user", "content": "Now, only include routes where the accumulated distance is greater than 5000 kilometers and order the results by accumulated distance descending."}, {"role": "assistant", "content": "SELECT\n r.route_number,\n l_origin.name AS origin_location_name,\n SUM(t.distance_km) AS total_accumulated_distance\nFROM transportation.routes AS r\nJOIN transportation.locations AS l_origin\n ON r.origin_location_id = l_origin.location_id\nJOIN transportation.trips AS t\n ON r.route_id = t.route_id\nWHERE\n l_origin.type = 'Port' AND t.status = 'Completed'\nGROUP BY\n r.route_id,\n r.route_number,\n l_origin.name\nHAVING\n SUM(t.distance_km) > 5000\nORDER BY\n total_accumulated_distance DESC;"}, {"role": "user", "content": "Also include the number of completed trips for each of these routes and filter further to only show routes that have had more than 5 completed trips."}, {"role": "assistant", "content": "SELECT\n r.route_number,\n l_origin.name AS origin_location_name,\n SUM(t.distance_km) AS total_accumulated_distance,\n COUNT(t.trip_id) AS completed_trip_count\nFROM transportation.routes AS r\nJOIN transportation.locations AS l_origin\n ON r.origin_location_id = l_origin.location_id\nJOIN transportation.trips AS t\n ON r.route_id = t.route_id\nWHERE\n l_origin.type = 'Port' AND t.status = 'Completed'\nGROUP BY\n r.route_id,\n r.route_number,\n l_origin.name\nHAVING\n SUM(t.distance_km) > 5000 AND COUNT(t.trip_id) > 5\nORDER BY\n total_accumulated_distance DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id text PRIMARY KEY, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.trips ( trip_id text PRIMARY KEY, route_id text, vehicle_id text, driver_id text, scheduled_departure timestamp, actual_departure timestamp, scheduled_arrival timestamp, actual_arrival timestamp, origin_location_id text, destination_location_id text, status text, passenger_count int, cargo_manifest_id text )\nCREATE TABLE transportation.locations ( location_id text PRIMARY KEY, name text, type text, address_line1 text, city text, state_province text, postal_code text, country text, latitude numeric, longitude numeric, timezone text )\nCREATE TABLE transportation.maintenance_logs ( log_id text PRIMARY KEY, vehicle_id text, service_date date, odometer_reading int, service_type text, description text, cost numeric, mechanic_name text, next_service_due_date date )\nCREATE TABLE transportation.bookings ( booking_id text PRIMARY KEY, passenger_id text, trip_id text, seat_number text, booking_time timestamp, status text, fare numeric, payment_transaction_id text, special_requests text )\n"} {"conversations": [{"role": "user", "content": "What is the schedule of trains arriving at station with ID 'ST789' tomorrow?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide the train schedule for station ID 'ST789' as this information is not available in the current database. The table only contains details about station attributes such as name, location, and number of platforms. For train schedules, please refer to the relevant train service provider or timetable database."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.stations ( station_id text, station_name text, city text, state_province text, country_code text, address text, timezone text, number_of_platforms integer, created_at timestamp, last_updated_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Provide a report of each user with their username and the count of all log entries from the last 30 days."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, COUNT(l.log_id) AS log_count\nFROM trading_platform.users u\nLEFT JOIN trading_platform.logs l\n ON u.user_id = l.user_id\n AND l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\nGROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Actually, show only logs where the action includes the word 'trade'."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, COUNT(l.log_id) AS log_count\nFROM trading_platform.users u\nJOIN trading_platform.logs l\n ON u.user_id = l.user_id\nWHERE l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\n AND l.action ILIKE '%trade%'\nGROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Also include the earliest log date for each user in that period."}, {"role": "assistant", "content": "SELECT u.user_id,\n u.username,\n COUNT(l.log_id) AS log_count,\n MIN(l.logged_at) AS first_log_date\nFROM trading_platform.users u\nJOIN trading_platform.logs l\n ON u.user_id = l.user_id\nWHERE l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\n AND l.action ILIKE '%trade%'\nGROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Finally, sort the results by log_count descending and limit to the top 5 users."}, {"role": "assistant", "content": "SELECT u.user_id,\n u.username,\n COUNT(l.log_id) AS log_count,\n MIN(l.logged_at) AS first_log_date\nFROM trading_platform.users u\nJOIN trading_platform.logs l\n ON u.user_id = l.user_id\nWHERE l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\n AND l.action ILIKE '%trade%'\nGROUP BY u.user_id, u.username\nORDER BY log_count DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.orders (\n order_id character varying(64) NOT NULL, -- unique identifier for the order\n user_id character varying(64) NOT NULL, -- identifier of the user placing the order\n wallet_id character varying(64) NOT NULL, -- identifier of the wallet used for the order\n asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n order_type character varying(32) NOT NULL, -- type of the order (e.g., buy, sell)\n quantity numeric(38,14) NOT NULL, -- quantity of the asset in the order\n price numeric(38,14) NOT NULL, -- price per unit of the asset\n status character varying(32) NOT NULL, -- status of the order (e.g., open, filled, canceled)\n created_at timestamp NOT NULL, -- time when the order was created\n PRIMARY KEY (order_id)\n)\nCREATE TABLE trading_platform.utxos (\n utxo_id character varying(64) NOT NULL, -- unique identifier for the UTXO\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction that created the UTXO\n output_index integer NOT NULL, -- index of the output in the transaction\n address character varying(128) NOT NULL, -- address that can spend the UTXO\n amount numeric(38,14) NOT NULL, -- amount of the asset in the UTXO\n spent boolean NOT NULL, -- whether the UTXO has been spent\n PRIMARY KEY (utxo_id)\n)\nCREATE TABLE trading_platform.dapps (\n dapp_id character varying(64) NOT NULL, -- unique identifier for the DApp\n name character varying(128) NOT NULL, -- name of the DApp\n description text NOT NULL, -- description of the DApp\n url character varying(256) NOT NULL, -- URL of the DApp\n PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.peers (\n peer_id character varying(64) NOT NULL, -- unique identifier for the peer\n ip_address character varying(15) NOT NULL, -- IP address of the peer\n port integer NOT NULL, -- port number of the peer\n last_seen timestamp NOT NULL, -- last time the peer was active\n PRIMARY KEY (peer_id)\n)\nCREATE TABLE trading_platform.logs (\n log_id character varying(64) NOT NULL, -- unique identifier for the log entry\n user_id character varying(64), -- identifier of the user associated with the log entry\n action character varying(128) NOT NULL, -- action performed\n details text NOT NULL, -- details of the action\n logged_at timestamp NOT NULL, -- time when the log entry was created\n PRIMARY KEY (log_id)\n)\n"} {"conversations": [{"role": "user", "content": "What are the maintenance costs for a specific aircraft model like the Airbus A320?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to data regarding maintenance costs for specific aircraft models such as the Airbus A320. The information in the database is limited to details like model name, manufacturer, passenger capacity, and technical specifications. For maintenance cost information, you may need to consult with the manufacturer or a maintenance service provider."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models ( model_id character varying(64) NOT NULL, model_name character varying(128) NOT NULL, manufacturer character varying(128) NOT NULL, passenger_capacity integer, max_range_km integer, engine_type character varying(100), wingspan_m numeric(6,2), status character varying(50) NOT NULL, first_flight_date date, PRIMARY KEY (model_id) )\n"} {"conversations": [{"role": "user", "content": "Show the number of active agents in each license state."}, {"role": "assistant", "content": "SELECT license_state,\n COUNT(*) AS active_agent_count\nFROM insurance.agents\nWHERE status = 'active'\nGROUP BY license_state;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.agents ( agent_id text PRIMARY KEY, first_name text, last_name text, agency_name text, license_number text, license_state text, contact_email text, contact_phone text, hire_date date, termination_date date, status text, commission_rate numeric, manager_id text )\n"} {"conversations": [{"role": "user", "content": "List all peer logs, showing the user_id and the action taken, ordered by the most recent log entry."}, {"role": "assistant", "content": "SELECT user_id, action, logged_at\nFROM trading_platform.logs\nORDER BY logged_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id.text, username.text, email.text, password_hash.text, created_at.timestamp )\nCREATE TABLE trading_platform.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\nCREATE TABLE trading_platform.orders ( order_id text, user_id text, wallet_id text, asset_id text, order_type text, quantity numeric, price numeric, status text, created_at timestamp )\nCREATE TABLE trading_platform.assets ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.utxos ( utxo_id text PRIMARY KEY, transaction_id text, output_index int, address text, amount numeric, spent boolean )\nCREATE TABLE trading_platform.dapps ( dapp_id text, name text, description text, url text )\nCREATE TABLE trading_platform.logs ( log_id text PRIMARY KEY, user_id text, action text, details text, logged_at timestamp )\nCREATE TABLE trading_platform.notifications ( notification_id text, user_id text, message text, sent_at timestamp, read_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Find pairs of BUY and SELL trades from the trades table for the same account that occurred on the same settlement_date and had matching quantities."}, {"role": "assistant", "content": "SELECT\n a.trade_id AS buy_trade_id,\n b.trade_id AS sell_trade_id,\n a.account_id,\n a.settlement_date,\n a.quantity\nFROM financial_services.trades a\nJOIN financial_services.trades b\n ON a.account_id = b.account_id\n AND a.settlement_date = b.settlement_date\n AND a.quantity = b.quantity\nWHERE a.trade_type = 'BUY'\n AND b.trade_type = 'SELL';"}, {"role": "user", "content": "Only include pairs where the execution_venue is different between the two trades."}, {"role": "assistant", "content": "SELECT\n a.trade_id AS buy_trade_id,\n b.trade_id AS sell_trade_id,\n a.account_id,\n a.settlement_date,\n a.quantity\nFROM financial_services.trades a\nJOIN financial_services.trades b\n ON a.account_id = b.account_id\n AND a.settlement_date = b.settlement_date\n AND a.quantity = b.quantity\nWHERE a.trade_type = 'BUY'\n AND b.trade_type = 'SELL'\n AND a.execution_venue <> b.execution_venue;"}, {"role": "user", "content": "Sort the results by account_id ascending and settlement_date descending."}, {"role": "assistant", "content": "SELECT\n a.trade_id AS buy_trade_id,\n b.trade_id AS sell_trade_id,\n a.account_id,\n a.settlement_date,\n a.quantity\nFROM financial_services.trades a\nJOIN financial_services.trades b\n ON a.account_id = b.account_id\n AND a.settlement_date = b.settlement_date\n AND a.quantity = b.quantity\nWHERE a.trade_type = 'BUY'\n AND b.trade_type = 'SELL'\n AND a.execution_venue <> b.execution_venue\nORDER BY a.account_id ASC, a.settlement_date DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.trades ( trade_id character varying(64) NOT NULL, account_id character varying(64) NOT NULL, security_id character varying(64) NOT NULL, order_id character varying(64), trade_type character varying(10) NOT NULL, quantity numeric(19, 8) NOT NULL, price_per_unit numeric(19, 8) NOT NULL, total_amount numeric(19, 4) NOT NULL, commission numeric(10, 4), trade_timestamp timestamp NOT NULL, settlement_date date, status character varying(32) NOT NULL, execution_venue character varying(100), PRIMARY KEY (trade_id), FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id), FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id) )\nCREATE TABLE financial_services.employees ( employee_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(100) NOT NULL, department character varying(100), branch_id character varying(64), email character varying(128) NOT NULL UNIQUE, phone_extension character varying(20), hire_date date NOT NULL, termination_date date, manager_id character varying(64), status character varying(32) NOT NULL, PRIMARY KEY (employee_id), FOREIGN KEY (branch_id) REFERENCES financial_services.branches(branch_id), FOREIGN KEY (manager_id) REFERENCES financial_services.employees(employee_id) )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 ERC20 tokens with the highest total supply, along with their names and contract addresses."}, {"role": "assistant", "content": "SELECT name, contract_address, total_supply FROM token_metas WHERE is_erc20 = 1 ORDER BY CAST(total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Can you modify the query to also include the symbol and filter for tokens with decimals equal to 18?"}, {"role": "assistant", "content": "SELECT name, symbol, contract_address, total_supply FROM token_metas WHERE is_erc20 = 1 AND decimals = 18 ORDER BY CAST(total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Now join this with the erc20_balances_historical table to show the total balance held across all wallets for each token."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tm.total_supply, SUM(CAST(ebh.amount AS decimal)) AS total_balance FROM token_metas tm JOIN erc20_balances_historical ebh ON tm.contract_address = ebh.contract_address WHERE tm.is_erc20 = 1 AND tm.decimals = 18 GROUP BY tm.name, tm.symbol, tm.contract_address, tm.total_supply ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk varchar )\nCREATE TABLE nft_holder_historical (\n block_number bigint NOT NULL, -- Block number containing the transaction\n contract_address varchar NOT NULL, -- Event contract address\n wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n token_id varchar NOT NULL, -- NFT token id\n contract_type varchar NOT NULL, -- NFT contract type\n amount varchar NOT NULL, -- The quantity held in the wallet\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 7200))\n)\nCREATE TABLE sui_nfts (\n object_id varchar NOT NULL, -- object id of the nft\n status varchar NOT NULL, -- status of the package, exists or deleted\n collection_type varchar NOT NULL, -- collection type of the nft, eg. 0x...123::avatars::Avatar\n package_id varchar NOT NULL, -- which package the nft belongs to, eg. 0x...123::avatars belongs to 0x...123\n previous_transaction varchar NOT NULL, -- previous transaction of the nft\n display varchar NOT NULL, -- nft metadata json object\n owner varchar NOT NULL, -- nft owner\n name varchar NOT NULL -- nft name\n)\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE mud_holesky_redstone (\n address varchar NOT NULL, -- address fields for the functionType in contract\n table_id varchar NOT NULL, -- table_id fields for the functionType in contract\n key_bytes varchar NOT NULL, -- key_bytes fields for the functionType in contract\n key0 varchar NOT NULL, -- key0 fields for the functionType in contract\n key1 varchar NOT NULL, -- key1 fields for the functionType in contract\n static_data varchar NOT NULL, -- static_data fields for the functionType in contract\n encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType in contract\n dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType in contract\n is_deleted boolean NOT NULL, -- is_deleted fields for the functionType in contract\n block_number bigint NOT NULL, -- Block number uniquely identifying the block\n log_index bigint NOT NULL -- Index of the log within the transaction\n)\nCREATE TABLE token_balances_bitcoin ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.text, amount.text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\n"} {"conversations": [{"role": "user", "content": "Find all smart contracts where the code length is greater than 1000 characters."}, {"role": "assistant", "content": "SELECT contract_id, creator_address, LENGTH(code) AS code_length FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000;"}, {"role": "user", "content": "Now group these by creator_address and show the count of such contracts per creator."}, {"role": "assistant", "content": "SELECT creator_address, COUNT(*) AS large_code_contract_count FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000 GROUP BY creator_address;"}, {"role": "user", "content": "Can you order the results by the count in descending order?"}, {"role": "assistant", "content": "SELECT creator_address, COUNT(*) AS large_code_contract_count FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000 GROUP BY creator_address ORDER BY large_code_contract_count DESC;"}, {"role": "user", "content": "Now show only creators who have more than 3 such contracts."}, {"role": "assistant", "content": "SELECT creator_address, COUNT(*) AS large_code_contract_count FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000 GROUP BY creator_address HAVING COUNT(*) > 3 ORDER BY large_code_contract_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.smart_contracts ( contract_id.text, creator_address.text, code.text, timestamp.timestamp )\n"} {"conversations": [{"role": "user", "content": "For each security issuer, show the count of market data points and the average close price for their securities."}, {"role": "assistant", "content": "SELECT T2.issuer_name, COUNT(T1.*) AS data_point_count, AVG(T1.close_price) AS avg_close_price FROM financial_services.market_data AS T1 JOIN financial_services.securities AS T2 ON T1.security_id = T2.security_id GROUP BY T2.issuer_name;"}, {"role": "user", "content": "Only include issuers who have more than 1000 market data points in total."}, {"role": "assistant", "content": "SELECT T2.issuer_name, COUNT(T1.*) AS data_point_count, AVG(T1.close_price) AS avg_close_price FROM financial_services.market_data AS T1 JOIN financial_services.securities AS T2 ON T1.security_id = T2.security_id GROUP BY T2.issuer_name HAVING COUNT(T1.*) > 1000;"}, {"role": "user", "content": "Also, include the average volume for each issuer and sort the results by average close price descending."}, {"role": "assistant", "content": "SELECT T2.issuer_name, COUNT(T1.*) AS data_point_count, AVG(T1.close_price) AS avg_close_price, AVG(T1.volume) AS avg_volume FROM financial_services.market_data AS T1 JOIN financial_services.securities AS T2 ON T1.security_id = T2.security_id GROUP BY T2.issuer_name HAVING COUNT(T1.*) > 1000 ORDER BY avg_close_price DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.market_data (\n data_point_id bigserial NOT NULL, -- auto-incrementing primary key\n security_id character varying(64) NOT NULL, -- identifier for the security\n data_timestamp timestamp NOT NULL, -- timestamp for the data point (e.g., end of day, intraday)\n open_price numeric(19, 8), -- opening price for the period\n high_price numeric(19, 8), -- highest price during the period\n low_price numeric(19, 8), -- lowest price during the period\n close_price numeric(19, 8) NOT NULL, -- closing price for the period\n adjusted_close_price numeric(19, 8), -- closing price adjusted for dividends and splits\n volume bigint, -- trading volume during the period\n source character varying(50), -- source of the market data (e.g., Bloomberg, Refinitiv)\n PRIMARY KEY (data_point_id),\n UNIQUE (security_id, data_timestamp), -- Ensure unique data point per security per time\n FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id)\n)\n"} {"conversations": [{"role": "user", "content": "What is the current market price of a Boeing 737 MAX aircraft?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to the current market price of aircraft models. The data I have is limited to technical specifications and general information about aircraft models such as passenger capacity, range, and status. For pricing information, you may need to consult with manufacturers or industry reports."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models (\n model_id character varying(64) NOT NULL, -- unique identifier for the aircraft model\n model_name character varying(128) NOT NULL, -- commercial name of the model (e.g., 737 MAX, A320neo)\n manufacturer character varying(128) NOT NULL, -- manufacturer name (e.g., Boeing, Airbus)\n passenger_capacity integer, -- typical passenger capacity\n max_range_km integer, -- maximum flight range in kilometers\n engine_type character varying(100), -- type of engines used\n wingspan_m numeric(6,2), -- wingspan in meters\n status character varying(50) NOT NULL, -- e.g., 'In Production', 'Development', 'Discontinued'\n first_flight_date date, -- date of the model's first flight\n PRIMARY KEY (model_id)\n)\n"} {"conversations": [{"role": "user", "content": "Which employees have verified more than 5 documents in the last 30 days? Return the employee's full name, department, and the number of verifications."}, {"role": "assistant", "content": "SELECT e.first_name || ' ' || e.last_name AS full_name, e.department, COUNT(d.document_id) AS verification_count\nFROM government_services.documents d\nJOIN government_services.employees e ON d.verified_by_employee_id = e.employee_id\nWHERE d.verification_status = 'Verified'\n AND d.verification_timestamp >= now() - interval '30 days'\nGROUP BY e.first_name, e.last_name, e.department\nHAVING COUNT(d.document_id) > 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.services ( service_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, service_name character varying(255) NOT NULL, description text, category character varying(100), eligibility_criteria text, standard_fee numeric(10, 2) DEFAULT 0.00, average_processing_time_days integer, is_active boolean DEFAULT true, online_application_url character varying(255), PRIMARY KEY (service_id) )\nCREATE TABLE government_services.applications ( application_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, submitted_at timestamp NOT NULL, status character varying(50) NOT NULL, last_updated_at timestamp NOT NULL, assigned_employee_id character varying(64), decision_date date, notes text, reference_number character varying(100) UNIQUE, PRIMARY KEY (application_id) )\nCREATE TABLE government_services.documents ( document_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, document_type character varying(100) NOT NULL, file_reference text NOT NULL, upload_timestamp timestamp NOT NULL, expiry_date date, verification_status character varying(30) DEFAULT 'Pending', verified_by_employee_id character varying(64), verification_timestamp timestamp, PRIMARY KEY (document_id) )\nCREATE TABLE government_services.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_id) )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\n"} {"conversations": [{"role": "user", "content": "Show me the number of players registered in each country, along with the number of different games available for each country."}, {"role": "assistant", "content": "SELECT p.country_code, COUNT(DISTINCT p.player_id) AS player_count, COUNT(DISTINCT g.game_id) AS game_count\nFROM gaming_technology.players p\nCROSS JOIN gaming_technology.games g\nGROUP BY p.country_code;"}, {"role": "user", "content": "This doesn't make sense; the game count should be the number of games, not all possible combinations. Can you fix it to just show the count of players per country?"}, {"role": "assistant", "content": "SELECT p.country_code, COUNT(*) AS player_count\nFROM gaming_technology.players p\nGROUP BY p.country_code;"}, {"role": "user", "content": "Now add in the total number of servers located in each country, based on the players' country code matching the server's region."}, {"role": "assistant", "content": "SELECT p.country_code, COUNT(*) AS player_count,\n (SELECT COUNT(*) FROM gaming_technology.servers s WHERE s.region = p.country_code) AS server_count\nFROM gaming_technology.players p\nGROUP BY p.country_code;"}, {"role": "user", "content": "Show only countries where there are at least 5 servers."}, {"role": "assistant", "content": "SELECT p.country_code, COUNT(*) AS player_count,\n (SELECT COUNT(*) FROM gaming_technology.servers s WHERE s.region = p.country_code) AS server_count\nFROM gaming_technology.players p\nGROUP BY p.country_code\nHAVING (SELECT COUNT(*) FROM gaming_technology.servers s WHERE s.region = p.country_code) >= 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id.uuid, username.text, email.text, password_hash.text, registration_date.timestamptz, last_login.timestamptz, country_code.text, status.text, profile_data.jsonb )\nCREATE TABLE gaming_technology.games (\n game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n title character varying(200) NOT NULL, -- official title of the game\n developer_id uuid NOT NULL, -- FK linking to the developers table\n publisher_id uuid, -- FK linking to a potential publishers table (optional)\n genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n release_date date, -- official release date\n description text, -- short description or synopsis of the game\n platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n website character varying(255), -- official website URL\n PRIMARY KEY (game_id)\n -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.servers ( server_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, server_name character varying(150), region character varying(50) NOT NULL, ip_address character varying(45), port integer, current_players integer NOT NULL DEFAULT 0, max_players integer NOT NULL, status character varying(30) NOT NULL DEFAULT 'offline', last_heartbeat timestamp with time zone, PRIMARY KEY (server_id) )\nCREATE TABLE gaming_technology.achievements ( achievement_id uuid, game_id uuid, name text, description text, icon_url text, points integer, hidden boolean )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, item_name character varying(150) NOT NULL, item_type character varying(50) NOT NULL, description text, rarity character varying(30), cost_currency character varying(10), cost_amount numeric(12, 2), attributes jsonb, PRIMARY KEY (item_id) )\n"} {"conversations": [{"role": "user", "content": "Find services that have associated documents with a 'Pending' verification status. Show the service name and the document type name."}, {"role": "assistant", "content": "SELECT DISTINCT s.service_name, dt.document_type_name FROM government_services.services AS s JOIN government_services.applications AS a ON s.service_id = a.service_id JOIN government_services.application_documents AS ad ON a.application_id = ad.application_id JOIN government_services.document_types AS dt ON ad.document_type_id = dt.document_type_id WHERE ad.verification_status = 'Pending';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n citizen_id character varying(64) NOT NULL, -- unique identifier for the citizen\n national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n date_of_birth date NOT NULL,\n gender character varying(20),\n primary_address text NOT NULL, -- full primary residential address\n contact_email character varying(128) UNIQUE,\n contact_phone character varying(32),\n registration_date timestamp NOT NULL, -- when the citizen profile was created\n is_verified boolean DEFAULT false, -- whether identity has been officially verified\n PRIMARY KEY (citizen_id)\n)\n"} {"conversations": [{"role": "user", "content": "Provide a list of all vehicles and the total quantity of fuel refueled for each vehicle."}, {"role": "assistant", "content": "SELECT T1.license_plate, sum(T2.quantity) FROM transportation.vehicles AS T1 JOIN transportation.fuel_logs AS T2 ON T1.vehicle_id = T2.vehicle_id GROUP BY T1.license_plate"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id text PRIMARY KEY, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.trips ( trip_id text PRIMARY KEY, route_id text, vehicle_id text, driver_id text, scheduled_departure timestamp, actual_departure timestamp, scheduled_arrival timestamp, actual_arrival timestamp, origin_location_id text, destination_location_id text, status text, passenger_count int, cargo_manifest_id text )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id text PRIMARY KEY, vehicle_id text, trip_id text, log_timestamp timestamp, fuel_type text, quantity numeric, unit text, cost_per_unit numeric, total_cost numeric, odometer_reading int, location_id text )\nCREATE TABLE transportation.passengers ( passenger_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, loyalty_program_id text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "List each employee's first and last name along with the count of active services offered by their agency."}, {"role": "assistant", "content": "SELECT e.first_name, e.last_name, COUNT(s.service_id) AS active_service_count\nFROM government_services.employees e\nJOIN government_services.services s ON e.agency_id = s.agency_id AND s.is_active = TRUE\nGROUP BY e.employee_id, e.first_name, e.last_name;"}, {"role": "user", "content": "Actually, only include employees whose service count is greater than 5."}, {"role": "assistant", "content": "SELECT e.first_name, e.last_name, COUNT(s.service_id) AS active_service_count\nFROM government_services.employees e\nJOIN government_services.services s ON e.agency_id = s.agency_id AND s.is_active = TRUE\nGROUP BY e.employee_id, e.first_name, e.last_name\nHAVING COUNT(s.service_id) > 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\nCREATE TABLE government_services.services ( service_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, service_name character varying(255) NOT NULL, description text, category character varying(100), eligibility_criteria text, standard_fee numeric(10, 2) DEFAULT 0.00, average_processing_time_days integer, is_active boolean DEFAULT true, online_application_url character varying(255), PRIMARY KEY (service_id) )\nCREATE TABLE government_services.applications ( application_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, submitted_at timestamp NOT NULL, status character varying(50) NOT NULL, last_updated_at timestamp NOT NULL, assigned_employee_id character varying(64), decision_date date, notes text, reference_number character varying(100) UNIQUE, PRIMARY KEY (application_id) )\nCREATE TABLE government_services.payments ( payment_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, service_id character varying(64), amount numeric(12, 2) NOT NULL, currency character varying(3) NOT NULL DEFAULT 'USD', payment_method character varying(50), payment_provider_reference character varying(128), payment_timestamp timestamp NOT NULL, status character varying(30) NOT NULL, notes text, PRIMARY KEY (payment_id) )\nCREATE TABLE government_services.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_id) )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "Show me the average, maximum, and minimum points for all achievements."}, {"role": "assistant", "content": "SELECT AVG(points) AS average_points, MAX(points) AS maximum_points, MIN(points) AS minimum_points FROM gaming_technology.achievements;"}, {"role": "user", "content": "Can you break this down by whether the achievement is hidden or not?"}, {"role": "assistant", "content": "SELECT hidden, AVG(points) AS average_points, MAX(points) AS maximum_points, MIN(points) AS minimum_points FROM gaming_technology.achievements GROUP BY hidden;"}, {"role": "user", "content": "Exclude achievements with zero points from this calculation."}, {"role": "assistant", "content": "SELECT hidden, AVG(points) AS average_points, MAX(points) AS maximum_points, MIN(points) AS minimum_points FROM gaming_technology.achievements WHERE points > 0 GROUP BY hidden;"}, {"role": "user", "content": "Also, include the count of achievements in each group."}, {"role": "assistant", "content": "SELECT hidden, COUNT(achievement_id) AS achievement_count, AVG(points) AS average_points, MAX(points) AS maximum_points, MIN(points) AS minimum_points FROM gaming_technology.achievements WHERE points > 0 GROUP BY hidden;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.games ( game_id.uuid, title.text, developer_id.uuid, publisher_id.uuid, genre.text, release_date.date, description.text, platform.text, engine.text, website.text )\nCREATE TABLE gaming_technology.developers ( developer_id uuid PRIMARY KEY, name text, country text, founded_year int, website text, created_at timestamptz )\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid PRIMARY KEY, player_id uuid, game_id uuid, server_id uuid, start_time timestamptz, end_time timestamptz, duration_seconds int, score int, session_data jsonb )\nCREATE TABLE gaming_technology.achievements (\n achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an achievement definition\n game_id uuid NOT NULL, -- FK linking to the game the achievement belongs to\n name character varying(150) NOT NULL, -- name of the achievement\n description text NOT NULL, -- how to unlock the achievement\n icon_url character varying(255), -- URL for the achievement's icon\n points integer DEFAULT 0, -- points awarded for unlocking (optional)\n hidden boolean DEFAULT false, -- whether the achievement details are hidden until unlocked\n PRIMARY KEY (achievement_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_inventory (\n inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an inventory entry\n player_id uuid NOT NULL, -- FK linking to the player owning the item\n item_id uuid NOT NULL, -- FK linking to the item definition\n quantity integer NOT NULL DEFAULT 1, -- number of items held (for stackable items)\n acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the item was acquired\n instance_data jsonb, -- data specific to this instance (e.g., weapon mods, durability)\n PRIMARY KEY (inventory_id),\n -- Optional unique constraint if items are non-stackable or unique instances\n -- UNIQUE (player_id, item_id) -- Use if quantity is always 1\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (item_id) REFERENCES gaming_technology.in_game_items(item_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show each contract's address along with the total number of events it has emitted and the total number of transactions sent to it."}, {"role": "assistant", "content": "SELECT\n c.address,\n COUNT(e.event_id) AS event_count,\n COUNT(t.transaction_id) AS tx_count\nFROM web3.contracts c\nLEFT JOIN web3.events e\n ON c.contract_id = e.contract_id\nLEFT JOIN web3.transactions t\n ON c.address = t.to_address\nGROUP BY c.address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts (\n contract_id character varying(64) NOT NULL, -- unique identifier for the contract\n address character varying(128) NOT NULL, -- address of the deployed contract\n abi text NOT NULL, -- application binary interface of the contract\n bytecode text NOT NULL, -- bytecode of the contract\n deployer_address character varying(128) NOT NULL, -- address of the deployer\n deployed_at timestamp NOT NULL, -- time when the contract was deployed\n network_id character varying(64) NOT NULL, -- identifier of the network where the contract is deployed\n status character varying(32) NOT NULL, -- status of the contract (e.g., active, deprecated)\n PRIMARY KEY (contract_id)\n)\nCREATE TABLE web3.events (\n event_id character varying(64) NOT NULL, -- unique identifier for the event\n contract_id character varying(64) NOT NULL, -- identifier of the contract emitting the event\n event_name character varying(128) NOT NULL, -- name of the event\n data text NOT NULL, -- data payload of the event\n emitted_at timestamp NOT NULL, -- time when the event was emitted\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction that triggered the event\n log_index integer NOT NULL, -- index of the event log in the transaction\n PRIMARY KEY (event_id)\n)\nCREATE TABLE web3.transactions (\n transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n from_address character varying(128) NOT NULL, -- address of the sender\n to_address character varying(128), -- address of the receiver (can be null for contract deployment)\n value numeric(38,14) NOT NULL, -- value transferred\n gas_used integer NOT NULL, -- amount of gas used by the transaction\n gas_price numeric(38,14) NOT NULL, -- price of gas at the time of the transaction\n block_number integer NOT NULL, -- block number containing the transaction\n timestamp timestamp NOT NULL, -- time when the transaction was mined\n input_data text, -- input data of the transaction (can be null)\n status character varying(32) NOT NULL, -- status of the transaction (e.g., success, failed)\n nonce integer NOT NULL, -- nonce of the sender at the time of the transaction\n PRIMARY KEY (transaction_id)\n)\nCREATE TABLE web3.tokens (\n token_id character varying(64) NOT NULL, -- unique identifier for the token\n contract_address character varying(128) NOT NULL, -- address of the token contract\n token_name character varying(128) NOT NULL, -- name of the token\n token_symbol character varying(32) NOT NULL, -- symbol of the token\n decimals integer NOT NULL, -- number of decimals for the token\n total_supply numeric(38,14) NOT NULL, -- total supply of the token\n PRIMARY KEY (token_id)\n)\nCREATE TABLE web3.token_transfers (\n transfer_id character varying(64) NOT NULL, -- unique identifier for the transfer\n token_id character varying(64) NOT NULL, -- identifier of the token being transferred\n from_address character varying(128) NOT NULL, -- address of the sender\n to_address character varying(128) NOT NULL, -- address of the receiver\n value numeric(38,14) NOT NULL, -- amount of tokens transferred\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction containing the transfer\n log_index integer NOT NULL, -- index of the transfer log in the transaction\n PRIMARY KEY (transfer_id)\n)\nCREATE TABLE web3.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\n"} {"conversations": [{"role": "user", "content": "Find all pairs of contracts that were deployed on the same network. Show both contract IDs, the network ID, and the deployment timestamps for both contracts."}, {"role": "assistant", "content": "SELECT a.contract_id AS contract_id_1, b.contract_id AS contract_id_2, a.network_id, a.deployed_at AS deployed_at_1, b.deployed_at AS deployed_at_2\nFROM web3.contracts a\nJOIN web3.contracts b\n ON a.network_id = b.network_id AND a.contract_id < b.contract_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id character varying(64) NOT NULL, address character varying(128) NOT NULL, abi text NOT NULL, bytecode text NOT NULL, deployer_address character varying(128) NOT NULL, deployed_at timestamp NOT NULL, network_id character varying(64) NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (contract_id) )\n"} {"conversations": [{"role": "user", "content": "Count the number of users for each location where the location is not empty."}, {"role": "assistant", "content": "SELECT location, COUNT(user_id) FROM social_media.users WHERE location IS NOT NULL AND location != '' GROUP BY location;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified bool )\n"} {"conversations": [{"role": "user", "content": "Find all transactions where the from_address is the same as the to_address, indicating self-transactions, and show the transaction_id, value, and gas_used."}, {"role": "assistant", "content": "SELECT transaction_id, value, gas_used FROM web3.transactions WHERE from_address = to_address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.transactions ( transaction_id character varying(64) NOT NULL, from_address character varying(128) NOT NULL, to_address character varying(128), value numeric(38,14) NOT NULL, gas_used integer NOT NULL, gas_price numeric(38,14) NOT NULL, block_number integer NOT NULL, timestamp timestamp NOT NULL, input_data text, status character varying(32) NOT NULL, nonce integer NOT NULL, PRIMARY KEY (transaction_id) )\n"} {"conversations": [{"role": "user", "content": "What is the total number of unique manufacturers listed in the medications table?"}, {"role": "assistant", "content": "SELECT COUNT(DISTINCT manufacturer) FROM healthcare.medications;"}, {"role": "user", "content": "Could you also show the count of medications for each manufacturer, but only for those manufacturers who have less than 50 medications listed?"}, {"role": "assistant", "content": "SELECT manufacturer, COUNT(*) AS medication_count FROM healthcare.medications GROUP BY manufacturer HAVING COUNT(*) < 50;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.medications ( medication_id text PRIMARY KEY, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\n"} {"conversations": [{"role": "user", "content": "Show all rooms that are on floor 3."}, {"role": "assistant", "content": "SELECT room_id, property_id, room_number FROM hospitality_technology.rooms WHERE floor = 3;"}, {"role": "user", "content": "For these rooms, include the property name and room number."}, {"role": "assistant", "content": "SELECT r.room_number, p.property_name FROM hospitality_technology.rooms AS r JOIN hospitality_technology.properties AS p ON r.property_id = p.property_id WHERE r.floor = 3;"}, {"role": "user", "content": "Also, include the type name and current status for each room."}, {"role": "assistant", "content": "SELECT r.room_number, p.property_name, rt.type_name, r.status FROM hospitality_technology.rooms AS r JOIN hospitality_technology.properties AS p ON r.property_id = p.property_id JOIN hospitality_technology.room_types AS rt ON r.room_type_id = rt.room_type_id AND r.property_id = rt.property_id WHERE r.floor = 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.rooms ( room_id text, property_id text, room_number text, room_type_id text, floor integer, status text, is_smoking boolean, features text, current_condition text, last_cleaned_at timestamp )\nCREATE TABLE hospitality_technology.room_types ( room_type_id text, property_id text, type_name text, description text, base_rate numeric, max_occupancy integer, bed_type text, area_sqft numeric, amenities text )\n"} {"conversations": [{"role": "user", "content": "Show me the document name and the date worked for time entries logged by the same lawyer."}, {"role": "assistant", "content": "SELECT T1.document_name , T2.date_worked FROM documents AS T1 JOIN time_entries AS T2 ON T1.uploaded_by_lawyer_id = T2.lawyer_id"}, {"role": "user", "content": "Only show pairs where the time entry is billable."}, {"role": "assistant", "content": "SELECT T1.document_name , T2.date_worked FROM documents AS T1 JOIN time_entries AS T2 ON T1.uploaded_by_lawyer_id = T2.lawyer_id WHERE T2.is_billable = true"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.documents ( document_id text, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version integer, description text )\nCREATE TABLE legal_services.time_entries (\n entry_id character varying(64) NOT NULL, -- unique identifier for the time entry\n case_id character varying(64) NOT NULL, -- FK to cases table\n lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (who performed the work)\n date_worked date NOT NULL, -- date the work was performed\n hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), -- duration of work in hours (e.g., 1.5 for 1h 30m)\n billing_rate numeric(10, 2) NOT NULL, -- hourly rate applied for this entry\n description text NOT NULL, -- detailed description of the work performed\n is_billable boolean DEFAULT true, -- whether this time entry is billable to the client\n is_billed boolean DEFAULT false, -- whether this entry has been included in an invoice\n invoice_id character varying(64), -- FK to invoices table (once billed)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the entry was recorded\n PRIMARY KEY (entry_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me the user_id and number of conversations they have joined. Only include users who joined more than one conversation."}, {"role": "assistant", "content": "SELECT user_id, COUNT(DISTINCT conversation_id) AS conversations_joined\nFROM social_media.conversation_participants\nGROUP BY user_id\nHAVING COUNT(DISTINCT conversation_id) > 1;"}, {"role": "user", "content": "Add the time they joined their most recent conversation as latest_joined_at."}, {"role": "assistant", "content": "SELECT user_id, COUNT(DISTINCT conversation_id) AS conversations_joined, MAX(joined_at) AS latest_joined_at\nFROM social_media.conversation_participants\nGROUP BY user_id\nHAVING COUNT(DISTINCT conversation_id) > 1;"}, {"role": "user", "content": "Also, show the IDs of the conversations for each user as a comma-separated list."}, {"role": "assistant", "content": "SELECT user_id,\n COUNT(DISTINCT conversation_id) AS conversations_joined,\n MAX(joined_at) AS latest_joined_at,\n STRING_AGG(DISTINCT conversation_id, ',') AS conversation_ids\nFROM social_media.conversation_participants\nGROUP BY user_id\nHAVING COUNT(DISTINCT conversation_id) > 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text, post_id text, hashtag_id text )\nCREATE TABLE social_media.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Find all medical records where the vitals JSON field contains a blood pressure reading with systolic higher than 140, and show the patient_id, record_date, and vitals."}, {"role": "assistant", "content": "SELECT patient_id, record_date, vitals FROM healthcare.medical_records WHERE (vitals->>'blood_pressure_systolic')::integer > 140;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.medical_records (\n record_id character varying(64) NOT NULL, -- unique identifier for the medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n chief_complaint text, -- patient's primary reason for visit\n present_illness_history text, -- detailed history of the current issue\n past_medical_history text, -- relevant past conditions/surgeries\n physical_examination_notes text, -- findings from the physical exam\n assessment text, -- doctor's assessment/diagnosis summary\n treatment_plan text, -- planned course of action\n vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (record_id)\n)\n"} {"conversations": [{"role": "user", "content": "For each citizen who has made at least one payment, show the citizen's full name, number of payments, and total amount paid, grouped by currency."}, {"role": "assistant", "content": "SELECT\n c.first_name || ' ' || c.last_name AS full_name,\n p.currency,\n COUNT(*) AS payment_count,\n SUM(p.amount) AS total_amount\nFROM government_services.citizens c\nJOIN government_services.payments p ON c.citizen_id = p.citizen_id\nGROUP BY full_name, p.currency;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.payments ( payment_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, service_id character varying(64), amount numeric(12, 2) NOT NULL, currency character varying(3) NOT NULL DEFAULT 'USD', payment_method character varying(50), payment_provider_reference character varying(128), payment_timestamp timestamp NOT NULL, status character varying(30) NOT NULL, notes text, PRIMARY KEY (payment_id) )\nCREATE TABLE government_services.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_id) )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "Find all patients who have been prescribed medications with dosage greater than 50mg, along with their medication details and prescribing doctor's name."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name, p.last_name, pr.dosage, pr.medication_id, pr.start_date, doc.first_name AS doctor_first_name, doc.last_name AS doctor_last_name FROM healthcare.patients p JOIN healthcare.prescriptions pr ON p.patient_id = pr.patient_id JOIN healthcare.doctors doc ON pr.doctor_id = doc.doctor_id WHERE CAST(SUBSTRING_INDEX(pr.dosage, 'mg', 1) AS UNSIGNED) > 50;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id.text, first_name.text, last_name.text, date_of_birth.date, gender.text, address.text, phone_number.text, email.text, emergency_contact_name.text, emergency_contact_phone.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id.text, record_id.text, patient_id.text, doctor_id.text, diagnosis_code.text, code_type.text, description.text, diagnosis_date.date, status.text, is_chronic.boolean )\nCREATE TABLE healthcare.prescriptions ( prescription_id.text, record_id.text, patient_id.text, doctor_id.text, medication_id.text, dosage.text, frequency.text, route.text, start_date.date, end_date.date, quantity_dispensed.numeric, refills_allowed.integer, prescription_date.timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\n"} {"conversations": [{"role": "user", "content": "List the username and email of users whose first wallet creation date is the same day as their user registration date."}, {"role": "assistant", "content": "SELECT u.username, u.email FROM web3.users u JOIN (SELECT user_id, MIN(created_at) as first_wallet_created_at FROM web3.wallets GROUP BY user_id) w ON u.user_id = w.user_id WHERE DATE(u.created_at) = DATE(w.first_wallet_created_at);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.events (\n event_id character varying(64) NOT NULL, -- unique identifier for the event\n contract_id character varying(64) NOT NULL, -- identifier of the contract emitting the event\n event_name character varying(128) NOT NULL, -- name of the event\n data text NOT NULL, -- data payload of the event\n emitted_at timestamp NOT NULL, -- time when the event was emitted\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction that triggered the event\n log_index integer NOT NULL, -- index of the event log in the transaction\n PRIMARY KEY (event_id)\n)\nCREATE TABLE web3.tokens (\n token_id character varying(64) NOT NULL, -- unique identifier for the token\n contract_address character varying(128) NOT NULL, -- address of the token contract\n token_name character varying(128) NOT NULL, -- name of the token\n token_symbol character varying(32) NOT NULL, -- symbol of the token\n decimals integer NOT NULL, -- number of decimals for the token\n total_supply numeric(38,14) NOT NULL, -- total supply of the token\n PRIMARY KEY (token_id)\n)\nCREATE TABLE web3.wallets (\n wallet_id character varying(64) NOT NULL, -- unique identifier for the wallet\n user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n address character varying(128) NOT NULL, -- address of the wallet\n private_key text NOT NULL, -- private key of the wallet\n created_at timestamp NOT NULL, -- time when the wallet was created\n PRIMARY KEY (wallet_id)\n)\nCREATE TABLE web3.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\n"} {"conversations": [{"role": "user", "content": "List pairs of distinct routes that originate from the same location but go to different destinations. Show the route ID and route number for both routes and the common origin location ID."}, {"role": "assistant", "content": "SELECT\n r1.route_id AS route1_id,\n r1.route_number AS route1_number,\n r2.route_id AS route2_id,\n r2.route_number AS route2_number,\n r1.origin_location_id AS shared_origin_location_id\nFROM transportation.routes AS r1\nJOIN transportation.routes AS r2\n ON r1.origin_location_id = r2.origin_location_id\n AND r1.route_id < r2.route_id\nWHERE\n r1.destination_location_id != r2.destination_location_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.routes ( route_id text, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes integer, type text )\n"} {"conversations": [{"role": "user", "content": "How many unique patient records are there for each gender?"}, {"role": "assistant", "content": "SELECT gender, COUNT(DISTINCT patient_id) AS patient_count FROM healthcare.patients GROUP BY gender;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id.text, first_name.text, last_name.text, date_of_birth.date, gender.text, address.text, phone_number.text, email.text, emergency_contact_name.text, emergency_contact_phone.text, created_at.timestamp, updated_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "Find all pairs of transactions that occurred in the same block and were sent to the same address. Show both transaction IDs, the shared recipient address, and the block number."}, {"role": "assistant", "content": "SELECT t1.transaction_id AS tx1,\n t2.transaction_id AS tx2,\n t1.to_address,\n t1.block_number\nFROM transactions t1\nJOIN transactions t2\n ON t1.to_address = t2.to_address\n AND t1.block_number = t2.block_number\n AND t1.transaction_id < t2.transaction_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.transactions ( transaction_id text, from_address text, to_address text, value numeric, gas_used integer, gas_price numeric, block_number integer, timestamp timestamp, input_data text, status text, nonce integer )\n"} {"conversations": [{"role": "user", "content": "Show a list of all fuel refueling events for each trip, including the trip ID, fuel type, quantity, total cost, and the name of the refueling location."}, {"role": "assistant", "content": "SELECT fl.trip_id, fl.fuel_type, fl.quantity, fl.total_cost, l.name AS location_name\nFROM transportation.fuel_logs fl\nJOIN transportation.locations l ON fl.location_id = l.location_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text, license_plate text, vin text, make text, model text, year integer, type text, capacity integer, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id text, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes integer, type text )\nCREATE TABLE transportation.trips ( trip_id text, route_id text, vehicle_id text, driver_id text, scheduled_departure timestamp, actual_departure timestamp, scheduled_arrival timestamp, actual_arrival timestamp, origin_location_id text, destination_location_id text, status text, passenger_count integer, cargo_manifest_id text )\nCREATE TABLE transportation.locations ( location_id text, name text, type text, address_line1 text, city text, state_province text, postal_code text, country text, latitude numeric, longitude numeric, timezone text )\nCREATE TABLE transportation.maintenance_logs ( log_id text, vehicle_id text, service_date date, odometer_reading integer, service_type text, description text, cost numeric, mechanic_name text, next_service_due_date date )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id text, vehicle_id text, trip_id text, log_timestamp timestamp, fuel_type text, quantity numeric, unit text, cost_per_unit numeric, total_cost numeric, odometer_reading integer, location_id text )\nCREATE TABLE transportation.passengers ( passenger_id text, first_name text, last_name text, email text, phone_number text, date_of_birth date, loyalty_program_id text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me the usernames along with the names of group chats they are participating in and the dates they joined each group."}, {"role": "assistant", "content": "SELECT u.username, c.group_name, cp.joined_at\nFROM social_media.conversation_participants cp\nJOIN social_media.users u ON cp.user_id = u.user_id\nJOIN social_media.conversations c ON cp.conversation_id = c.conversation_id\nWHERE c.is_group_chat = TRUE;"}, {"role": "user", "content": "Only display records where the user joined after January 1, 2024."}, {"role": "assistant", "content": "SELECT u.username, c.group_name, cp.joined_at\nFROM social_media.conversation_participants cp\nJOIN social_media.users u ON cp.user_id = u.user_id\nJOIN social_media.conversations c ON cp.conversation_id = c.conversation_id\nWHERE c.is_group_chat = TRUE\nAND cp.joined_at > '2024-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.comments ( comment_id text, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.likes ( like_id text, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.follows ( follow_id text, follower_user_id text, following_user_id text, created_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id text, tag_name text, created_at timestamp )\nCREATE TABLE social_media.messages ( message_id text, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id text, created_at timestamp, last_message_at timestamp, is_group_chat boolean, group_name text )\nCREATE TABLE social_media.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.user_settings ( setting_id text, user_id text, theme text, email_notifications_enabled boolean, push_notifications_enabled boolean, private_profile boolean, updated_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me the service name, category, and price for all services that are currently not available."}, {"role": "assistant", "content": "SELECT service_name, category, price FROM hospitality_technology.services WHERE is_available = FALSE;"}, {"role": "user", "content": "Filter this list further to only include services from the 'Transportation' department that are not available."}, {"role": "assistant", "content": "SELECT service_name, category, price FROM hospitality_technology.services WHERE is_available = FALSE AND department = 'Transportation';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.services ( service_id.text, property_id.text, service_name.text, description.text, category.text, price.numeric, unit.text, is_available.boolean, department.text )\n"} {"conversations": [{"role": "user", "content": "Show me all insurance plans that have more than 5 patients enrolled as their primary insurance, along with the provider name and count of patients."}, {"role": "assistant", "content": "SELECT ip.plan_id, ip.plan_name, ip.insurance_provider, COUNT(pi.patient_id) AS patient_count FROM healthcare.insurance_plans ip JOIN healthcare.patient_insurance pi ON ip.plan_id = pi.plan_id WHERE pi.is_primary = true GROUP BY ip.plan_id, ip.plan_name, ip.insurance_provider HAVING COUNT(pi.patient_id) > 5 ORDER BY patient_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.doctors ( doctor_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, specialty character varying(100) NOT NULL, license_number character varying(50) UNIQUE NOT NULL, phone_number character varying(20), email character varying(128) UNIQUE, hospital_affiliation_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (doctor_id) )\nCREATE TABLE healthcare.appointments ( appointment_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, appointment_time timestamp with time zone NOT NULL, duration_minutes integer NOT NULL, reason text, status character varying(32) NOT NULL, location_id character varying(64), notes text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (appointment_id) )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, diagnosis_code character varying(20) NOT NULL, code_type character varying(10) NOT NULL DEFAULT 'ICD-10', description text, diagnosis_date date NOT NULL, status character varying(32) NOT NULL, is_chronic boolean DEFAULT false, PRIMARY KEY (diagnosis_id) )\nCREATE TABLE healthcare.medications ( medication_id character varying(64) NOT NULL, medication_name character varying(255) NOT NULL, generic_name character varying(255), manufacturer character varying(100), ndc_code character varying(20) UNIQUE, description text, PRIMARY KEY (medication_id) )\nCREATE TABLE healthcare.prescriptions ( prescription_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, medication_id character varying(64) NOT NULL, dosage character varying(100) NOT NULL, frequency character varying(100) NOT NULL, route character varying(50), start_date date NOT NULL, end_date date, quantity_dispensed numeric(10,2), refills_allowed integer NOT NULL DEFAULT 0, prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (prescription_id) )\nCREATE TABLE healthcare.insurance_plans ( plan_id character varying(64) NOT NULL, plan_name character varying(200) NOT NULL, insurance_provider character varying(100) NOT NULL, plan_type character varying(50), contact_phone character varying(20), website character varying(255), PRIMARY KEY (plan_id) )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n"} {"conversations": [{"role": "user", "content": "Find documents that have the same document_name but are associated with different cases. Show the document name and the two different case IDs."}, {"role": "assistant", "content": "SELECT d1.document_name, d1.case_id AS case_id_1, d2.case_id AS case_id_2 FROM legal_services.documents AS d1 JOIN legal_services.documents AS d2 ON d1.document_name = d2.document_name WHERE d1.case_id <> d2.case_id AND d1.document_id < d2.document_id;"}, {"role": "user", "content": "Actually, only show pairs where at least one of the documents is of document_type 'Contract'."}, {"role": "assistant", "content": "SELECT d1.document_name, d1.case_id AS case_id_1, d2.case_id AS case_id_2 FROM legal_services.documents AS d1 JOIN legal_services.documents AS d2 ON d1.document_name = d2.document_name WHERE d1.case_id <> d2.case_id AND d1.document_id < d2.document_id AND (d1.document_type = 'Contract' OR d2.document_type = 'Contract');"}, {"role": "user", "content": "Also, only include pairs where both documents were uploaded in the year 2024."}, {"role": "assistant", "content": "SELECT d1.document_name, d1.case_id AS case_id_1, d2.case_id AS case_id_2 FROM legal_services.documents AS d1 JOIN legal_services.documents AS d2 ON d1.document_name = d2.document_name WHERE d1.case_id <> d2.case_id AND d1.document_id < d2.document_id AND (d1.document_type = 'Contract' OR d2.document_type = 'Contract') AND YEAR(d1.upload_timestamp) = 2024 AND YEAR(d2.upload_timestamp) = 2024;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.documents ( document_id.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\n"} {"conversations": [{"role": "user", "content": "Show me the names of law firms founded after 2010, along with the full name of their managing partner."}, {"role": "assistant", "content": "SELECT f.firm_name, l.first_name, l.last_name FROM legal_services.law_firms AS f JOIN legal_services.lawyers AS l ON f.managing_partner_id = l.lawyer_id WHERE f.founded_date > '2010-12-31';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers (\n lawyer_id character varying(64) NOT NULL, -- unique identifier for the lawyer\n first_name character varying(100) NOT NULL, -- lawyer's first name\n last_name character varying(100) NOT NULL, -- lawyer's last name\n bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n firm_id character varying(64), -- FK to law_firms table\n email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n phone character varying(32), -- lawyer's contact phone number\n specialization text, -- areas of legal expertise\n hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n PRIMARY KEY (lawyer_id)\n)\n"} {"conversations": [{"role": "user", "content": "For each transaction status, what is the average transaction value?"}, {"role": "assistant", "content": "SELECT status, AVG(value) FROM web3.transactions GROUP BY status"}, {"role": "user", "content": "Could you filter this to only show statuses where the average value is greater than 100?"}, {"role": "assistant", "content": "SELECT status, AVG(value) FROM web3.transactions GROUP BY status HAVING AVG(value) > 100"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts (\n contract_id character varying(64) NOT NULL, -- unique identifier for the contract\n address character varying(128) NOT NULL, -- address of the deployed contract\n abi text NOT NULL, -- application binary interface of the contract\n bytecode text NOT NULL, -- bytecode of the contract\n deployer_address character varying(128) NOT NULL, -- address of the deployer\n deployed_at timestamp NOT NULL, -- time when the contract was deployed\n network_id character varying(64) NOT NULL, -- identifier of the network where the contract is deployed\n status character varying(32) NOT NULL, -- status of the contract (e.g., active, deprecated)\n PRIMARY KEY (contract_id)\n)\nCREATE TABLE web3.transactions (\n transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n from_address character varying(128) NOT NULL, -- address of the sender\n to_address character varying(128), -- address of the receiver (can be null for contract deployment)\n value numeric(38,14) NOT NULL, -- value transferred\n gas_used integer NOT NULL, -- amount of gas used by the transaction\n gas_price numeric(38,14) NOT NULL, -- price of gas at the time of the transaction\n block_number integer NOT NULL, -- block number containing the transaction\n timestamp timestamp NOT NULL, -- time when the transaction was mined\n input_data text, -- input data of the transaction (can be null)\n status character varying(32) NOT NULL, -- status of the transaction (e.g., success, failed)\n nonce integer NOT NULL, -- nonce of the sender at the time of the transaction\n PRIMARY KEY (transaction_id)\n)\nCREATE TABLE web3.tokens (\n token_id character varying(64) NOT NULL, -- unique identifier for the token\n contract_address character varying(128) NOT NULL, -- address of the token contract\n token_name character varying(128) NOT NULL, -- name of the token\n token_symbol character varying(32) NOT NULL, -- symbol of the token\n decimals integer NOT NULL, -- number of decimals for the token\n total_supply numeric(38,14) NOT NULL, -- total supply of the token\n PRIMARY KEY (token_id)\n)\nCREATE TABLE web3.token_transfers (\n transfer_id character varying(64) NOT NULL, -- unique identifier for the transfer\n token_id character varying(64) NOT NULL, -- identifier of the token being transferred\n from_address character varying(128) NOT NULL, -- address of the sender\n to_address character varying(128) NOT NULL, -- address of the receiver\n value numeric(38,14) NOT NULL, -- amount of tokens transferred\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction containing the transfer\n log_index integer NOT NULL, -- index of the transfer log in the transaction\n PRIMARY KEY (transfer_id)\n)\n"} {"conversations": [{"role": "user", "content": "What is the maintenance schedule for the platforms at the station with ID 'ST234' for the next month?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to the maintenance schedule for the platforms at any station. The data I have only includes basic station information such as station ID, name, location, and number of platforms. For maintenance schedules, you may need to contact the station management or relevant authorities."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.stations ( station_id text PRIMARY KEY, station_name text, city text, state_province text, country_code text, address text, timezone text, number_of_platforms int, created_at timestamp, last_updated_at timestamp )\n"} {"conversations": [{"role": "user", "content": "For each prescription, find the next prescription for the same patient. Return current prescription_id, next_prescription_id, patient_id, and days between start dates."}, {"role": "assistant", "content": "SELECT p1.patient_id,\n p1.prescription_id AS current_id,\n p2.prescription_id AS next_id,\n (p2.start_date - p1.start_date) AS days_between\nFROM healthcare.prescriptions p1\nJOIN healthcare.prescriptions p2\n ON p1.patient_id = p2.patient_id\n AND p2.start_date = (\n SELECT MIN(start_date)\n FROM healthcare.prescriptions p3\n WHERE p3.patient_id = p1.patient_id\n AND p3.start_date > p1.start_date\n );"}, {"role": "user", "content": "Only include pairs where days_between is less than 30 days."}, {"role": "assistant", "content": "SELECT p1.patient_id,\n p1.prescription_id AS current_id,\n p2.prescription_id AS next_id,\n (p2.start_date - p1.start_date) AS days_between\nFROM healthcare.prescriptions p1\nJOIN healthcare.prescriptions p2\n ON p1.patient_id = p2.patient_id\n AND p2.start_date = (\n SELECT MIN(start_date)\n FROM healthcare.prescriptions p3\n WHERE p3.patient_id = p1.patient_id\n AND p3.start_date > p1.start_date\n )\nWHERE (p2.start_date - p1.start_date) < 30;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.prescriptions ( prescription_id.text, record_id.text, patient_id.text, doctor_id.text, medication_id.text, dosage.text, frequency.text, route.text, start_date.date, end_date.date, quantity_dispensed.numeric, refills_allowed.integer, prescription_date.timestamp )\n"} {"conversations": [{"role": "user", "content": "For each booking, show the booking_id, seat_number, fare, and the city of the origin location for the trip that was booked."}, {"role": "assistant", "content": "SELECT b.booking_id, b.seat_number, b.fare, orig.city AS origin_city\nFROM transportation.bookings b\nJOIN transportation.trips t ON b.trip_id = t.trip_id\nJOIN transportation.routes r ON t.route_id = r.route_id\nJOIN transportation.locations orig ON r.origin_location_id = orig.location_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.drivers ( driver_id character varying(64) NOT NULL, employee_id character varying(64) NOT NULL UNIQUE, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, license_number character varying(64) NOT NULL UNIQUE, license_expiry_date date NOT NULL, contact_number character varying(32), email character varying(128) UNIQUE, hire_date date NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (driver_id) )\nCREATE TABLE transportation.routes ( route_id character varying(64) NOT NULL, route_number character varying(32) NOT NULL UNIQUE, description text, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, distance_km numeric(10, 2), estimated_duration_minutes integer, type character varying(32) NOT NULL, PRIMARY KEY (route_id) )\nCREATE TABLE transportation.locations ( location_id character varying(64) NOT NULL, name character varying(255) NOT NULL, type character varying(64) NOT NULL, address_line1 character varying(255), city character varying(128), state_province character varying(128), postal_code character varying(32), country character varying(64) NOT NULL, latitude numeric(9, 6), longitude numeric(9, 6), timezone character varying(64), PRIMARY KEY (location_id) )\nCREATE TABLE transportation.maintenance_logs ( log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, service_date date NOT NULL, odometer_reading integer, service_type character varying(128) NOT NULL, description text NOT NULL, cost numeric(10, 2), mechanic_name character varying(128), next_service_due_date date, PRIMARY KEY (log_id) )\nCREATE TABLE transportation.bookings ( booking_id character varying(64) NOT NULL, passenger_id character varying(64) NOT NULL, trip_id character varying(64) NOT NULL, seat_number character varying(16), booking_time timestamp with time zone NOT NULL, status character varying(32) NOT NULL, fare numeric(10, 2) NOT NULL, payment_transaction_id character varying(128), special_requests text, PRIMARY KEY (booking_id) )\n"} {"conversations": [{"role": "user", "content": "Which projects raised funds in January 2022?"}, {"role": "assistant", "content": "SELECT project_name, rounds_name, investment_value, investment_date FROM project_fundraising_record WHERE investment_date >= '2022-01-01' AND investment_date < '2022-02-01';"}, {"role": "user", "content": "Please also show their introductions."}, {"role": "assistant", "content": "SELECT project_name, rounds_name, investment_value, investment_date, introduction FROM project_fundraising_record WHERE investment_date >= '2022-01-01' AND investment_date < '2022-02-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id.text, project_id.text, project_name.text, rounds_name.text, investment_value.numeric, investment_date.text, introduction.text, valuation.numeric )\n"} {"conversations": [{"role": "user", "content": "Now, sort the results by the date opened, oldest first, and show only the top 10."}, {"role": "assistant", "content": "SELECT case_name, case_number, date_opened FROM legal_services.cases WHERE lead_lawyer_id = 'lawyer_abc' AND status = 'Open' AND case_type = 'Criminal' ORDER BY date_opened ASC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.cases ( case_id.text, case_number.text, case_name.text, client_id.text, lead_lawyer_id.text, case_type.text, status.text, date_opened.timestamp, date_closed.timestamp, description.text, court_jurisdiction.text )\n"} {"conversations": [{"role": "user", "content": "What are the specific tools or equipment used during the maintenance with record_id 'REC456'?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about the specific tools or equipment used during a maintenance record. The data in the maintenance_records table does not include details about tools or equipment used."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.maintenance_records ( record_id text PRIMARY KEY, asset_id text, asset_type text, maintenance_type text, staff_id text, start_datetime timestamp, end_datetime timestamp, description text, cost numeric, status text )\n"} {"conversations": [{"role": "user", "content": "Find currently employed employees whose direct manager has been terminated. Display the employee's full name, hire date, manager's full name, and manager's termination date."}, {"role": "assistant", "content": "SELECT e.employee_id,\n CONCAT(e.first_name, ' ', e.last_name) AS employee_full_name,\n e.hire_date,\n CONCAT(m.first_name, ' ', m.last_name) AS manager_full_name,\n m.termination_date\nFROM government_services.employees e\nJOIN government_services.employees m ON e.manager_employee_id = m.employee_id\nWHERE e.termination_date IS NULL\n AND m.termination_date IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees (\n employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n job_title character varying(150) NOT NULL,\n department character varying(100),\n work_email character varying(128) NOT NULL UNIQUE,\n work_phone character varying(32),\n hire_date date NOT NULL,\n termination_date date, -- null if currently employed\n access_level character varying(50), -- Role or permission level\n manager_employee_id character varying(64), -- FK to self for reporting structure\n PRIMARY KEY (employee_id)\n)\nCREATE TABLE government_services.service_locations ( location_id text PRIMARY KEY, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "Find all pairs of users where the registration times are within 30 minutes of each other, and show both user IDs, usernames, and the time difference in minutes."}, {"role": "assistant", "content": "SELECT u1.user_id AS user1_id, u1.username AS user1_name, u2.user_id AS user2_id, u2.username AS user2_name, ROUND(ABS(EXTRACT(EPOCH FROM u1.created_at - u2.created_at))/60,2) AS diff_minutes FROM web3.users u1 JOIN web3.users u2 ON u1.user_id < u2.user_id WHERE ABS(EXTRACT(EPOCH FROM u1.created_at - u2.created_at))/60 <= 30;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.users ( user_id.text, username.text, email.text, password_hash.text, created_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "List each appointment with appointment ID, appointment time, doctor's last name, and the patient's primary insurance plan name."}, {"role": "assistant", "content": "SELECT a.appointment_id,\n a.appointment_time,\n d.last_name AS doctor_last_name,\n p.plan_name\nFROM healthcare.appointments a\nJOIN healthcare.doctors d ON a.doctor_id = d.doctor_id\nJOIN healthcare.patient_insurance pi ON a.patient_id = pi.patient_id AND pi.is_primary = true\nJOIN healthcare.insurance_plans p ON pi.plan_id = p.plan_id;"}, {"role": "user", "content": "Filter to only show appointments with status 'Completed' in the year 2024."}, {"role": "assistant", "content": "SELECT a.appointment_id,\n a.appointment_time,\n d.last_name AS doctor_last_name,\n p.plan_name\nFROM healthcare.appointments a\nJOIN healthcare.doctors d ON a.doctor_id = d.doctor_id\nJOIN healthcare.patient_insurance pi ON a.patient_id = pi.patient_id AND pi.is_primary = true\nJOIN healthcare.insurance_plans p ON pi.plan_id = p.plan_id\nWHERE a.status = 'Completed'\n AND a.appointment_time >= '2024-01-01'\n AND a.appointment_time < '2025-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.doctors ( doctor_id text PRIMARY KEY, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table\n appointment_time timestamp with time zone NOT NULL, -- date and time of the appointment\n duration_minutes integer NOT NULL, -- expected duration in minutes\n reason text, -- reason for the visit\n status character varying(32) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-show\n location_id character varying(64), -- FK to a potential locations/clinics table\n notes text, -- notes related to scheduling\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (appointment_id)\n)\nCREATE TABLE healthcare.medical_records ( record_id.text, patient_id.text, appointment_id.text, doctor_id.text, record_date.timestamp, chief_complaint.text, present_illness_history.text, past_medical_history.text, physical_examination_notes.text, assessment.text, treatment_plan.text, vitals.json, created_at.timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\nCREATE TABLE healthcare.patient_insurance (\n patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n patient_id character varying(64) NOT NULL, -- FK to patients table\n plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n policy_number character varying(100) NOT NULL, -- patient's policy number\n group_number character varying(100), -- group number, if applicable\n subscriber_name character varying(200), -- name of the primary policy holder\n effective_date date NOT NULL, -- date the coverage begins\n expiration_date date, -- date the coverage ends (if known)\n is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n PRIMARY KEY (patient_insurance_id),\n UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"} {"conversations": [{"role": "user", "content": "List all invoices where amount_paid is less than total_amount."}, {"role": "assistant", "content": "SELECT *\nFROM legal_services.invoices\nWHERE amount_paid < total_amount;"}, {"role": "user", "content": "Only include those with due_date before today."}, {"role": "assistant", "content": "SELECT *\nFROM legal_services.invoices\nWHERE amount_paid < total_amount\n AND due_date < CURRENT_DATE;"}, {"role": "user", "content": "Now also compute how many days each invoice is overdue as difference between CURRENT_DATE and due_date, and only show those overdue by more than 30 days."}, {"role": "assistant", "content": "SELECT invoice_id,\n invoice_number,\n client_id,\n total_amount,\n amount_paid,\n due_date,\n CURRENT_DATE - due_date AS days_overdue\nFROM legal_services.invoices\nWHERE amount_paid < total_amount\n AND due_date < CURRENT_DATE\n AND CURRENT_DATE - due_date > 30;"}, {"role": "user", "content": "Finally, order the result by days_overdue descending."}, {"role": "assistant", "content": "SELECT invoice_id,\n invoice_number,\n client_id,\n total_amount,\n amount_paid,\n due_date,\n CURRENT_DATE - due_date AS days_overdue\nFROM legal_services.invoices\nWHERE amount_paid < total_amount\n AND due_date < CURRENT_DATE\n AND CURRENT_DATE - due_date > 30\nORDER BY days_overdue DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.invoices ( invoice_id.text, invoice_number.text, client_id.text, case_id.text, issue_date.date, due_date.date, total_amount.numeric, amount_paid.numeric, status.text, payment_date.timestamp, notes.text, created_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "List each lawyer's full name with the full name of the partner at the same firm."}, {"role": "assistant", "content": "SELECT l.lawyer_id,\n CONCAT(l.first_name, ' ', l.last_name) AS lawyer_name,\n CONCAT(p.first_name, ' ', p.last_name) AS partner_name\nFROM legal_services.lawyers l\nJOIN legal_services.lawyers p\n ON l.firm_id = p.firm_id\n AND p.is_partner = true;"}, {"role": "user", "content": "Actually, I only want those lawyers whose specialization includes 'Corporate Law'. Could you update the query?"}, {"role": "assistant", "content": "SELECT l.lawyer_id,\n CONCAT(l.first_name, ' ', l.last_name) AS lawyer_name,\n CONCAT(p.first_name, ' ', p.last_name) AS partner_name\nFROM legal_services.lawyers l\nJOIN legal_services.lawyers p\n ON l.firm_id = p.firm_id\n AND p.is_partner = true\nWHERE l.specialization ILIKE '%Corporate Law%';"}, {"role": "user", "content": "Also only show those who were hired after 2020-01-01."}, {"role": "assistant", "content": "SELECT l.lawyer_id,\n CONCAT(l.first_name, ' ', l.last_name) AS lawyer_name,\n CONCAT(p.first_name, ' ', p.last_name) AS partner_name\nFROM legal_services.lawyers l\nJOIN legal_services.lawyers p\n ON l.firm_id = p.firm_id\n AND p.is_partner = true\nWHERE l.specialization ILIKE '%Corporate Law%'\n AND l.hire_date > '2020-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers (\n lawyer_id character varying(64) NOT NULL, -- unique identifier for the lawyer\n first_name character varying(100) NOT NULL, -- lawyer's first name\n last_name character varying(100) NOT NULL, -- lawyer's last name\n bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n firm_id character varying(64), -- FK to law_firms table\n email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n phone character varying(32), -- lawyer's contact phone number\n specialization text, -- areas of legal expertise\n hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n PRIMARY KEY (lawyer_id)\n)\n"} {"conversations": [{"role": "user", "content": "List the names of services for which documents are set to expire in the next 90 days."}, {"role": "assistant", "content": "SELECT DISTINCT T1.service_name FROM government_services.services AS T1 JOIN applications AS T2 ON T1.service_id = T2.service_id JOIN government_services.documents AS T3 ON T2.application_id = T3.application_id WHERE T3.expiry_date IS NOT NULL AND T3.expiry_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '90 days'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.services ( service_id text PRIMARY KEY, agency_id text, service_name text, description text, category text, eligibility_criteria text, standard_fee numeric, average_processing_time_days int, is_active boolean, online_application_url text )\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\n"} {"conversations": [{"role": "user", "content": "For each group chat, can you show me each participant's username and the date they joined the chat?"}, {"role": "assistant", "content": "SELECT u.username, c.group_name, cp.joined_at\nFROM social_media.conversation_participants cp\nJOIN social_media.users u ON cp.user_id = u.user_id\nJOIN social_media.conversations c ON cp.conversation_id = c.conversation_id\nWHERE c.is_group_chat = true;"}, {"role": "user", "content": "Can you also include the total number of participants for each group chat in the result?"}, {"role": "assistant", "content": "SELECT u.username, c.group_name, cp.joined_at, COUNT(cp2.participant_id) AS total_participants\nFROM social_media.conversation_participants cp\nJOIN social_media.users u ON cp.user_id = u.user_id\nJOIN social_media.conversations c ON cp.conversation_id = c.conversation_id\nJOIN social_media.conversation_participants cp2 ON cp2.conversation_id = cp.conversation_id\nWHERE c.is_group_chat = true\nGROUP BY u.username, c.group_name, cp.joined_at;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.comments ( comment_id text, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.follows ( follow_id text, follower_user_id text, following_user_id text, created_at timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text, post_id text, hashtag_id text )\nCREATE TABLE social_media.messages ( message_id text, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\nCREATE TABLE social_media.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications ( notification_id text, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\nCREATE TABLE social_media.user_settings ( setting_id text, user_id text, theme text, email_notifications_enabled boolean, push_notifications_enabled boolean, private_profile boolean, updated_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Give me the total number of reservations and the sum of total_amount by month for the year 2023."}, {"role": "assistant", "content": "SELECT DATE_TRUNC('month', check_in_date) AS month,\n COUNT(*) AS reservation_count,\n SUM(total_amount) AS total_revenue\nFROM hospitality_technology.reservations\nWHERE EXTRACT(YEAR FROM check_in_date) = 2023\nGROUP BY DATE_TRUNC('month', check_in_date)\nORDER BY month;"}, {"role": "user", "content": "Actually, I only want reservations with status 'CheckedOut' or 'Completed'."}, {"role": "assistant", "content": "SELECT DATE_TRUNC('month', check_in_date) AS month,\n COUNT(*) AS reservation_count,\n SUM(total_amount) AS total_revenue\nFROM hospitality_technology.reservations\nWHERE EXTRACT(YEAR FROM check_in_date) = 2023\n AND status IN ('CheckedOut', 'Completed')\nGROUP BY DATE_TRUNC('month', check_in_date)\nORDER BY month;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.reservations ( reservation_id text PRIMARY KEY, property_id text, guest_id text, room_id text, room_type_id text, check_in_date date, check_out_date date, actual_check_in_ts timestamp, actual_check_out_ts timestamp, num_adults int, num_children int, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Get all non-smoking rooms with status 'Available'."}, {"role": "assistant", "content": "SELECT room_id, property_id, room_number, floor\nFROM hospitality_technology.rooms\nWHERE is_smoking = FALSE\n AND status = 'Available';"}, {"role": "user", "content": "Now include the property_name for each room."}, {"role": "assistant", "content": "SELECT r.room_id, r.room_number, p.property_name, r.floor\nFROM hospitality_technology.rooms r\nJOIN hospitality_technology.properties p\n ON r.property_id = p.property_id\nWHERE r.is_smoking = FALSE\n AND r.status = 'Available';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text PRIMARY KEY, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.rooms ( room_id text PRIMARY KEY, property_id text, room_number text, room_type_id text, floor int, status text, is_smoking boolean, features text, current_condition text, last_cleaned_at timestamp )\n"} {"conversations": [{"role": "user", "content": "List all ERC20 tokens where the price is between $1 and $10, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price BETWEEN 1 AND 10;"}, {"role": "user", "content": "I think there's an error in your query - it should be joining with token_prices_latest on address not contract_address. Also, can you add the current price to the results?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price BETWEEN 1 AND 10;"}, {"role": "user", "content": "Now filter these results to only show tokens with decimals equal to 18 and sort by name alphabetically."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price BETWEEN 1 AND 10 AND tm.decimals = 18 ORDER BY tm.name ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash text, transaction_index bigint, from_address text, contract_address text, symbol text, total_supply text, name text, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info text, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address text, wallet_address text, amount text, pk text )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk text )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk integer )\nCREATE TABLE sui_coins ( object_id text, status text, coin_type text, balance text, owner text )\nCREATE TABLE sui_coins_metadata ( object_id text, coin_type text, status text, decimals bigint, description text, icon_url text, symbol text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain text, contract_address text, name text, symbol text, deploy_block_number bigint, deploy_block_time bigint, erc_type text, owner text, traits text, description text, slug text, media_info text, image_url text, banner_image_url text, updated_at bigint, banner text, token_count bigint, floor_price text, floor_price_symbol text, floor_price_contract text, pk integer )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest ( blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply text, amount text )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"} {"conversations": [{"role": "user", "content": "What is the fuel efficiency of the train car with car_id 'TC456'?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to information about the fuel efficiency of specific train cars. The data available in the train_cars table only includes details such as car_id, train_id, car_number, car_type, class, capacity, and features. If you have another question or need assistance with something else, I'm happy to help."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.train_cars ( car_id.text, train_id.text, car_number.text, car_type.text, class.text, capacity.integer, features.text )\n"} {"conversations": [{"role": "user", "content": "Show me the record_id, patient_id, prescription_id, medication_id, start_date, and the systolic blood pressure from the associated medical record for all prescriptions."}, {"role": "assistant", "content": "SELECT p.prescription_id,\n p.medication_id,\n p.start_date,\n m.record_id,\n m.patient_id,\n (m.vitals->'blood_pressure'->>'systolic')::int AS systolic_bp\nFROM healthcare.prescriptions p\nJOIN healthcare.medical_records m\n ON p.record_id = m.record_id;"}, {"role": "user", "content": "Actually, only include those where the systolic blood pressure is greater than 140."}, {"role": "assistant", "content": "SELECT p.prescription_id,\n p.medication_id,\n p.start_date,\n m.record_id,\n m.patient_id,\n (m.vitals->'blood_pressure'->>'systolic')::int AS systolic_bp\nFROM healthcare.prescriptions p\nJOIN healthcare.medical_records m\n ON p.record_id = m.record_id\nWHERE (m.vitals->'blood_pressure'->>'systolic')::int > 140;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.medical_records ( record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, appointment_id character varying(64) UNIQUE, doctor_id character varying(64) NOT NULL, record_date timestamp with time zone NOT NULL, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals jsonb, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (record_id) )\nCREATE TABLE healthcare.prescriptions ( prescription_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, medication_id character varying(64) NOT NULL, dosage character varying(100) NOT NULL, frequency character varying(100) NOT NULL, route character varying(50), start_date date NOT NULL, end_date date, quantity_dispensed numeric(10,2), refills_allowed integer NOT NULL DEFAULT 0, prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (prescription_id) )\n"} {"conversations": [{"role": "user", "content": "What is the current salary of employee with ID 'EMP123'?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about an employee's salary as it is not included in the data available in the 'employees' table."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.employees (\n employee_id character varying(64) NOT NULL, -- unique identifier for the employee\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n job_title character varying(128) NOT NULL, -- e.g., 'Aircraft Mechanic', 'Quality Inspector', 'Assembly Technician'\n skill_certifications text, -- comma-separated list or JSON of certifications\n hire_date date NOT NULL,\n assigned_line_id character varying(64), -- FK to the assembly line the employee is currently assigned to (can be null)\n employment_status character varying(50) NOT NULL, -- e.g., 'Active', 'On Leave', 'Terminated'\n supervisor_employee_id character varying(64), -- FK to the employee's supervisor (self-reference, nullable)\n PRIMARY KEY (employee_id)\n)\n"}