{"conversations": [{"role": "user", "content": "Show each player’s username, the number of achievements they have unlocked, and the total quantity of items they currently have in their inventory."}, {"role": "assistant", "content": "SELECT p.username,\n COUNT(DISTINCT pa.achievement_id) AS achievements_count,\n COALESCE(SUM(pi.quantity), 0) AS total_items\nFROM gaming_technology.players p\nLEFT JOIN gaming_technology.player_achievements pa ON p.player_id = pa.player_id\nLEFT JOIN gaming_technology.player_inventory pi ON p.player_id = pi.player_id\nGROUP BY p.username;"}, {"role": "user", "content": "Only include players with status 'active' and count only items of rarity 'Legendary'."}, {"role": "assistant", "content": "SELECT p.username,\n COUNT(DISTINCT pa.achievement_id) AS achievements_count,\n COALESCE(SUM(pi.quantity), 0) AS total_items\nFROM gaming_technology.players p\nLEFT JOIN gaming_technology.player_achievements pa ON p.player_id = pa.player_id\nLEFT JOIN gaming_technology.player_inventory pi ON p.player_id = pi.player_id\nLEFT JOIN gaming_technology.in_game_items i ON pi.item_id = i.item_id\nWHERE p.status = 'active'\n AND i.rarity = 'Legendary'\nGROUP BY p.username;"}, {"role": "user", "content": "Also, only show players who have unlocked at least 5 achievements and whose total item quantity is greater than 20."}, {"role": "assistant", "content": "SELECT p.username,\n COUNT(DISTINCT pa.achievement_id) AS achievements_count,\n SUM(pi.quantity) AS total_items\nFROM gaming_technology.players p\nLEFT JOIN gaming_technology.player_achievements pa ON p.player_id = pa.player_id\nLEFT JOIN gaming_technology.player_inventory pi ON p.player_id = pi.player_id\nLEFT JOIN gaming_technology.in_game_items i ON pi.item_id = i.item_id\nWHERE p.status = 'active'\n AND i.rarity = 'Legendary'\nGROUP BY p.username\nHAVING COUNT(DISTINCT pa.achievement_id) >= 5\n AND SUM(pi.quantity) > 20;"}, {"role": "user", "content": "Finally, order the results by total_items descending."}, {"role": "assistant", "content": "SELECT p.username,\n COUNT(DISTINCT pa.achievement_id) AS achievements_count,\n SUM(pi.quantity) AS total_items\nFROM gaming_technology.players p\nLEFT JOIN gaming_technology.player_achievements pa ON p.player_id = pa.player_id\nLEFT JOIN gaming_technology.player_inventory pi ON p.player_id = pi.player_id\nLEFT JOIN gaming_technology.in_game_items i ON pi.item_id = i.item_id\nWHERE p.status = 'active'\n AND i.rarity = 'Legendary'\nGROUP BY p.username\nHAVING COUNT(DISTINCT pa.achievement_id) >= 5\n AND SUM(pi.quantity) > 20\nORDER BY total_items 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 ( player_id uuid PRIMARY KEY, 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.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 ( 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, player_id.uuid, achievement_id.uuid, unlocked_at.timestamptz )\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) )\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": "List all primary insurance policies that will expire within the next 30 days. Return patient_insurance_id, patient_id, policy_number, and expiration_date."}, {"role": "assistant", "content": "SELECT patient_insurance_id,\n patient_id,\n policy_number,\n expiration_date\nFROM healthcare.patient_insurance\nWHERE is_primary = TRUE\n AND expiration_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '30 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 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.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": "Count the number of policies issued in each calendar year, and show the year and the count."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM issued_at), COUNT(*) FROM insurance.policies WHERE issued_at IS NOT NULL GROUP BY 1 ORDER BY 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 insurance.customers ( customer_id text, 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.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.policy_beneficiaries ( beneficiary_id text, 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": "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": "List all patients who have a medical record with a chief complaint containing the word 'headache'. Show patient ID, first name, last name, and date of birth."}, {"role": "assistant", "content": "SELECT DISTINCT\n p.patient_id,\n p.first_name,\n p.last_name,\n p.date_of_birth\nFROM healthcare.patients AS p\nJOIN healthcare.medical_records AS mr\n ON p.patient_id = mr.patient_id\nWHERE\n mr.chief_complaint ILIKE '%headache%';"}, {"role": "user", "content": "Refine the query to only include records created in the year 2024."}, {"role": "assistant", "content": "SELECT DISTINCT\n p.patient_id,\n p.first_name,\n p.last_name,\n p.date_of_birth\nFROM healthcare.patients AS p\nJOIN healthcare.medical_records AS mr\n ON p.patient_id = mr.patient_id\nWHERE\n mr.chief_complaint ILIKE '%headache%' AND mr.record_date >= '2024-01-01 00:00:00' AND mr.record_date < '2025-01-01 00:00:00';"}], "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.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.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\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": "Show me the subject and start times of all appointments along with the corresponding lawyer IDs for each client."}, {"role": "assistant", "content": "SELECT client_id, lawyer_id, subject, start_time FROM legal_services.appointments;"}], "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 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": "List the service_id, service_name, and agency_id for all active services that have an online application URL provided."}, {"role": "assistant", "content": "SELECT service_id,\n service_name,\n agency_id\nFROM government_services.services\nWHERE is_active = TRUE\n AND online_application_url 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 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.services ( service_id text, agency_id text, service_name text, description text, category text, eligibility_criteria text, standard_fee numeric, average_processing_time_days integer, is_active boolean, online_application_url text )\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.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 (\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 ( 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": "Show the document ID, document type, and upload timestamp for all documents uploaded by citizens who registered after January 1st, 2023."}, {"role": "assistant", "content": "SELECT d.document_id, d.document_type, d.upload_timestamp FROM government_services.documents d JOIN citizens c ON d.citizen_id = c.citizen_id WHERE c.registration_date > '2023-01-01';"}], "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.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 )\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": "List the first name, last name, license number, and status for all drivers whose license expires in the next 6 months."}, {"role": "assistant", "content": "SELECT\n first_name,\n last_name,\n license_number,\n status\nFROM transportation.drivers\nWHERE\n license_expiry_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '6 month'\nORDER BY\n license_expiry_date;"}, {"role": "user", "content": "Now, count how many drivers from that list have an 'Active' status."}, {"role": "assistant", "content": "SELECT\n COUNT(*)\nFROM transportation.drivers\nWHERE\n license_expiry_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '6 month' AND status = 'Active';"}], "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 )\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": "Show me all transactions (transaction_id, amount, transaction_type) where the transaction_type is 'Transfer' and the status is 'Completed', along with the account_id and related_account_id."}, {"role": "assistant", "content": "SELECT transaction_id, amount, transaction_type, account_id, related_account_id FROM financial_services.transactions WHERE transaction_type = 'Transfer' AND status = 'Completed';"}, {"role": "user", "content": "Now modify the query to include only transfers with amounts greater than $1,000 and sort them by transaction_date in descending order."}, {"role": "assistant", "content": "SELECT transaction_id, amount, transaction_type, account_id, related_account_id FROM financial_services.transactions WHERE transaction_type = 'Transfer' AND status = 'Completed' AND amount > 1000 ORDER BY transaction_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.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.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 )\n"} {"conversations": [{"role": "user", "content": "For each claim, show the claim ID, policy ID, and the product name of the insurance product that applies to the policy."}, {"role": "assistant", "content": "SELECT c.claim_id, c.policy_id, ip.product_name FROM insurance.claims c JOIN insurance.insurance_products ip ON c.policy_id = ip.product_id;"}, {"role": "user", "content": "Wait, the policy_id and product_id are different things. Can you instead show, for each claim, the claim ID and incident date, along with the name and type of the insurance product if the policy is of the same id as product_id?"}, {"role": "assistant", "content": "SELECT c.claim_id, c.incident_date, ip.product_name, ip.product_type FROM insurance.claims c JOIN insurance.insurance_products ip ON c.policy_id = ip.product_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 ( 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 )\n"} {"conversations": [{"role": "user", "content": "List the user IDs of all private profiles who last updated their settings in 2024."}, {"role": "assistant", "content": "SELECT user_id FROM social_media.user_settings WHERE private_profile = true AND updated_at >= '2024-01-01' AND updated_at < '2025-01-01';"}, {"role": "user", "content": "Please also include the theme they've chosen."}, {"role": "assistant", "content": "SELECT user_id, theme FROM social_media.user_settings WHERE private_profile = true AND updated_at >= '2024-01-01' AND updated_at < '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 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": "For each user, show their username and the timestamp of their most recent notification. Include users who have never received notifications."}, {"role": "assistant", "content": "SELECT T1.username, max(T2.sent_at) FROM users AS T1 LEFT JOIN trading_platform.notifications AS T2 ON T1.user_id = T2.user_id GROUP BY T1.username"}, {"role": "user", "content": "Could you also include the total number of notifications for each user?"}, {"role": "assistant", "content": "SELECT T1.username, count(T2.notification_id), max(T2.sent_at) FROM users AS T1 LEFT JOIN trading_platform.notifications AS T2 ON T1.user_id = T2.user_id GROUP BY T1.username"}, {"role": "user", "content": "Actually, only show users whose latest notification is unread."}, {"role": "assistant", "content": "WITH LatestNotification AS ( SELECT user_id, sent_at, read_at, ROW_NUMBER() OVER(PARTITION BY user_id ORDER BY sent_at DESC) AS rn FROM trading_platform.notifications ) SELECT T1.username, T2.sent_at FROM users AS T1 JOIN LatestNotification AS T2 ON T1.user_id = T2.user_id WHERE T2.rn = 1 AND T2.read_at IS NULL"}, {"role": "user", "content": "Also, include the count of unread notifications for these users."}, {"role": "assistant", "content": "WITH LatestNotification AS ( SELECT user_id, sent_at, read_at, ROW_NUMBER() OVER(PARTITION BY user_id ORDER BY sent_at DESC) AS rn FROM trading_platform.notifications ) SELECT T1.username, count(CASE WHEN T3.read_at IS NULL THEN T3.notification_id ELSE NULL END), T2.sent_at FROM users AS T1 JOIN LatestNotification AS T2 ON T1.user_id = T2.user_id AND T2.rn = 1 AND T2.read_at IS NULL JOIN trading_platform.notifications AS T3 ON T1.user_id = T3.user_id GROUP BY T1.username, T2.sent_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 trading_platform.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_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.patient_id, 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 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, 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, 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.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": "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": "Show me all insurance plans where the website includes 'secure'."}, {"role": "assistant", "content": "SELECT * FROM healthcare.insurance_plans WHERE website ILIKE '%secure%';"}], "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.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.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": "List the ERC20 tokens (from token_metas) with exactly 6 decimals. Show their symbol, contract_address, and name."}, {"role": "assistant", "content": "SELECT symbol, contract_address, name FROM token_metas WHERE is_erc20 = 1 AND decimals = 6;"}, {"role": "user", "content": "Can you also include the total current supply for each token?"}, {"role": "assistant", "content": "SELECT symbol, contract_address, name, total_supply FROM token_metas WHERE is_erc20 = 1 AND decimals = 6;"}, {"role": "user", "content": "Now, join with token_prices_latest to also include the latest price for each token."}, {"role": "assistant", "content": "SELECT tm.symbol, tm.contract_address, tm.name, tm.total_supply, tpl.price AS latest_price\nFROM token_metas tm\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum'\nWHERE tm.is_erc20 = 1 AND tm.decimals = 6;"}, {"role": "user", "content": "Only include tokens where the latest price is between 0.5 and 2.0 USD, and limit the result to the top 5 tokens by price descending."}, {"role": "assistant", "content": "SELECT tm.symbol, tm.contract_address, tm.name, tm.total_supply, tpl.price AS latest_price\nFROM token_metas tm\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum'\nWHERE tm.is_erc20 = 1 AND tm.decimals = 6 AND tpl.price BETWEEN 0.5 AND 2.0\nORDER BY tpl.price 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 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 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 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_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_metadata ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer 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": "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": "For projects that have completed more than one fundraising round, calculate the average investment value across all their recorded rounds. Display the project name and this average value."}, {"role": "assistant", "content": "SELECT project_name, AVG(investment_value) AS average_investment FROM project_fundraising_record GROUP BY project_name HAVING COUNT(*) > 1;"}, {"role": "user", "content": "Can you modify this to only show projects where the average investment value is greater than 10 million USD and order the results by average investment value descending?"}, {"role": "assistant", "content": "SELECT project_name, AVG(investment_value) AS average_investment FROM project_fundraising_record GROUP BY project_name HAVING COUNT(*) > 1 AND AVG(investment_value) > 10000000 ORDER BY average_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 character varying(32) NOT NULL, -- fundraising record id project_id character varying(32) NOT NULL, -- the invested project's id project_name character varying(128) NOT NULL, -- name of the invested project rounds_name character varying(32), -- name of the fundraising round investment_value numeric(38,14), -- amount of the fundraising in USD investment_date character varying(128), -- the date of the investment happened introduction character varying(128), -- the introduction of the invested project valuation numeric(38,14), -- the valuation of the project in USD when invested )\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": "Find all wallets that have deployed contracts on both 'ethereum' and 'polygon' networks, showing the wallet address and the count of contracts deployed on each network."}, {"role": "assistant", "content": "SELECT w.address, SUM(CASE WHEN c.network_id = 'ethereum' THEN 1 ELSE 0 END) AS ethereum_count, SUM(CASE WHEN c.network_id = 'polygon' THEN 1 ELSE 0 END) AS polygon_count FROM web3.wallets w JOIN web3.contracts c ON w.address = c.deployer_address WHERE c.network_id IN ('ethereum', 'polygon') GROUP BY w.address HAVING SUM(CASE WHEN c.network_id = 'ethereum' THEN 1 ELSE 0 END) > 0 AND SUM(CASE WHEN c.network_id = 'polygon' THEN 1 ELSE 0 END) > 0;"}], "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 )\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 the name, symbol, and type of each asset, along with the total number of orders placed for each asset."}, {"role": "assistant", "content": "SELECT a.name, a.symbol, a.type, COUNT(o.order_id) AS order_count\nFROM trading_platform.assets a\nLEFT JOIN trading_platform.orders o ON a.asset_id = o.asset_id\nGROUP BY a.asset_id, a.name, a.symbol, a.type;"}, {"role": "user", "content": "Only include assets that have at least 10 orders, and order the result by order_count descending."}, {"role": "assistant", "content": "SELECT a.name, a.symbol, a.type, COUNT(o.order_id) AS order_count\nFROM trading_platform.assets a\nLEFT JOIN trading_platform.orders o ON a.asset_id = o.asset_id\nGROUP BY a.asset_id, a.name, a.symbol, a.type\nHAVING COUNT(o.order_id) >= 10\nORDER BY order_count DESC;"}, {"role": "user", "content": "Instead of all orders, only consider orders with status 'open'."}, {"role": "assistant", "content": "SELECT a.name, a.symbol, a.type, COUNT(o.order_id) AS open_order_count\nFROM trading_platform.assets a\nLEFT JOIN trading_platform.orders o ON a.asset_id = o.asset_id AND o.status = 'open'\nGROUP BY a.asset_id, a.name, a.symbol, a.type\nHAVING COUNT(o.order_id) >= 10\nORDER BY open_order_count DESC;"}, {"role": "user", "content": "The SQL doesn't work because some assets have no open orders, but I want to include those assets with a count of 0. Please update the query accordingly."}, {"role": "assistant", "content": "SELECT a.name, a.symbol, a.type, COUNT(o.order_id) AS open_order_count\nFROM trading_platform.assets a\nLEFT JOIN trading_platform.orders o ON a.asset_id = o.asset_id AND o.status = 'open'\nGROUP BY a.asset_id, a.name, a.symbol, a.type\nHAVING COUNT(o.order_id) >= 10 OR COUNT(o.order_id) = 0\nORDER BY open_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 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.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 ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.dapps ( dapp_id text PRIMARY KEY, name text, description text, url text )\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 ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "How many distinct ports have been used by peers in the system?"}, {"role": "assistant", "content": "SELECT COUNT(DISTINCT port) AS distinct_port_count\nFROM trading_platform.peers;"}], "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 PRIMARY KEY, username text, email text, password_hash text, created_at timestamp )\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 ( 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 (\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 ( dapp_id.text, name.text, description.text, url.text )\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 (\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 ( kyc_audit_id.text, user_id.text, status.text, reviewed_at.timestamp )\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)\nCREATE TABLE trading_platform.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\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": "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": "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 medical records along with the chief complaint and record date for patients who had their medical record created after March 1, 2023 and whose record was created by doctor with ID 'doctor_123'."}, {"role": "assistant", "content": "SELECT record_id, patient_id, chief_complaint, record_date FROM healthcare.medical_records WHERE doctor_id = 'doctor_123' AND record_date > '2023-03-01';"}, {"role": "user", "content": "Can you also include the treatment plan for each record in the result?"}, {"role": "assistant", "content": "SELECT record_id, patient_id, chief_complaint, record_date, treatment_plan FROM healthcare.medical_records WHERE doctor_id = 'doctor_123' AND record_date > '2023-03-01';"}, {"role": "user", "content": "Actually, I only want records where the assessment field is not null."}, {"role": "assistant", "content": "SELECT record_id, patient_id, chief_complaint, record_date, treatment_plan FROM healthcare.medical_records WHERE doctor_id = 'doctor_123' AND record_date > '2023-03-01' AND assessment IS NOT NULL;"}, {"role": "user", "content": "Now, restrict the results to records where the chief complaint contains the word 'cough'."}, {"role": "assistant", "content": "SELECT record_id, patient_id, chief_complaint, record_date, treatment_plan FROM healthcare.medical_records WHERE doctor_id = 'doctor_123' AND record_date > '2023-03-01' AND assessment IS NOT NULL AND chief_complaint ILIKE '%cough%';"}], "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 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 )\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": "Could you list each game title along with the total number of players currently connected across all its servers?"}, {"role": "assistant", "content": "SELECT g.title, SUM(s.current_players) AS total_current_players FROM gaming_technology.games g JOIN gaming_technology.servers s ON g.game_id = s.game_id GROUP BY 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, 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 ( 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, name.text, country.text, founded_year.integer, website.text, created_at.timestamptz )\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 )\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, player_id.uuid, achievement_id.uuid, unlocked_at.timestamptz )\nCREATE TABLE gaming_technology.in_game_items ( item_id.uuid, game_id.uuid, item_name.text, item_type.text, description.text, rarity.text, cost_currency.text, cost_amount.numeric, attributes.jsonb )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id.uuid, player_id.uuid, item_id.uuid, quantity.integer, acquired_at.timestamptz, instance_data.jsonb )\n"} {"conversations": [{"role": "user", "content": "Show all payments made for reservations that had more than 2 adults. Include the payment ID, amount, currency, reservation ID, guest full name, and the number of adults in the reservation."}, {"role": "assistant", "content": "SELECT T1.payment_id, T1.amount, T1.currency_code, T1.reservation_id, T3.first_name, T3.last_name, T2.num_adults FROM hospitality_technology.payments AS T1 JOIN hospitality_technology.reservations AS T2 ON T1.reservation_id = T2.reservation_id JOIN hospitality_technology.guests AS T3 ON T1.guest_id = T3.guest_id WHERE T2.num_adults > 2;"}, {"role": "user", "content": "Filter these payments to only include those with a status of 'Succeeded'. Also, include the property name associated with the reservation."}, {"role": "assistant", "content": "SELECT T1.payment_id, T1.amount, T1.currency_code, T1.reservation_id, T3.first_name, T3.last_name, T2.num_adults, T4.property_name FROM hospitality_technology.payments AS T1 JOIN hospitality_technology.reservations AS T2 ON T1.reservation_id = T2.reservation_id JOIN hospitality_technology.guests AS T3 ON T1.guest_id = T3.guest_id JOIN hospitality_technology.properties AS T4 ON T2.property_id = T4.property_id WHERE T2.num_adults > 2 AND T1.status = 'Succeeded';"}, {"role": "user", "content": "Further filter to only show payments made using the 'CreditCard' method and order the results by payment timestamp descending."}, {"role": "assistant", "content": "SELECT T1.payment_id, T1.amount, T1.currency_code, T1.reservation_id, T3.first_name, T3.last_name, T2.num_adults, T4.property_name FROM hospitality_technology.payments AS T1 JOIN hospitality_technology.reservations AS T2 ON T1.reservation_id = T2.reservation_id JOIN hospitality_technology.guests AS T3 ON T1.guest_id = T3.guest_id JOIN hospitality_technology.properties AS T4 ON T2.property_id = T4.property_id WHERE T2.num_adults > 2 AND T1.status = 'Succeeded' AND T1.payment_method = 'CreditCard' ORDER BY T1.payment_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 hospitality_technology.properties (\n property_id character varying(64) NOT NULL, -- unique identifier for the property (hotel, resort, etc.)\n property_name character varying(255) NOT NULL, -- name of the property\n address_line1 character varying(255) NOT NULL, -- primary address line\n address_line2 character varying(255), -- secondary address line\n city character varying(100) NOT NULL, -- city\n state_province character varying(100), -- state or province\n postal_code character varying(20) NOT NULL, -- zip or postal code\n country_code character varying(3) NOT NULL, -- ISO country code (e.g., USA, CAN)\n phone_number character varying(30), -- main contact phone\n email_address character varying(255), -- main contact email\n property_type character varying(50) NOT NULL, -- e.g., Hotel, Resort, B&B, Motel\n star_rating numeric(2,1), -- star rating (e.g., 4.5)\n timezone character varying(64) NOT NULL, -- IANA timezone ID (e.g., America/New_York)\n manager_staff_id character varying(64), -- FK to staff table for the general manager\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 (property_id)\n)\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.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\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 )\nCREATE TABLE hospitality_technology.services ( service_id text PRIMARY KEY, property_id text, service_name text, description text, category text, price numeric, unit text, is_available boolean, department text )\nCREATE TABLE hospitality_technology.payments ( payment_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, bill_id character varying(64), amount numeric(12,2) NOT NULL, currency_code character varying(3) NOT NULL, payment_method character varying(50) NOT NULL, card_type character varying(50), card_last_four character varying(4), transaction_ref character varying(128), payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, status character varying(50) NOT NULL, staff_id_processed character varying(64), notes text, PRIMARY KEY (payment_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (staff_id_processed) 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 medication names and dosage for all prescriptions issued for patient with ID 'patient_555'."}, {"role": "assistant", "content": "SELECT m.medication_name, p.dosage\nFROM healthcare.prescriptions p\nJOIN healthcare.medications m ON p.medication_id = m.medication_id\nWHERE p.patient_id = 'patient_555';"}], "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.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.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 ( medication_id text PRIMARY KEY, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\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": "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 all wallets that were created on the same day and list their wallet IDs, addresses, and the creation date."}, {"role": "assistant", "content": "SELECT w1.wallet_id, w1.address, w1.created_at::date AS creation_date FROM web3.wallets w1 JOIN (SELECT created_at::date AS creation_date FROM web3.wallets GROUP BY created_at::date HAVING COUNT(*) > 1) w2 ON w1.created_at::date = w2.creation_date ORDER BY creation_date, w1.wallet_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.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": "Find all non-smoking rooms that have not been cleaned in the last 7 days."}, {"role": "assistant", "content": "SELECT room_id, room_number, last_cleaned_at\nFROM hospitality_technology.rooms\nWHERE is_smoking = false\n AND last_cleaned_at < NOW() - INTERVAL '7 days';"}, {"role": "user", "content": "Now also include only those rooms with 'Balcony' in the features."}, {"role": "assistant", "content": "SELECT room_id, room_number, last_cleaned_at, features\nFROM hospitality_technology.rooms\nWHERE is_smoking = false\n AND last_cleaned_at < NOW() - INTERVAL '7 days'\n AND features ILIKE '%Balcony%';"}], "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)\nCREATE TABLE hospitality_technology.payments ( payment_id text, reservation_id text, guest_id text, bill_id text, amount numeric, currency_code text, payment_method text, card_type text, card_last_four text, transaction_ref text, payment_timestamp timestamp, status text, staff_id_processed text, notes text )\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": "Please list the contact phone number and website for each insurance plan."}, {"role": "assistant", "content": "SELECT plan_id, plan_name, contact_phone, website FROM healthcare.insurance_plans;"}, {"role": "user", "content": "Show only the plans where the website contains '.gov'."}, {"role": "assistant", "content": "SELECT plan_id, plan_name, contact_phone, website FROM healthcare.insurance_plans WHERE website LIKE '%.gov%';"}], "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, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\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": "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 the list of developer names and their corresponding website domains (the domain part of the website URL)."}, {"role": "assistant", "content": "SELECT name, \n CASE \n WHEN website LIKE 'http%' THEN SUBSTRING(website FROM '://([^/]+)')\n ELSE NULL\n END AS domain\nFROM gaming_technology.developers;"}, {"role": "user", "content": "Only include developers whose website ends with '.com'."}, {"role": "assistant", "content": "SELECT name, \n CASE WHEN website LIKE 'http%' THEN SUBSTRING(website FROM '://([^/]+)') ELSE NULL END AS domain\nFROM gaming_technology.developers\nWHERE website LIKE '%.com';"}, {"role": "user", "content": "Order the results by the developer name in ascending order."}, {"role": "assistant", "content": "SELECT name, \n CASE WHEN website LIKE 'http%' THEN SUBSTRING(website FROM '://([^/]+)') ELSE NULL END AS domain\nFROM gaming_technology.developers\nWHERE website LIKE '%.com'\nORDER BY 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 gaming_technology.developers ( developer_id uuid, name text, country text, founded_year integer, website text, created_at timestamp with time zone )\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 all maintenance service records for vehicles that have successfully completed any trip."}, {"role": "assistant", "content": "SELECT DISTINCT ml.* FROM transportation.maintenance_logs AS ml JOIN transportation.trips AS t ON ml.vehicle_id = t.vehicle_id WHERE t.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.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.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.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 )\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": "For each employee who has verified documents, show their full name and the total number of documents they have verified with a status of 'Verified'."}, {"role": "assistant", "content": "SELECT e.full_name, COUNT(d.document_id) FROM government_services.documents d JOIN employees e ON d.verified_by_employee_id = e.employee_id WHERE d.verification_status = 'Verified' GROUP BY e.full_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 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 )\n"} {"conversations": [{"role": "user", "content": "For each user, show their user ID and the count of unique wallet addresses they own."}, {"role": "assistant", "content": "SELECT user_id, COUNT(DISTINCT address) FROM wallets GROUP BY 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 trading_platform.wallets ( wallet_id.text, user_id.text, address.text, private_key.text, created_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "For the 'DeFi' narrative, what is the average ROI and the total net inflow (usd_value where type=1) from smart money token inflow?"}, {"role": "assistant", "content": "SELECT AVG(sm.roi) AS avg_roi, SUM(smt.usd_value) AS total_net_inflow\nFROM smart_money_token_inflow smt\nJOIN smart_money_profit sm ON smt.chain = sm.chain\nWHERE smt.narrative = 'DeFi' AND smt.type = 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_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 cex_token_balance ( snapshot_time text, chain text, address text, exchange text, token_address text, token_symbol text, balance numeric, usd_value numeric, price numeric )\nCREATE TABLE smart_money_profit ( address text, rank numeric, profit numeric, roi numeric, realized_ratio numeric, most_profit_token text, last_trade_time text, chain text )\nCREATE TABLE smart_money_token_inflow ( token_address text, token_symbol text, token_amount numeric, usd_value numeric, avg_price numeric, type numeric, address_amount numeric, narrative text, chain text )\n"} {"conversations": [{"role": "user", "content": "What are the training programs or certifications completed by a staff member with the role of Platform Supervisor?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to information about the training programs or certifications completed by staff members. The data available to me only includes basic staff details such as name, role, and contact information. For details on training or certifications, please refer to the HR department or relevant training records."}], "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.staff ( staff_id text PRIMARY KEY, first_name text, last_name text, role text, primary_station_id text, employee_number text UNIQUE, hire_date date, contact_email text UNIQUE, contact_phone text, is_active boolean )\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 name, symbol, address FROM token_prices_latest WHERE price BETWEEN 1 AND 10 AND blockchain = 'ethereum';"}, {"role": "user", "content": "I think there's an error in your query - it should be joining with sui_coins_metadata on coin_type not address. Also, can you add the current price to the results?"}, {"role": "assistant", "content": "SELECT scm.name, scm.symbol, scm.coin_type, tpl.price FROM sui_coins_metadata scm JOIN token_prices_latest tpl ON scm.coin_type = tpl.address WHERE 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 scm.name, scm.symbol, scm.coin_type, tpl.price FROM sui_coins_metadata scm JOIN token_prices_latest tpl ON scm.coin_type = tpl.address WHERE tpl.price BETWEEN 1 AND 10 AND scm.decimals = 18 ORDER BY scm.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 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_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_coins_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\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 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 ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\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_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(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 )\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": "Which route numbers connect locations with a distance less than 80 km and more than 5 words in their description? Include the route type in the results."}, {"role": "assistant", "content": "SELECT route_number, type FROM transportation.routes WHERE distance_km < 80 AND array_length(regexp_split_to_array(description, '\\s+'), 1) > 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 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": "List all patients who have insurance plans with group numbers, showing their patient IDs and the count of such plans per patient."}, {"role": "assistant", "content": "SELECT patient_id, COUNT(*) AS plan_count FROM healthcare.patient_insurance WHERE group_number IS NOT NULL GROUP BY patient_id;"}, {"role": "user", "content": "Actually, I only need patients who have more than 2 such plans."}, {"role": "assistant", "content": "SELECT patient_id, COUNT(*) AS plan_count FROM healthcare.patient_insurance WHERE group_number IS NOT NULL GROUP BY patient_id HAVING COUNT(*) > 2;"}, {"role": "user", "content": "Can you also include the earliest effective date among these plans for each patient?"}, {"role": "assistant", "content": "SELECT patient_id, COUNT(*) AS plan_count, MIN(effective_date) AS earliest_effective_date FROM healthcare.patient_insurance WHERE group_number IS NOT NULL GROUP BY patient_id HAVING COUNT(*) > 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 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": "What is the fuel consumption rate of train number T1234?"}, {"role": "assistant", "content": "I'm sorry, but I don't have information on the fuel consumption rate of train number T1234. The data available in the system only includes details such as train ID, model, manufacturer, year manufactured, capacity, status, and maintenance dates."}], "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 ( train_id character varying(64) NOT NULL, train_number character varying(32) NOT NULL, model character varying(128), manufacturer character varying(128), year_manufactured integer, capacity integer NOT NULL, status character varying(32) NOT NULL DEFAULT 'Active', last_maintenance_date date, next_maintenance_date date, PRIMARY KEY (train_id), UNIQUE (train_number) )\n"} {"conversations": [{"role": "user", "content": "List the usernames and full names of users who created their account in 2024 and are verified."}, {"role": "assistant", "content": "SELECT username, full_name FROM social_media.users WHERE created_at >= '2024-01-01' AND created_at < '2025-01-01' AND is_verified = true;"}, {"role": "user", "content": "Also include their email address and location."}, {"role": "assistant", "content": "SELECT username, full_name, email, location FROM social_media.users WHERE created_at >= '2024-01-01' AND created_at < '2025-01-01' AND 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 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": "Show me properties that have more than 10 service orders delivered in the last month. Include the property_name and the number of delivered orders."}, {"role": "assistant", "content": "SELECT p.property_name,\n COUNT(o.order_id) AS delivered_orders\nFROM hospitality_technology.properties p\nJOIN hospitality_technology.services s ON p.property_id = s.property_id\nJOIN hospitality_technology.service_orders o ON s.service_id = o.service_id\nWHERE o.status = 'Delivered'\n AND o.delivery_timestamp >= current_date - interval '1 month'\nGROUP BY p.property_name\nHAVING COUNT(o.order_id) > 10;"}, {"role": "user", "content": "Actually, only include those properties where the average total_price per delivered order exceeds 50, and sort by that average descending."}, {"role": "assistant", "content": "SELECT p.property_name,\n COUNT(o.order_id) AS delivered_orders,\n AVG(o.total_price) AS avg_price\nFROM hospitality_technology.properties p\nJOIN hospitality_technology.services s ON p.property_id = s.property_id\nJOIN hospitality_technology.service_orders o ON s.service_id = o.service_id\nWHERE o.status = 'Delivered'\n AND o.delivery_timestamp >= current_date - interval '1 month'\nGROUP BY p.property_name\nHAVING COUNT(o.order_id) > 10\n AND AVG(o.total_price) > 50\nORDER BY avg_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 hospitality_technology.properties (\n property_id character varying(64) NOT NULL, -- unique identifier for the property (hotel, resort, etc.)\n property_name character varying(255) NOT NULL, -- name of the property\n address_line1 character varying(255) NOT NULL, -- primary address line\n address_line2 character varying(255), -- secondary address line\n city character varying(100) NOT NULL, -- city\n state_province character varying(100), -- state or province\n postal_code character varying(20) NOT NULL, -- zip or postal code\n country_code character varying(3) NOT NULL, -- ISO country code (e.g., USA, CAN)\n phone_number character varying(30), -- main contact phone\n email_address character varying(255), -- main contact email\n property_type character varying(50) NOT NULL, -- e.g., Hotel, Resort, B&B, Motel\n star_rating numeric(2,1), -- star rating (e.g., 4.5)\n timezone character varying(64) NOT NULL, -- IANA timezone ID (e.g., America/New_York)\n manager_staff_id character varying(64), -- FK to staff table for the general manager\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 (property_id)\n)\nCREATE TABLE hospitality_technology.services ( service_id text PRIMARY KEY, property_id text, service_name text, description text, category text, price numeric, unit text, is_available boolean, department text )\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) )\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 all users who follow both user 'U100' and user 'U101'."}, {"role": "assistant", "content": "SELECT f1.follower_user_id\nFROM social_media.follows f1\nJOIN social_media.follows f2 ON f1.follower_user_id = f2.follower_user_id\nWHERE f1.following_user_id = 'U100' AND f2.following_user_id = 'U101';"}], "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.comments ( comment_id text PRIMARY KEY, 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 PRIMARY KEY, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.follows ( follow_id text PRIMARY KEY, follower_user_id text, following_user_id text, created_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id text PRIMARY KEY, tag_name text, created_at timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text PRIMARY KEY, post_id text, hashtag_id text )\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.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 )\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": "List all invoices that were paid within 7 days of their issue date. Show invoice number, issue date, payment date, and total amount."}, {"role": "assistant", "content": "SELECT invoice_number, issue_date, payment_date, total_amount FROM legal_services.invoices WHERE status = 'Paid' AND payment_date IS NOT NULL AND (payment_date::DATE - issue_date) <= 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 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 )\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": "Show the total fuel cost for each month in 2023 based on the log timestamp."}, {"role": "assistant", "content": "SELECT\n EXTRACT(MONTH FROM log_timestamp) AS log_month,\n SUM(total_cost) AS monthly_total_cost\nFROM transportation.fuel_logs\nWHERE EXTRACT(YEAR FROM log_timestamp) = 2023\nGROUP BY 1\nORDER BY 1;"}, {"role": "user", "content": "Only include months where the total cost is greater than 5000 and order the results by month."}, {"role": "assistant", "content": "SELECT\n EXTRACT(MONTH FROM log_timestamp) AS log_month,\n SUM(total_cost) AS monthly_total_cost\nFROM transportation.fuel_logs\nWHERE EXTRACT(YEAR FROM log_timestamp) = 2023\nGROUP BY 1\nHAVING SUM(total_cost) > 5000\nORDER BY 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.fuel_logs ( fuel_log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, trip_id character varying(64), log_timestamp timestamp with time zone NOT NULL, fuel_type character varying(32) NOT NULL, quantity numeric(10, 3) NOT NULL, unit character varying(16) NOT NULL, cost_per_unit numeric(8, 4), total_cost numeric(10, 2) NOT NULL, odometer_reading integer, location_id character varying(64), PRIMARY KEY (fuel_log_id) )\n"} {"conversations": [{"role": "user", "content": "I need a report of total maintenance cost per vehicle type."}, {"role": "assistant", "content": "SELECT v.type AS vehicle_type,\n SUM(m.cost) AS total_maintenance_cost\nFROM transportation.vehicles v\nJOIN transportation.maintenance_logs m ON v.vehicle_id = m.vehicle_id\nGROUP BY v.type;"}, {"role": "user", "content": "Only include types where total maintenance cost is greater than 10000."}, {"role": "assistant", "content": "SELECT v.type AS vehicle_type,\n SUM(m.cost) AS total_maintenance_cost\nFROM transportation.vehicles v\nJOIN transportation.maintenance_logs m ON v.vehicle_id = m.vehicle_id\nGROUP BY v.type\nHAVING SUM(m.cost) > 10000;"}, {"role": "user", "content": "Also include the number of maintenance events per vehicle type."}, {"role": "assistant", "content": "SELECT v.type AS vehicle_type,\n SUM(m.cost) AS total_maintenance_cost,\n COUNT(m.log_id) AS maintenance_event_count\nFROM transportation.vehicles v\nJOIN transportation.maintenance_logs m ON v.vehicle_id = m.vehicle_id\nGROUP BY v.type\nHAVING SUM(m.cost) > 10000;"}, {"role": "user", "content": "Sort the results by average cost per event in descending order."}, {"role": "assistant", "content": "SELECT v.type AS vehicle_type,\n SUM(m.cost) AS total_maintenance_cost,\n COUNT(m.log_id) AS maintenance_event_count,\n AVG(m.cost) AS average_cost_per_event\nFROM transportation.vehicles v\nJOIN transportation.maintenance_logs m ON v.vehicle_id = m.vehicle_id\nGROUP BY v.type\nHAVING SUM(m.cost) > 10000\nORDER BY AVG(m.cost) 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)\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 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 (\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.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 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.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 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": "For each achievement, show its name, the game_id it belongs to, and the number of distinct players who have played a session for that game."}, {"role": "assistant", "content": "SELECT a.name, a.game_id, COUNT(DISTINCT gs.player_id) AS players_with_sessions\nFROM gaming_technology.achievements a\nLEFT JOIN gaming_technology.game_sessions gs ON a.game_id = gs.game_id\nGROUP BY a.achievement_id, a.name, a.game_id;"}, {"role": "user", "content": "Now, filter to only include achievements for games that have at least 50 players who have played a session."}, {"role": "assistant", "content": "SELECT a.name, a.game_id, COUNT(DISTINCT gs.player_id) AS players_with_sessions\nFROM gaming_technology.achievements a\nLEFT JOIN gaming_technology.game_sessions gs ON a.game_id = gs.game_id\nGROUP BY a.achievement_id, a.name, a.game_id\nHAVING COUNT(DISTINCT gs.player_id) >= 50;"}, {"role": "user", "content": "Please also include the number of times each achievement has been unlocked by unique players, labeled as unique_unlocks."}, {"role": "assistant", "content": "SELECT a.name, a.game_id, COUNT(DISTINCT gs.player_id) AS players_with_sessions,\n (SELECT COUNT(DISTINCT gs2.player_id)\n FROM gaming_technology.game_sessions gs2\n WHERE gs2.game_id = a.game_id) AS unique_unlocks\nFROM gaming_technology.achievements a\nLEFT JOIN gaming_technology.game_sessions gs ON a.game_id = gs.game_id\nGROUP BY a.achievement_id, a.name, a.game_id\nHAVING COUNT(DISTINCT gs.player_id) >= 50;"}, {"role": "user", "content": "I think unique_unlocks should be the count of distinct players who have unlocked each specific achievement, not just played a session. Can you correct that?"}, {"role": "assistant", "content": "-- With the provided tables, there is no direct record of players unlocking a specific achievement, unless unlocking is inferred elsewhere. If you have an achievement unlocks table, you could join it here. Otherwise, only possible to count sessions per game."}], "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.developers ( developer_id.uuid, name.text, country.text, founded_year.integer, website.text, created_at.timestamptz )\nCREATE TABLE gaming_technology.game_sessions ( session_id.uuid, player_id.uuid, game_id.uuid, server_id.uuid, start_time.timestamptz, end_time.timestamptz, duration_seconds.integer, score.integer, session_data.jsonb )\nCREATE TABLE gaming_technology.achievements ( achievement_id.uuid, game_id.uuid, name.text, description.text, icon_url.text, points.integer, hidden.boolean )\n"} {"conversations": [{"role": "user", "content": "For each relationship type among policy beneficiaries, count how many beneficiaries exist of that type. Provide relationship and count, ordered by count descending."}, {"role": "assistant", "content": "SELECT relationship,\n COUNT(*) AS beneficiary_count\nFROM insurance.policy_beneficiaries\nGROUP BY relationship\nORDER BY beneficiary_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 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 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 )\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.premium_payments ( payment_id text PRIMARY KEY, 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 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 )\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": "Show me all wallet addresses that belong to user_id 'U1001', along with their private keys."}, {"role": "assistant", "content": "SELECT address_id, private_key FROM blockchain.wallets WHERE user_id = 'U1001';"}, {"role": "user", "content": "Now join this with another table to show the count of transactions for each of these wallet addresses."}, {"role": "assistant", "content": "Note: The schema only includes the wallets table. Without a transactions table in the schema, this query cannot be executed. Please provide the transactions table structure if you need this analysis."}], "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": "Which games have at least one achievement worth exactly 75 points, and what are the names and descriptions of those achievements?"}, {"role": "assistant", "content": "SELECT g.title, a.name AS achievement_name, a.description\nFROM gaming_technology.games g\nJOIN gaming_technology.achievements a ON g.game_id = a.game_id\nWHERE a.points = 75;"}, {"role": "user", "content": "Also include the release date of each game in the output."}, {"role": "assistant", "content": "SELECT g.title, g.release_date, a.name AS achievement_name, a.description\nFROM gaming_technology.games g\nJOIN gaming_technology.achievements a ON g.game_id = a.game_id\nWHERE a.points = 75;"}, {"role": "user", "content": "Now, only show results for games released after 2021-01-01."}, {"role": "assistant", "content": "SELECT g.title, g.release_date, a.name AS achievement_name, a.description\nFROM gaming_technology.games g\nJOIN gaming_technology.achievements a ON g.game_id = a.game_id\nWHERE a.points = 75 AND g.release_date > '2021-01-01';"}, {"role": "user", "content": "Order the list by game release date ascending, then achievement name ascending."}, {"role": "assistant", "content": "SELECT g.title, g.release_date, a.name AS achievement_name, a.description\nFROM gaming_technology.games g\nJOIN gaming_technology.achievements a ON g.game_id = a.game_id\nWHERE a.points = 75 AND g.release_date > '2021-01-01'\nORDER BY g.release_date ASC, a.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 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.developers ( developer_id uuid, name text, country text, founded_year integer, website text, created_at timestamp with time zone )\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 ( 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.player_achievements ( player_achievement_id.uuid, player_id.uuid, achievement_id.uuid, unlocked_at.timestamptz )\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) )\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": "What are the personal contact details of the staff member associated with staff_id 'STAFF789' who worked on a specific maintenance record?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide personal contact details of staff members as this information is not stored in the maintenance_records table and is outside the scope of the available data."}], "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": "What is the current job satisfaction level or feedback from staff members working at a specific train station?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on job satisfaction levels or feedback from staff members as this data is not included in the staff 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 train_station_management.staff ( staff_id.text, first_name.text, last_name.text, role.text, primary_station_id.text, employee_number.text, hire_date.date, contact_email.text, contact_phone.text, is_active.boolean )\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": "Show me the content of all comments that have received at least one like."}, {"role": "assistant", "content": "SELECT DISTINCT T1.content FROM social_media.comments AS T1 JOIN social_media.likes AS T2 ON T1.comment_id = T2.comment_id;"}, {"role": "user", "content": "Also include the creation time of these comments and the user_id of the commenter?"}, {"role": "assistant", "content": "SELECT DISTINCT T1.comment_id, T1.content, T1.created_at, T1.user_id FROM social_media.comments AS T1 JOIN social_media.likes AS T2 ON T1.comment_id = T2.comment_id;"}, {"role": "user", "content": "Only show comments created before '2024-05-01'."}, {"role": "assistant", "content": "SELECT DISTINCT T1.comment_id, T1.content, T1.created_at, T1.user_id FROM social_media.comments AS T1 JOIN social_media.likes AS T2 ON T1.comment_id = T2.comment_id WHERE T1.created_at < '2024-05-01';"}], "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.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.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": "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": "List all servers that are currently online and have a player count greater than their average player count across all servers in the same region."}, {"role": "assistant", "content": "SELECT s.server_id, s.server_name, s.region, s.current_players\nFROM gaming_technology.servers s\nJOIN (SELECT region, AVG(current_players) AS avg_players FROM gaming_technology.servers GROUP BY region) r\n ON s.region = r.region\nWHERE s.status = 'online' AND s.current_players > r.avg_players;"}, {"role": "user", "content": "Can you also include the maximum players of each server in the result?"}, {"role": "assistant", "content": "SELECT s.server_id, s.server_name, s.region, s.current_players, s.max_players\nFROM gaming_technology.servers s\nJOIN (SELECT region, AVG(current_players) AS avg_players FROM gaming_technology.servers GROUP BY region) r\n ON s.region = r.region\nWHERE s.status = 'online' AND s.current_players > r.avg_players;"}, {"role": "user", "content": "Now only show servers where current_players is at least 75% of max_players."}, {"role": "assistant", "content": "SELECT s.server_id, s.server_name, s.region, s.current_players, s.max_players\nFROM gaming_technology.servers s\nJOIN (SELECT region, AVG(current_players) AS avg_players FROM gaming_technology.servers GROUP BY region) r\n ON s.region = r.region\nWHERE s.status = 'online'\n AND s.current_players > r.avg_players\n AND s.current_players >= 0.75 * s.max_players;"}, {"role": "user", "content": "Please also show the average player count for the region in each row."}, {"role": "assistant", "content": "SELECT s.server_id, s.server_name, s.region, s.current_players, s.max_players, r.avg_players\nFROM gaming_technology.servers s\nJOIN (SELECT region, AVG(current_players) AS avg_players FROM gaming_technology.servers GROUP BY region) r\n ON s.region = r.region\nWHERE s.status = 'online'\n AND s.current_players > r.avg_players\n AND s.current_players >= 0.75 * s.max_players;"}], "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.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.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 )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, achievement_id uuid NOT NULL, unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (player_achievement_id), UNIQUE (player_id, achievement_id) )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid, game_id uuid, item_name text, item_type text, description text, rarity text, cost_currency text, cost_amount numeric, attributes jsonb )\n"} {"conversations": [{"role": "user", "content": "List all properties located in the USA with a star rating of 4.0 or higher, along with their city and property type."}, {"role": "assistant", "content": "SELECT property_name, city, property_type, star_rating FROM hospitality_technology.properties WHERE country_code = 'USA' AND star_rating >= 4.0;"}, {"role": "user", "content": "Now, include only properties that are Resorts and order them by star rating in descending order."}, {"role": "assistant", "content": "SELECT property_name, city, property_type, star_rating FROM hospitality_technology.properties WHERE country_code = 'USA' AND star_rating >= 4.0 AND property_type = 'Resort' ORDER BY star_rating 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.properties (\n property_id character varying(64) NOT NULL, -- unique identifier for the property (hotel, resort, etc.)\n property_name character varying(255) NOT NULL, -- name of the property\n address_line1 character varying(255) NOT NULL, -- primary address line\n address_line2 character varying(255), -- secondary address line\n city character varying(100) NOT NULL, -- city\n state_province character varying(100), -- state or province\n postal_code character varying(20) NOT NULL, -- zip or postal code\n country_code character varying(3) NOT NULL, -- ISO country code (e.g., USA, CAN)\n phone_number character varying(30), -- main contact phone\n email_address character varying(255), -- main contact email\n property_type character varying(50) NOT NULL, -- e.g., Hotel, Resort, B&B, Motel\n star_rating numeric(2,1), -- star rating (e.g., 4.5)\n timezone character varying(64) NOT NULL, -- IANA timezone ID (e.g., America/New_York)\n manager_staff_id character varying(64), -- FK to staff table for the general manager\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 (property_id)\n)\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": "Can you help me get the total number of operational platforms across all stations?"}, {"role": "assistant", "content": "db.platforms.countDocuments({ status: 'Operational' });"}], "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('platforms')\n// Optional: db.platforms.createIndex({ platform_id: 1 }, { unique: true })\n// Optional: db.platforms.createIndex({ station_id: 1 })\n{\n _id: ObjectId(),\n platform_id: \"plat_123\", // String (unique)\n station_id: \"station_xyz\", // String (references stations.station_id)\n platform_number: \"1A\", // String\n track_number: \"T1\", // String\n status: \"Operational\", // String ('Operational', 'Maintenance', 'Closed')\n length_meters: 250.50, // Decimal128 or Double\n accessible: true // Boolean\n}\n// db.createCollection('routes')\n// Optional: db.routes.createIndex({ route_id: 1 }, { unique: true })\n{\n _id: ObjectId(),\n route_id: \"route_ne_corr\", // String (unique)\n route_name: \"Northeast Corridor\", // String\n description: \"High-speed rail linking Boston and Washington D.C.\", // String\n origin_station_id: \"station_bos\", // String (references stations.station_id)\n destination_station_id: \"station_was\", // String (references stations.station_id)\n is_active: true // Boolean\n}\n// db.createCollection('route_stations')\n// Optional: db.route_stations.createIndex({ route_station_id: 1 }, { unique: true })\n// Optional: db.route_stations.createIndex({ route_id: 1, sequence_order: 1 }, { unique: true })\n{\n _id: ObjectId(),\n route_station_id: \"rs_ne_1\", // String (unique)\n route_id: \"route_ne_corr\", // String (references routes.route_id)\n station_id: \"station_bos\", // String (references stations.station_id)\n sequence_order: 1, // Int32\n distance_from_previous_km: null, // Decimal128 or Double (null for first stop)\n typical_stop_duration_minutes: null // Int32 (null for origin/destination or if no stop)\n}\n// --- OR --- Embed within the Route document:\n// {\n// _id: ObjectId(), route_id: \"route_ne_corr\", ...,\n// stations: [\n// { station_id: \"station_bos\", sequence_order: 1, distance_from_previous_km: null, typical_stop_duration_minutes: null },\n// { station_id: \"station_pvd\", sequence_order: 2, distance_from_previous_km: 70.5, typical_stop_duration_minutes: 5 },\n// ...\n// ]\n// }\n// db.createCollection('schedules')\n// Optional: db.schedules.createIndex({ schedule_id: 1 }, { unique: true })\n// Optional: db.schedules.createIndex({ route_id: 1, departure_datetime: 1 })\n{\n _id: ObjectId(),\n schedule_id: \"sched_1122\", // String (unique)\n train_id: \"train_789\", // String (references trains.train_id)\n route_id: \"route_ne_corr\", // String (references routes.route_id)\n departure_datetime: ISODate(\"2024-05-10T08:00:00-04:00\"), // Date (with timezone)\n arrival_datetime: ISODate(\"2024-05-10T15:30:00-04:00\"), // Date (with timezone)\n status: \"Scheduled\", // String ('Scheduled', 'On Time', 'Delayed', 'Cancelled', 'Arrived')\n notes: \"Track work expected near Philadelphia\" // String\n}\n// db.createCollection('schedule_stops')\n// Optional: db.schedule_stops.createIndex({ stop_id: 1 }, { unique: true })\n// Optional: db.schedule_stops.createIndex({ schedule_id: 1, sequence_order: 1 }, { unique: true })\n{\n _id: ObjectId(),\n stop_id: \"stop_sched1122_1\", // String (unique)\n schedule_id: \"sched_1122\", // String (references schedules.schedule_id)\n station_id: \"station_bos\", // String (references stations.station_id)\n platform_id: \"plat_bos_3\", // String (references platforms.platform_id, nullable)\n sequence_order: 1, // Int32\n scheduled_arrival_time: null, // Date\n scheduled_departure_time: ISODate(\"2024-05-10T08:00:00-04:00\"), // Date\n actual_arrival_time: null, // Date\n actual_departure_time: ISODate(\"2024-05-10T08:01:00-04:00\"), // Date\n status: \"On Time\" // String\n}\n// --- OR --- Embed within the Schedule document using an array 'stops'\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// db.createCollection('staff')\n// Optional: db.staff.createIndex({ staff_id: 1 }, { unique: true })\n// Optional: db.staff.createIndex({ employee_number: 1 }, { unique: true })\n// Optional: db.staff.createIndex({ contact_email: 1 }, { unique: true, sparse: true })\n{\n _id: ObjectId(),\n staff_id: \"staff_mno\", // String (unique)\n first_name: \"Bob\", // String\n last_name: \"Jones\", // String\n role: \"Conductor\", // String\n primary_station_id: null, // String (references stations.station_id, nullable)\n employee_number: \"E12345\", // String (unique)\n hire_date: ISODate(\"2018-06-01\"), // Date\n contact_email: \"bob.jones@example-rail.com\", // String (unique, sparse)\n contact_phone: \"+15559876543\", // String\n is_active: true // Boolean\n}\n"} {"conversations": [{"role": "user", "content": "Show me the number of guests for each city they reside in."}, {"role": "assistant", "content": "SELECT city, count(*) AS guest_count FROM hospitality_technology.guests WHERE city IS NOT NULL GROUP BY city;"}, {"role": "user", "content": "Now, only show cities with more than 10 guests and order the results by the guest count in descending order."}, {"role": "assistant", "content": "SELECT city, count(*) AS guest_count FROM hospitality_technology.guests WHERE city IS NOT NULL GROUP BY city HAVING count(*) > 10 ORDER BY guest_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 )\n"} {"conversations": [{"role": "user", "content": "List all vehicles and their last maintenance service date along with the odometer reading, including only those that have not had a fuel refill in the past 30 days."}, {"role": "assistant", "content": "SELECT m.vehicle_id,\n m.last_service_date,\n m.last_odometer\nFROM (\n SELECT l.vehicle_id,\n MAX(l.service_date) AS last_service_date,\n (SELECT odometer_reading\n FROM transportation.maintenance_logs\n WHERE vehicle_id = l.vehicle_id\n ORDER BY service_date DESC\n LIMIT 1) AS last_odometer\n FROM transportation.maintenance_logs l\n GROUP BY l.vehicle_id\n) AS m\nLEFT JOIN (\n SELECT fl.vehicle_id,\n MAX(fl.log_timestamp) AS last_fuel_date\n FROM transportation.fuel_logs fl\n GROUP BY fl.vehicle_id\n) AS f ON m.vehicle_id = f.vehicle_id\nWHERE COALESCE(f.last_fuel_date, '1900-01-01'::timestamp) < NOW() - INTERVAL '30 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.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.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 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.fuel_logs ( fuel_log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, trip_id character varying(64), log_timestamp timestamp with time zone NOT NULL, fuel_type character varying(32) NOT NULL, quantity numeric(10, 3) NOT NULL, unit character varying(16) NOT NULL, cost_per_unit numeric(8, 4), total_cost numeric(10, 2) NOT NULL, odometer_reading integer, location_id character varying(64), PRIMARY KEY (fuel_log_id) )\nCREATE TABLE transportation.passengers ( passenger_id character varying(64) NOT NULL, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32) UNIQUE, date_of_birth date, loyalty_program_id character varying(64), created_at timestamp with time zone NOT NULL, PRIMARY KEY (passenger_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": "List users who have received notifications triggered by another user (non-system notifications). Show the recipient username, notification type, and the sender username."}, {"role": "assistant", "content": "SELECT T1.username AS recipient_username, T2.notification_type, T3.username AS sender_username FROM social_media.users AS T1 JOIN social_media.notifications AS T2 ON T1.user_id = T2.recipient_user_id JOIN social_media.users AS T3 ON T2.sender_user_id = T3.user_id;"}, {"role": "user", "content": "Refine the list from Turn 1 to only include notifications of type 'follow' or 'mention'."}, {"role": "assistant", "content": "SELECT T1.username AS recipient_username, T2.notification_type, T3.username AS sender_username FROM social_media.users AS T1 JOIN social_media.notifications AS T2 ON T1.user_id = T2.recipient_user_id JOIN social_media.users AS T3 ON T2.sender_user_id = T3.user_id WHERE T2.notification_type IN ('follow', 'mention');"}, {"role": "user", "content": "Further filter to only include notifications created in 2024 and order the results by notification creation time descending."}, {"role": "assistant", "content": "SELECT T1.username AS recipient_username, T2.notification_type, T3.username AS sender_username FROM social_media.users AS T1 JOIN social_media.notifications AS T2 ON T1.user_id = T2.recipient_user_id JOIN social_media.users AS T3 ON T2.sender_user_id = T3.user_id WHERE T2.notification_type IN ('follow', 'mention') AND EXTRACT(YEAR FROM T2.created_at) = 2024 ORDER BY T2.created_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.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": "Show me the count of service orders for each distinct status."}, {"role": "assistant", "content": "SELECT status, COUNT(order_id) FROM hospitality_technology.service_orders GROUP BY status;"}, {"role": "user", "content": "Also, include the total quantity of items ordered for each status."}, {"role": "assistant", "content": "SELECT status, COUNT(order_id), SUM(quantity) FROM hospitality_technology.service_orders GROUP BY status;"}], "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 character varying(64) NOT NULL, property_id character varying(64) NOT NULL, guest_id character varying(64) NOT NULL, room_id character varying(64), room_type_id character varying(64) NOT NULL, check_in_date date NOT NULL, check_out_date date NOT NULL, actual_check_in_ts timestamp with time zone, actual_check_out_ts timestamp with time zone, num_adults integer NOT NULL, num_children integer DEFAULT 0, status character varying(50) NOT NULL, booking_source character varying(100), rate_plan_id character varying(64), total_amount numeric(12, 2), amount_paid numeric(12, 2) DEFAULT 0.00, special_requests text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (reservation_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.service_orders ( order_id text PRIMARY KEY, reservation_id text, guest_id text, service_id text, staff_id_ordered text, staff_id_delivered text, order_timestamp timestamp, delivery_timestamp timestamp, quantity int, unit_price numeric, total_price numeric, status text, notes text, bill_id text )\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": "特定の組み立てラインに割り当てられた従業員とそのラインの手順情報を取得したいです。従業員ID、名前、職種と手順名、手順番号を含めてください。"}, {"role": "assistant", "content": "db.employees.aggregate([\n { $match: { assigned_line_id: '' } },\n { $lookup: {\n from: 'assembly_steps',\n localField: 'assigned_line_id',\n foreignField: 'line_id',\n as: 'steps'\n } },\n { $unwind: '$steps' },\n { $project: {\n employee_id: 1,\n first_name: 1,\n last_name: 1,\n job_title: 1,\n 'steps.step_name': 1,\n 'steps.step_number': 1,\n _id: 0\n } },\n { $sort: { 'steps.step_number': 1 } }\n])"}, {"role": "user", "content": "従業員の雇用ステータスが「Active」のデータだけに絞り込むことはできますか？"}, {"role": "assistant", "content": "db.employees.aggregate([\n { $match: { \n assigned_line_id: '',\n employment_status: 'Active'\n } },\n { $lookup: {\n from: 'assembly_steps',\n localField: 'assigned_line_id',\n foreignField: 'line_id',\n as: 'steps'\n } },\n { $unwind: '$steps' },\n { $project: {\n employee_id: 1,\n first_name: 1,\n last_name: 1,\n job_title: 1,\n 'steps.step_name': 1,\n 'steps.step_number': 1,\n _id: 0\n } },\n { $sort: { 'steps.step_number': 1 } }\n])"}, {"role": "user", "content": "手順の必要なスキルレベルが「Junior Technician」以上のものだけを表示するようにできますか？"}, {"role": "assistant", "content": "db.employees.aggregate([\n { $match: { \n assigned_line_id: '',\n employment_status: 'Active'\n } },\n { $lookup: {\n from: 'assembly_steps',\n localField: 'assigned_line_id',\n foreignField: 'line_id',\n as: 'steps'\n } },\n { $unwind: '$steps' },\n { $match: { 'steps.required_skill_level': { $in: ['Junior Technician', 'Senior Technician'] } } },\n { $project: {\n employee_id: 1,\n first_name: 1,\n last_name: 1,\n job_title: 1,\n 'steps.step_name': 1,\n 'steps.step_number': 1,\n _id: 0\n } },\n { $sort: { 'steps.step_number': 1 } }\n])"}, {"role": "user", "content": "最後に、従業員の雇用日も結果に含めて、雇用日順に並べ替えてください。"}, {"role": "assistant", "content": "db.employees.aggregate([\n { $match: { \n assigned_line_id: '',\n employment_status: 'Active'\n } },\n { $lookup: {\n from: 'assembly_steps',\n localField: 'assigned_line_id',\n foreignField: 'line_id',\n as: 'steps'\n } },\n { $unwind: '$steps' },\n { $match: { 'steps.required_skill_level': { $in: ['Junior Technician', 'Senior Technician'] } } },\n { $project: {\n employee_id: 1,\n first_name: 1,\n last_name: 1,\n job_title: 1,\n hire_date: 1,\n 'steps.step_name': 1,\n 'steps.step_number': 1,\n _id: 0\n } },\n { $sort: { hire_date: -1, 'steps.step_number': 1 } }\n])"}], "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\nCollection 'assembly_steps'. Document structure: { _id: , step_id: String, line_id: String (reference), step_number: NumberInt, step_name: String, description: String, standard_duration_hours: Decimal128, required_skill_level: String, workstation: String }. Required: step_id, line_id, step_number, step_name. Index on line_id, step_number.\nCollection 'employees'. Document structure: { _id: , employee_id: String, first_name: String, last_name: String, job_title: String, skill_certifications: [String], hire_date: ISODate, assigned_line_id: String (reference, optional), employment_status: String, supervisor_employee_id: String (reference, optional) }. Required: employee_id, first_name, last_name, job_title, hire_date, employment_status.\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": "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": "Find pairs of distinct routes that share the same destination location but start from different origins. Include the route ID and route number for both routes and the shared destination 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.destination_location_id AS shared_destination_location_id\nFROM transportation.routes AS r1\nJOIN transportation.routes AS r2\n ON r1.destination_location_id = r2.destination_location_id\n AND r1.route_id < r2.route_id\nWHERE\n r1.origin_location_id != r2.origin_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": "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 all rooms that include 'Kitchenette' in their features, showing the room number, property ID, and floor."}, {"role": "assistant", "content": "SELECT room_number, property_id, floor\nFROM hospitality_technology.rooms\nWHERE features LIKE '%Kitchenette%';"}, {"role": "user", "content": "Please also show only those rooms that are currently available."}, {"role": "assistant", "content": "SELECT room_number, property_id, floor\nFROM hospitality_technology.rooms\nWHERE features LIKE '%Kitchenette%' AND 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.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 )\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 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 all unique service categories and the count of services in each category."}, {"role": "assistant", "content": "SELECT category, COUNT(service_id) FROM hospitality_technology.services GROUP BY category;"}, {"role": "user", "content": "Only include categories with more than 10 services and order the results by the count descending."}, {"role": "assistant", "content": "SELECT category, COUNT(service_id) FROM hospitality_technology.services GROUP BY category HAVING COUNT(service_id) > 10 ORDER BY COUNT(service_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 hospitality_technology.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\nCREATE TABLE hospitality_technology.services ( service_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, service_name character varying(150) NOT NULL, description text, category character varying(100), price numeric(10, 2) NOT NULL, unit character varying(30), is_available boolean NOT NULL DEFAULT true, department character varying(100), PRIMARY KEY (service_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_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": "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 name and symbol for all assets that do not have a corresponding entry with the key 'website' in the metadata table."}, {"role": "assistant", "content": "SELECT T1.name , T1.symbol FROM trading_platform.assets AS T1 LEFT JOIN trading_platform.metadata AS T2 ON T1.asset_id = T2.asset_id AND T2.key = 'website' WHERE T2.metadata_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 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 (\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 ( asset_id text PRIMARY KEY, name text, symbol text, type text )\nCREATE TABLE trading_platform.utxos ( utxo_id.text, transaction_id.text, output_index.integer, address.text, amount.numeric, spent.boolean )\nCREATE TABLE trading_platform.dapps ( dapp_id.text, name.text, description.text, url.text )\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)\n"} {"conversations": [{"role": "user", "content": "Get the number of agents grouped by status. Return status and agent_count."}, {"role": "assistant", "content": "SELECT status,\n COUNT(*) AS agent_count\n FROM insurance.agents\n GROUP BY status;"}], "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": "For each claim, show the corresponding product_type of the insurance product for the related policy."}, {"role": "assistant", "content": "SELECT cl.claim_id, ip.product_type\nFROM insurance.claims cl\nJOIN insurance.policies p ON cl.policy_id = p.policy_id\nJOIN insurance.insurance_products ip ON p.product_id = ip.product_id;"}, {"role": "user", "content": "Sorry, there is no policies table, I got an error. Can you try joining claims to insurance_products another way?"}, {"role": "assistant", "content": "-- Unable to join directly since there is no 'policies' table connecting claims to insurance_products. If policy_id equals product_id, you may try:\nSELECT claim_id, policy_id, product_type\nFROM insurance.claims\nJOIN insurance.insurance_products ON claims.policy_id = insurance_products.product_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.customers ( customer_id.text, 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.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 )\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.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 pairs of transactions where both transactions have the same nonce and from_address, but different transaction_id. Show both transaction IDs, the shared from_address, shared nonce, and their block numbers."}, {"role": "assistant", "content": "SELECT t1.transaction_id AS transaction_id_1, t2.transaction_id AS transaction_id_2, t1.from_address, t1.nonce, t1.block_number AS block_number_1, t2.block_number AS block_number_2\nFROM web3.transactions t1\nJOIN web3.transactions t2\n ON t1.from_address = t2.from_address\n AND t1.nonce = t2.nonce\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 (\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)\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": "For each ERC20 token, how many unique wallets currently hold them? Show the contract address and unique wallet count."}, {"role": "assistant", "content": "SELECT contract_address, COUNT(DISTINCT wallet_address) AS unique_wallet_count FROM erc20_balances GROUP BY contract_address;"}, {"role": "user", "content": "Add the token symbol and name for each contract by joining to the token_prices_latest table."}, {"role": "assistant", "content": "SELECT e.contract_address, COUNT(DISTINCT e.wallet_address) AS unique_wallet_count, t.symbol, t.address AS token_name FROM erc20_balances e LEFT JOIN token_prices_latest t ON e.contract_address = t.address GROUP BY e.contract_address, t.symbol, t.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 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 (\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\n amount varchar NOT NULL, -- Wallet's on-chain balance at the corresponding block height\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 7200))\n)\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_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 varchar NOT NULL, status varchar NOT NULL, collection_type varchar NOT NULL, package_id varchar NOT NULL, previous_transaction varchar NOT NULL, display varchar NOT NULL, owner varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE nft_metadata ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer NOT NULL, pk integer NOT NULL )\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 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 (\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_info_bitcoin ( 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 )\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 )\n"} {"conversations": [{"role": "user", "content": "For each narrative in token_basic_info, compute the total liquidity and count of tokens from token_dexpool_info. Show narrative, total_liquidity, and token_count."}, {"role": "assistant", "content": "SELECT tbi.narrative,\n SUM(td.liquidity) AS total_liquidity,\n COUNT(DISTINCT td.token_symbol) AS token_count\nFROM token_basic_info tbi\nJOIN token_dexpool_info td\n ON tbi.token_address = td.token_address\nGROUP BY tbi.narrative;"}, {"role": "user", "content": "Include only tokens where volume_24h > 500000 and price_change_percentage_6h > 0."}, {"role": "assistant", "content": "SELECT tbi.narrative,\n SUM(td.liquidity) AS total_liquidity,\n COUNT(DISTINCT td.token_symbol) AS token_count\nFROM token_basic_info tbi\nJOIN token_dexpool_info td\n ON tbi.token_address = td.token_address\nWHERE td.volume_24h > 500000\n AND td.price_change_percentage_6h > 0\nGROUP BY tbi.narrative;"}, {"role": "user", "content": "Now join narrative_info to also get trend_rank and narrative volume_24h."}, {"role": "assistant", "content": "SELECT tbi.narrative,\n ni.trend_rank,\n ni.volume_24h AS narrative_volume,\n SUM(td.liquidity) AS total_liquidity,\n COUNT(DISTINCT td.token_symbol) AS token_count\nFROM token_basic_info tbi\nJOIN token_dexpool_info td\n ON tbi.token_address = td.token_address\nJOIN narrative_info ni\n ON tbi.narrative = ni.narrative\nWHERE td.volume_24h > 500000\n AND td.price_change_percentage_6h > 0\nGROUP BY tbi.narrative, ni.trend_rank, ni.volume_24h;"}, {"role": "user", "content": "Finally, only keep narratives where trend_rank <= 10 and order by total_liquidity descending."}, {"role": "assistant", "content": "SELECT tbi.narrative,\n ni.trend_rank,\n ni.volume_24h AS narrative_volume,\n SUM(td.liquidity) AS total_liquidity,\n COUNT(DISTINCT td.token_symbol) AS token_count\nFROM token_basic_info tbi\nJOIN token_dexpool_info td\n ON tbi.token_address = td.token_address\nJOIN narrative_info ni\n ON tbi.narrative = ni.narrative\nWHERE td.volume_24h > 500000\n AND td.price_change_percentage_6h > 0\n AND ni.trend_rank <= 10\nGROUP BY tbi.narrative, ni.trend_rank, ni.volume_24h\nORDER BY total_liquidity 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 character varying(32) NOT NULL, project_id character varying(32) NOT NULL, project_name character varying(128) NOT NULL, rounds_name character varying(32), investment_value numeric(38,14), investment_date character varying(128), introduction character varying(128), valuation numeric(38,14) )\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 \"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\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 \"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_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 )\nCREATE TABLE smart_money_token_inflow ( token_address text, token_symbol text, token_amount numeric, usd_value numeric, avg_price numeric, type numeric, address_amount numeric, narrative text, chain text )\n"} {"conversations": [{"role": "user", "content": "How many achievements were unlocked in total in the year 2023?"}, {"role": "assistant", "content": "SELECT COUNT(*) FROM gaming_technology.player_achievements WHERE unlocked_at >= '2023-01-01 00:00:00+00' AND unlocked_at < '2024-01-01 00:00:00+00';"}, {"role": "user", "content": "Now show the count of distinct players who unlocked achievements in 2023."}, {"role": "assistant", "content": "SELECT COUNT(DISTINCT player_id) FROM gaming_technology.player_achievements WHERE unlocked_at >= '2023-01-01 00:00:00+00' AND unlocked_at < '2024-01-01 00:00:00+00';"}], "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.player_achievements ( player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, achievement_id uuid NOT NULL, unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (player_achievement_id), UNIQUE (player_id, achievement_id) )\n"} {"conversations": [{"role": "user", "content": "How many insurance policies does each patient have? Return patient_id and policy_count."}, {"role": "assistant", "content": "SELECT patient_id,\n COUNT(*) AS policy_count\nFROM healthcare.patient_insurance\nGROUP BY patient_id;"}, {"role": "user", "content": "Only show patients with more than 2 policies and order by policy_count descending."}, {"role": "assistant", "content": "SELECT patient_id,\n COUNT(*) AS policy_count\nFROM healthcare.patient_insurance\nGROUP BY patient_id\nHAVING COUNT(*) > 2\nORDER BY policy_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.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.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.medications ( medication_id.text, medication_name.text, generic_name.text, manufacturer.text, ndc_code.text, description.text )\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": "List every diagnosis description paired with every insurance plan's website."}, {"role": "assistant", "content": "SELECT T1.description, T2.website FROM healthcare.diagnoses AS T1 CROSS JOIN healthcare.insurance_plans AS T2;"}, {"role": "user", "content": "Only include chronic diagnoses and plans whose website ends with '.org'."}, {"role": "assistant", "content": "SELECT T1.description, T2.website FROM healthcare.diagnoses AS T1 CROSS JOIN healthcare.insurance_plans AS T2 WHERE T1.is_chronic = true AND T2.website LIKE '%.org';"}], "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 ( 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.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 number of drivers hired each year? Provide the hire_year and driver_count."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM hire_date) AS hire_year,\n COUNT(*) AS driver_count\nFROM transportation.drivers\nGROUP BY EXTRACT(YEAR FROM hire_date);"}, {"role": "user", "content": "Now only include years where driver_count > 3 and order the results by driver_count DESC."}, {"role": "assistant", "content": "SELECT hire_year, driver_count\nFROM (\n SELECT EXTRACT(YEAR FROM hire_date) AS hire_year,\n COUNT(*) AS driver_count\n FROM transportation.drivers\n GROUP BY EXTRACT(YEAR FROM hire_date)\n) sub\nWHERE driver_count > 3\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": "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": "I want to see all time entries where the description contains the word 'draft' and that have not been billed yet."}, {"role": "assistant", "content": "SELECT *\nFROM legal_services.time_entries\nWHERE description ILIKE '%draft%'\n AND is_billed = false;"}, {"role": "user", "content": "Only include entries that were logged in June 2024."}, {"role": "assistant", "content": "SELECT *\nFROM legal_services.time_entries\nWHERE description ILIKE '%draft%'\n AND is_billed = false\n AND date_worked BETWEEN '2024-06-01' AND '2024-06-30';"}, {"role": "user", "content": "Now only show entries that are billable and where hours_spent is greater than 2."}, {"role": "assistant", "content": "SELECT *\nFROM legal_services.time_entries\nWHERE description ILIKE '%draft%'\n AND is_billed = false\n AND is_billable = true\n AND date_worked BETWEEN '2024-06-01' AND '2024-06-30'\n AND hours_spent > 2;"}, {"role": "user", "content": "Please only include the entry_id, lawyer_id, date_worked, and hours_spent in the output."}, {"role": "assistant", "content": "SELECT entry_id, lawyer_id, date_worked, hours_spent\nFROM legal_services.time_entries\nWHERE description ILIKE '%draft%'\n AND is_billed = false\n AND is_billable = true\n AND date_worked BETWEEN '2024-06-01' AND '2024-06-30'\n AND hours_spent > 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 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 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": "Count the number of logs for each action type."}, {"role": "assistant", "content": "SELECT action,\n COUNT(*) AS count\nFROM trading_platform.logs\nGROUP BY action;"}], "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.logs ( log_id text PRIMARY KEY, user_id text, action text, details text, logged_at timestamp )\n"} {"conversations": [{"role": "user", "content": "How many claims were reported in the last 90 days?"}, {"role": "assistant", "content": "SELECT COUNT(*) FROM claims WHERE reported_date >= 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 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 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.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 )\nCREATE TABLE insurance.premium_payments ( payment_id text PRIMARY KEY, 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 )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id.text, 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 the plan_id, plan_name, and plan_type for all insurance plans where the insurance_provider is 'Humana'."}, {"role": "assistant", "content": "SELECT\n plan_id,\n plan_name,\n plan_type\nFROM healthcare.insurance_plans\nWHERE\n insurance_provider = 'Humana';"}], "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 (\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.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.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 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)\n"} {"conversations": [{"role": "user", "content": "List all unique document types available in the system."}, {"role": "assistant", "content": "SELECT DISTINCT document_type FROM insurance.claim_documents;"}], "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": "Can you narrow this down to only show cases where the case type is 'Criminal'?"}, {"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';"}], "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": "List the first name and last name of citizens along with the type and verification status of their documents."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T2.document_type, T2.verification_status FROM government_services.citizens AS T1 JOIN government_services.documents 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.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.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 ( 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.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)\n"} {"conversations": [{"role": "user", "content": "List all events with their contract IDs and emitted timestamps, sorted by the most recent events first."}, {"role": "assistant", "content": "SELECT event_id, contract_id, emitted_at FROM web3.events ORDER BY emitted_at DESC;"}, {"role": "user", "content": "Actually, I only want to see events from contracts that start with '0x1234'."}, {"role": "assistant", "content": "SELECT event_id, contract_id, emitted_at FROM web3.events WHERE contract_id LIKE '0x1234%' ORDER BY emitted_at DESC;"}, {"role": "user", "content": "There's a typo in your SQL, it should be 'contract_id' not 'contract_id'. Also, add the event_name to the results."}, {"role": "assistant", "content": "SELECT event_id, contract_id, event_name, emitted_at FROM web3.events WHERE contract_id LIKE '0x1234%' ORDER BY emitted_at DESC;"}, {"role": "user", "content": "Now filter to only show events emitted in the last 24 hours."}, {"role": "assistant", "content": "SELECT event_id, contract_id, event_name, emitted_at FROM web3.events WHERE contract_id LIKE '0x1234%' AND emitted_at >= NOW() - INTERVAL '24 hours' 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 ( event_id.text, contract_id.text, event_name.text, data.text, emitted_at.timestamp, transaction_id.text, log_index.integer )\n"} {"conversations": [{"role": "user", "content": "List all ERC20 tokens from the `token_metas` table that have a total supply greater than 1 followed by 21 zeros. Show their contract address, symbol, name, and total supply."}, {"role": "assistant", "content": "SELECT contract_address, symbol, name, total_supply FROM token_metas WHERE is_erc20 = 1 AND CAST(total_supply AS DECIMAL) > 1000000000000000000000;"}, {"role": "user", "content": "Okay, for those tokens, can you also include the number of unique wallet addresses that hold each token? Only show tokens with more than 500 unique holders."}, {"role": "assistant", "content": "SELECT tm.contract_address, tm.symbol, tm.name, tm.total_supply, COUNT(DISTINCT eb.wallet_address) AS unique_holder_count FROM token_metas tm JOIN erc20_balances eb ON tm.contract_address = eb.contract_address WHERE tm.is_erc20 = 1 AND CAST(tm.total_supply AS DECIMAL) > 1000000000000000000000 GROUP BY tm.contract_address, tm.symbol, tm.name, tm.total_supply HAVING COUNT(DISTINCT eb.wallet_address) > 500;"}, {"role": "user", "content": "Great, now add the latest USD price and decimals for these tokens by joining with the `token_prices_latest` table."}, {"role": "assistant", "content": "SELECT tm.contract_address, tm.symbol, tm.name, tm.total_supply, tpl.usd_price, tm.decimals, COUNT(DISTINCT eb.wallet_address) AS unique_holder_count FROM token_metas tm JOIN erc20_balances eb ON tm.contract_address = eb.contract_address JOIN token_prices_latest tpl ON tm.contract_address = tpl.contract_address WHERE tm.is_erc20 = 1 AND CAST(tm.total_supply AS DECIMAL) > 1000000000000000000000 GROUP BY tm.contract_address, tm.symbol, tm.name, tm.total_supply, tpl.usd_price, tm.decimals HAVING COUNT(DISTINCT eb.wallet_address) > 500;"}, {"role": "user", "content": "Please filter the results to only include tokens where the latest price is greater than 0.1 USD, order by the number of unique holders descending, and limit the output to the top 10 tokens."}, {"role": "assistant", "content": "SELECT tm.contract_address, tm.symbol, tm.name, tm.total_supply, tpl.usd_price, tm.decimals, COUNT(DISTINCT eb.wallet_address) AS unique_holder_count FROM token_metas tm JOIN erc20_balances eb ON tm.contract_address = eb.contract_address JOIN token_prices_latest tpl ON tm.contract_address = tpl.contract_address WHERE tm.is_erc20 = 1 AND CAST(tm.total_supply AS DECIMAL) > 1000000000000000000000 AND tpl.usd_price > 0.1 GROUP BY tm.contract_address, tm.symbol, tm.name, tm.total_supply, tpl.usd_price, tm.decimals HAVING COUNT(DISTINCT eb.wallet_address) > 500 ORDER BY unique_holder_count 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 ( 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 erc20_balances ( block_number bigint, contract_address text, wallet_address text, amount text, pk text )\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 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_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_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\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_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": "List all unique claim handler IDs present in the claims table."}, {"role": "assistant", "content": "SELECT DISTINCT claim_handler_id FROM insurance.claims WHERE claim_handler_id 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 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 )\n"} {"conversations": [{"role": "user", "content": "Find pairs of achievements within each game where the point difference is exactly 10."}, {"role": "assistant", "content": "SELECT a1.achievement_id AS ach1_id,\n a2.achievement_id AS ach2_id,\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\nWHERE a1.achievement_id < a2.achievement_id\n AND ABS(a1.points - a2.points) = 10;"}, {"role": "user", "content": "Include the game_id and show both achievement names labeled ach1 and ach2."}, {"role": "assistant", "content": "SELECT a1.game_id,\n a1.name AS ach1_name,\n a2.name AS ach2_name,\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\nWHERE a1.achievement_id < a2.achievement_id\n AND ABS(a1.points - a2.points) = 10;"}, {"role": "user", "content": "Now restrict to pairs where both achievements are visible and the difference is at least 15."}, {"role": "assistant", "content": "SELECT a1.game_id,\n a1.name AS ach1_name,\n a2.name AS ach2_name,\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\nWHERE a1.achievement_id < a2.achievement_id\n AND a1.hidden = FALSE\n AND a2.hidden = FALSE\n AND ABS(a1.points - a2.points) >= 15;"}, {"role": "user", "content": "Order the result by game_id ascending and point_diff descending."}, {"role": "assistant", "content": "SELECT a1.game_id,\n a1.name AS ach1_name,\n a2.name AS ach2_name,\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\nWHERE a1.achievement_id < a2.achievement_id\n AND a1.hidden = FALSE\n AND a2.hidden = FALSE\n AND ABS(a1.points - a2.points) >= 15\nORDER BY a1.game_id ASC,\n point_diff 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.achievements ( achievement_id.uuid, game_id.uuid, name.text, description.text, icon_url.text, points.integer, hidden.boolean )\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": "What is the average price of tokens held by Binance exchange across all chains?"}, {"role": "assistant", "content": "SELECT AVG(price) as average_price FROM cex_token_balance WHERE exchange = 'Binance';"}], "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 cex_token_balance ( snapshot_time character varying(32) NOT NULL, chain character varying(128) NOT NULL, address character varying(128) NOT NULL, exchange character varying(512) NOT NULL, token_address character varying(128) NOT NULL, token_symbol character varying(512), balance numeric(38,10), usd_value numeric(38,14), price double precision )\n"} {"conversations": [{"role": "user", "content": "Find all policies that were cancelled due to 'Non-payment'. Show the policy number, cancellation date, and premium amount for these policies."}, {"role": "assistant", "content": "SELECT policy_number , cancellation_date , premium_amount FROM insurance.policies WHERE status = 'Cancelled' AND cancellation_reason = 'Non-payment'"}], "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)\n"} {"conversations": [{"role": "user", "content": "Find all nodes that were last seen in the last 7 days, along with their IP addresses and ports."}, {"role": "assistant", "content": "SELECT node_id, ip_address, port FROM blockchain.nodes WHERE last_seen >= NOW() - INTERVAL '7 days';"}, {"role": "user", "content": "Now filter these results to only show nodes with port numbers between 8000 and 9000."}, {"role": "assistant", "content": "SELECT node_id, ip_address, port FROM blockchain.nodes WHERE last_seen >= NOW() - INTERVAL '7 days' AND port BETWEEN 8000 AND 9000;"}, {"role": "user", "content": "How many unique IP addresses are there among these active nodes?"}, {"role": "assistant", "content": "SELECT COUNT(DISTINCT ip_address) FROM blockchain.nodes WHERE last_seen >= NOW() - INTERVAL '7 days' AND port BETWEEN 8000 AND 9000;"}, {"role": "user", "content": "Can you show me the count of nodes for each unique IP address?"}, {"role": "assistant", "content": "SELECT ip_address, COUNT(node_id) AS node_count FROM blockchain.nodes WHERE last_seen >= NOW() - INTERVAL '7 days' AND port BETWEEN 8000 AND 9000 GROUP BY ip_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 blockchain.blocks ( block_id text, previous_block_id text, timestamp timestamp, nonce integer, merkle_root text, difficulty integer )\nCREATE TABLE blockchain.transactions (\n transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n block_id character varying(64) NOT NULL, -- identifier of the block containing the transaction\n sender_address character varying(128) NOT NULL, -- address of the sender\n receiver_address character varying(128) NOT NULL, -- address of the receiver\n amount numeric(38,14) NOT NULL, -- amount transferred\n timestamp timestamp NOT NULL, -- time when the transaction was created\n signature text NOT NULL, -- digital signature of the transaction\n PRIMARY KEY (transaction_id)\n)\nCREATE TABLE blockchain.addresses ( address_id text PRIMARY KEY, public_key text, balance numeric )\nCREATE TABLE blockchain.nodes (\n node_id character varying(64) NOT NULL, -- unique identifier for the node\n ip_address character varying(15) NOT NULL, -- IP address of the node\n port integer NOT NULL, -- port number of the node\n last_seen timestamp NOT NULL, -- last time the node was active\n PRIMARY KEY (node_id)\n)\nCREATE TABLE blockchain.smart_contracts ( contract_id text PRIMARY KEY, creator_address text, code text, timestamp timestamp )\n"} {"conversations": [{"role": "user", "content": "List the first and last name of each citizen along with the city and state of the service location for their agency."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, sl.city, sl.state\nFROM government_services.citizens c\nJOIN government_services.payments p ON c.citizen_id = p.citizen_id\nJOIN government_services.employees e ON p.application_id IS NOT NULL AND e.agency_id IS NOT NULL\nJOIN government_services.service_locations sl ON e.agency_id = sl.agency_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.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.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 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 )\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": "Can you show the total quantity of all in-game items held by each player?"}, {"role": "assistant", "content": "SELECT player_id, SUM(quantity) AS total_quantity\nFROM gaming_technology.player_inventory\nGROUP BY player_id;"}, {"role": "user", "content": "I'd like to see only players whose total quantity is over 20."}, {"role": "assistant", "content": "SELECT player_id, SUM(quantity) AS total_quantity\nFROM gaming_technology.player_inventory\nGROUP BY player_id\nHAVING SUM(quantity) > 20;"}, {"role": "user", "content": "Also, can you include the number of different unique items each player owns?"}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT item_id) AS unique_items, SUM(quantity) AS total_quantity\nFROM gaming_technology.player_inventory\nGROUP BY player_id\nHAVING SUM(quantity) > 20;"}, {"role": "user", "content": "Order the final result by unique_items descending, then by total_quantity descending."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT item_id) AS unique_items, SUM(quantity) AS total_quantity\nFROM gaming_technology.player_inventory\nGROUP BY player_id\nHAVING SUM(quantity) > 20\nORDER BY unique_items DESC, total_quantity 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.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": "Which users have participated in conversations that are not group chats? Please show their usernames and the conversation IDs."}, {"role": "assistant", "content": "SELECT u.username, cp.conversation_id\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 = FALSE;"}, {"role": "user", "content": "Actually, can you show the time when they joined each conversation as well?"}, {"role": "assistant", "content": "SELECT u.username, cp.conversation_id, 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 = FALSE;"}, {"role": "user", "content": "Only include users who joined after March 1, 2024."}, {"role": "assistant", "content": "SELECT u.username, cp.conversation_id, 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 = FALSE\n AND cp.joined_at > '2024-03-01';"}], "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 (\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.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.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)\n"} {"conversations": [{"role": "user", "content": "List document names and versions for documents that share the same case_id, showing each pair of versions."}, {"role": "assistant", "content": "SELECT d1.case_id, d1.document_name AS doc_name_v1, d1.version AS version1, d2.document_name AS doc_name_v2, d2.version AS version2 FROM legal_services.documents d1 JOIN legal_services.documents d2 ON d1.case_id = d2.case_id AND d1.version < d2.version;"}, {"role": "user", "content": "Actually, I only want to compare the highest version against the second highest version per case."}, {"role": "assistant", "content": "SELECT d_prev.case_id, d_prev.document_name AS prev_doc, d_prev.version AS prev_version, d_latest.document_name AS latest_doc, d_latest.version AS latest_version FROM legal_services.documents d_latest JOIN legal_services.documents d_prev ON d_latest.case_id = d_prev.case_id AND d_prev.version = d_latest.version - 1 WHERE d_latest.version = (SELECT MAX(version) FROM legal_services.documents d WHERE d.case_id = d_latest.case_id);"}, {"role": "user", "content": "Also include the upload timestamps and restrict to cases with at least three versions."}, {"role": "assistant", "content": "SELECT d_latest.case_id, d_prev.document_name AS prev_doc, d_prev.upload_timestamp AS prev_upload, d_latest.document_name AS latest_doc, d_latest.upload_timestamp AS latest_upload FROM legal_services.documents d_latest JOIN legal_services.documents d_prev ON d_latest.case_id = d_prev.case_id AND d_prev.version = d_latest.version - 1 WHERE d_latest.version = (SELECT MAX(version) FROM legal_services.documents d WHERE d.case_id = d_latest.case_id) AND (SELECT COUNT(*) FROM legal_services.documents d2 WHERE d2.case_id = d_latest.case_id) >= 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.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)\n"} {"conversations": [{"role": "user", "content": "What is the ticket price for a journey on train number T4321?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to information about ticket prices for specific trains. The data I have is limited to train details such as model, manufacturer, capacity, and maintenance schedules. For ticket pricing, please consult the ticketing office or the official website."}], "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 ( train_id text PRIMARY KEY, train_number text UNIQUE, model text, manufacturer text, year_manufactured int, capacity int, status text, last_maintenance_date date, next_maintenance_date date )\n"} {"conversations": [{"role": "user", "content": "Provide the count of diagnoses by status."}, {"role": "assistant", "content": "SELECT status,\n COUNT(*) AS count\nFROM healthcare.diagnoses\nGROUP BY status;"}, {"role": "user", "content": "Now only include statuses with more than 10 diagnoses."}, {"role": "assistant", "content": "SELECT status,\n COUNT(*) AS count\nFROM healthcare.diagnoses\nGROUP BY status\nHAVING COUNT(*) > 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.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": "Find all assets that have metadata linking them to a DApp (where metadata value is a DApp ID), showing asset name, symbol, and the linked DApp name. Assume the metadata key used is 'linked_dapp_id'."}, {"role": "assistant", "content": "SELECT a.name AS asset_name, a.symbol, d.name AS dapp_name FROM trading_platform.assets a JOIN trading_platform.metadata m ON a.asset_id = m.asset_id JOIN trading_platform.dapps d ON m.value = d.dapp_id WHERE m.key = 'linked_dapp_id';"}, {"role": "user", "content": "Only show results for assets whose type is 'cryptocurrency'."}, {"role": "assistant", "content": "SELECT a.name AS asset_name, a.symbol, d.name AS dapp_name FROM trading_platform.assets a JOIN trading_platform.metadata m ON a.asset_id = m.asset_id JOIN trading_platform.dapps d ON m.value = d.dapp_id WHERE m.key = 'linked_dapp_id' AND a.type = 'cryptocurrency';"}, {"role": "user", "content": "The query didn't work, it returned no results. Maybe the key isn't exactly 'linked_dapp_id'. Can you find assets linked to DApps where the metadata value looks like a DApp ID (starts with 'dapp') and display the metadata key used as well?"}, {"role": "assistant", "content": "SELECT a.name AS asset_name, a.symbol, d.name AS dapp_name, m.key FROM trading_platform.assets a JOIN trading_platform.metadata m ON a.asset_id = m.asset_id JOIN trading_platform.dapps d ON m.value = d.dapp_id WHERE m.value LIKE 'dapp%';"}, {"role": "user", "content": "Okay, great, that worked. Now, only show assets where the metadata key used was 'associated_dapp' and order the results by asset name alphabetically."}, {"role": "assistant", "content": "SELECT a.name AS asset_name, a.symbol, d.name AS dapp_name, m.key FROM trading_platform.assets a JOIN trading_platform.metadata m ON a.asset_id = m.asset_id JOIN trading_platform.dapps d ON m.value = d.dapp_id WHERE m.key = 'associated_dapp' AND m.value LIKE 'dapp%' ORDER BY a.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 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.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.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": "Show me all rooms along with their current overall review rating for each room, including the room number and property id."}, {"role": "assistant", "content": "SELECT r.room_number, r.property_id, AVG(rv.rating_overall) AS average_overall_rating\nFROM hospitality_technology.rooms r\nLEFT JOIN hospitality_technology.reviews rv\n ON r.property_id = rv.property_id\nGROUP BY r.room_number, r.property_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 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.reviews ( review_id.text, property_id.text, reservation_id.text, guest_id.text, rating_overall.integer, rating_cleanliness.integer, rating_service.integer, rating_location.integer, rating_value.integer, comment.text, review_source.text, review_date.timestamp, is_public.boolean, staff_response.text, response_staff_id.text, response_date.timestamp )\n"} {"conversations": [{"role": "user", "content": "Find cases where an address received tokens in one transfer and then sent tokens in another. List the receive transfer_id, the send transfer_id, the address, and both transfer values."}, {"role": "assistant", "content": "SELECT recv.transfer_id AS receive_transfer_id,\n send.transfer_id AS send_transfer_id,\n recv.to_address AS address,\n recv.value AS received_value,\n send.value AS sent_value\nFROM web3.token_transfers recv\nJOIN web3.token_transfers send\n ON recv.to_address = send.from_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.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": "List all premium payments for policy 'POL123'. Show payment ID, payment date, amount paid, and status."}, {"role": "assistant", "content": "SELECT payment_id, payment_date, amount_paid, status FROM insurance.premium_payments WHERE policy_id = 'POL123';"}, {"role": "user", "content": "Only show payments made on or after January 1, 2024."}, {"role": "assistant", "content": "SELECT payment_id, payment_date, amount_paid, status FROM insurance.premium_payments WHERE policy_id = 'POL123' AND payment_date >= '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 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)\n"} {"conversations": [{"role": "user", "content": "List all service orders for spa services with their guest names and total prices, ordered by total price in descending order."}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, so.order_id, so.total_price FROM hospitality_technology.service_orders so JOIN hospitality_technology.guests g ON so.guest_id = g.guest_id WHERE so.service_id LIKE 'SPA%' ORDER BY so.total_price DESC;"}, {"role": "user", "content": "Now, include only orders with a total price over $100 and show the property ID where the service was ordered."}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, so.order_id, so.total_price, r.property_id FROM hospitality_technology.service_orders so JOIN hospitality_technology.guests g ON so.guest_id = g.guest_id JOIN hospitality_technology.reservations r ON so.reservation_id = r.reservation_id WHERE so.service_id LIKE 'SPA%' AND so.total_price > 100 ORDER BY so.total_price DESC;"}, {"role": "user", "content": "The query is missing the service name. Can you include that as well?"}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, so.order_id, so.total_price, r.property_id, s.service_name FROM hospitality_technology.service_orders so JOIN hospitality_technology.guests g ON so.guest_id = g.guest_id JOIN hospitality_technology.reservations r ON so.reservation_id = r.reservation_id JOIN hospitality_technology.services s ON so.service_id = s.service_id WHERE so.service_id LIKE 'SPA%' AND so.total_price > 100 ORDER BY so.total_price DESC;"}, {"role": "user", "content": "Actually, I only need orders from properties in California, and order by property ID first, then by total price."}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, so.order_id, so.total_price, r.property_id, s.service_name FROM hospitality_technology.service_orders so JOIN hospitality_technology.guests g ON so.guest_id = g.guest_id JOIN hospitality_technology.reservations r ON so.reservation_id = r.reservation_id JOIN hospitality_technology.services s ON so.service_id = s.service_id JOIN hospitality_technology.properties p ON r.property_id = p.property_id WHERE so.service_id LIKE 'SPA%' AND so.total_price > 100 AND p.state_province = 'California' ORDER BY r.property_id, so.total_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 hospitality_technology.room_types ( room_type_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, type_name character varying(100) NOT NULL, description text, base_rate numeric(10, 2) NOT NULL, max_occupancy integer NOT NULL, bed_type character varying(50), area_sqft numeric(8,2), amenities text, PRIMARY KEY (room_type_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.guests (\n guest_id character varying(64) NOT NULL, -- unique identifier for the guest profile\n first_name character varying(100) NOT NULL, -- guest's first name\n last_name character varying(100) NOT NULL, -- guest's last name\n email character varying(255) UNIQUE, -- guest's email address (unique identifier?)\n phone_number character varying(30), -- guest's phone number\n date_of_birth date, -- guest's date of birth\n address_line1 character varying(255), -- guest's home address\n city character varying(100),\n state_province character varying(100),\n postal_code character varying(20),\n country_code character varying(3),\n preferences text, -- notes on guest preferences (e.g., allergies, room location)\n loyalty_member_id character varying(64) UNIQUE, -- FK to loyalty_members table\n communication_consent boolean DEFAULT true, -- consent for marketing communications\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 (guest_id)\n)\nCREATE TABLE hospitality_technology.reservations (\n reservation_id character varying(64) NOT NULL, -- unique identifier for the booking\n property_id character varying(64) NOT NULL, -- FK to properties table\n guest_id character varying(64) NOT NULL, -- FK to guests table (primary guest)\n room_id character varying(64), -- FK to rooms table (assigned room, might be null initially)\n room_type_id character varying(64) NOT NULL, -- FK to room_types table (booked room type)\n check_in_date date NOT NULL, -- scheduled check-in date\n check_out_date date NOT NULL, -- scheduled check-out date\n actual_check_in_ts timestamp with time zone, -- actual check-in time\n actual_check_out_ts timestamp with time zone, -- actual check-out time\n num_adults integer NOT NULL, -- number of adults\n num_children integer DEFAULT 0, -- number of children\n status character varying(50) NOT NULL, -- e.g., Pending, Confirmed, CheckedIn, CheckedOut, Cancelled, NoShow\n booking_source character varying(100), -- e.g., Website, OTA (Expedia, Booking.com), Phone, WalkIn\n rate_plan_id character varying(64), -- FK to rate_plans table (optional)\n total_amount numeric(12, 2), -- estimated or final total cost\n amount_paid numeric(12, 2) DEFAULT 0.00, -- amount already paid\n special_requests text, -- specific guest requests for this booking\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 (reservation_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id),\n FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\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 ( payment_id text, reservation_id text, guest_id text, bill_id text, amount numeric, currency_code text, payment_method text, card_type text, card_last_four text, transaction_ref text, payment_timestamp timestamp, status text, staff_id_processed text, notes text )\nCREATE TABLE hospitality_technology.reviews ( review_id text, property_id text, reservation_id text, guest_id text, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source text, review_date timestamp, is_public boolean, staff_response text, response_staff_id text, response_date timestamp )\n"} {"conversations": [{"role": "user", "content": "Get the total balance of each SUI coin per coin_type, including symbol and name from metadata."}, {"role": "assistant", "content": "SELECT sc.coin_type,\n scm.symbol,\n scm.name,\n SUM(CAST(sc.balance AS NUMERIC)) AS total_balance\nFROM sui_coins AS sc\nJOIN sui_coins_metadata AS scm\n ON sc.coin_type = scm.coin_type\nGROUP BY sc.coin_type, scm.symbol, scm.name;"}, {"role": "user", "content": "Only include coins where description contains 'governance'."}, {"role": "assistant", "content": "SELECT sc.coin_type,\n scm.symbol,\n scm.name,\n SUM(CAST(sc.balance AS NUMERIC)) AS total_balance\nFROM sui_coins AS sc\nJOIN sui_coins_metadata AS scm\n ON sc.coin_type = scm.coin_type\nWHERE scm.description ILIKE '%governance%'\nGROUP BY sc.coin_type, scm.symbol, scm.name;"}, {"role": "user", "content": "Limit to top 5 coins sorted by total_balance descending."}, {"role": "assistant", "content": "SELECT sc.coin_type,\n scm.symbol,\n scm.name,\n SUM(CAST(sc.balance AS NUMERIC)) AS total_balance\nFROM sui_coins AS sc\nJOIN sui_coins_metadata AS scm\n ON sc.coin_type = scm.coin_type\nWHERE scm.description ILIKE '%governance%'\nGROUP BY sc.coin_type, scm.symbol, scm.name\nORDER BY total_balance 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 token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash varchar, transaction_index bigint, from_address varchar, contract_address varchar, symbol varchar, total_supply varchar, name varchar, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info varchar, 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_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_coins ( object_id varchar, status varchar, coin_type varchar, balance varchar, owner varchar )\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 varchar NOT NULL, status varchar NOT NULL, collection_type varchar NOT NULL, package_id varchar NOT NULL, previous_transaction varchar NOT NULL, display varchar NOT NULL, owner varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE nft_metadata ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer NOT NULL, pk integer NOT NULL )\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_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 (\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_balances_bitcoin ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(255) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply varchar NOT NULL, amount varchar NOT NULL )\nCREATE TABLE token_info_bitcoin ( 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 )\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 (\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(20) NOT NULL, -- Ticker: Identifier of the inscription\n max_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n lim decimal(38,0) NOT NULL, -- Mint limit: limit per inscription\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 minted decimal(38,0) NOT NULL, -- Sum of minted amount\n holders decimal(38,0) NOT NULL, -- Count of holders\n txs decimal(38,0) NOT NULL, -- Count of transactions\n updated_timestamp timestamp(3) NOT NULL, -- Timestamp of update\n completed_timestamp timestamp(3) NOT NULL, -- Timestamp of minted completed\n id varchar(255) NOT NULL -- id fields for the functionType in contract asc20\n)\n"} {"conversations": [{"role": "user", "content": "Show me the total transaction amount by transaction_type for all transactions processed by employees in the 'Trading' department, along with their department name."}, {"role": "assistant", "content": "SELECT t.transaction_type, SUM(t.amount) AS total_amount, e.department\nFROM financial_services.transactions t\nJOIN financial_services.employees e ON t.account_id IN (\n SELECT account_id \n FROM financial_services.accounts \n WHERE branch_id = e.branch_id\n)\nWHERE e.department = 'Trading'\nGROUP BY t.transaction_type, e.department;"}], "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 (\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 ( 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": "Find the claim ID and the total number of documents associated with each claim ID that has more than 10 documents."}, {"role": "assistant", "content": "SELECT claim_id, COUNT(*) FROM insurance.claim_documents GROUP BY claim_id HAVING COUNT(*) > 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 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": "For each player, show the player_id and the count of inventory items they acquired with a quantity greater than 1."}, {"role": "assistant", "content": "SELECT player_id, COUNT(inventory_id) AS items_qty_gt_1_count FROM gaming_technology.player_inventory WHERE quantity > 1 GROUP BY player_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 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 NOT NULL DEFAULT gen_random_uuid(), title character varying(200) NOT NULL, developer_id uuid NOT NULL, publisher_id uuid, genre character varying(100), release_date date, description text, platform character varying(50) NOT NULL, engine character varying(100), website character varying(255), PRIMARY KEY (game_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.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) )\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": "Find all users who registered with a Yahoo email address, along with their registration dates."}, {"role": "assistant", "content": "SELECT user_id, username, email, password_hash FROM blockchain.users WHERE email LIKE '%@yahoo.com';"}, {"role": "user", "content": "This query doesn't show registration dates. Can you modify it to include the registration date?"}, {"role": "assistant", "content": "I notice the users table doesn't have a registration date column. Would you like me to show other available information from the users table?"}, {"role": "user", "content": "Then just show me the count of Yahoo email users instead."}, {"role": "assistant", "content": "SELECT COUNT(*) as yahoo_user_count FROM blockchain.users WHERE email LIKE '%@yahoo.com';"}], "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.blocks ( block_id text, previous_block_id text, timestamp timestamp, nonce integer, merkle_root text, difficulty integer )\nCREATE TABLE blockchain.transactions (\n transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n block_id character varying(64) NOT NULL, -- identifier of the block containing the transaction\n sender_address character varying(128) NOT NULL, -- address of the sender\n receiver_address character varying(128) NOT NULL, -- address of the receiver\n amount numeric(38,14) NOT NULL, -- amount transferred\n timestamp timestamp NOT NULL, -- time when the transaction was created\n signature text NOT NULL, -- digital signature of the transaction\n PRIMARY KEY (transaction_id)\n)\nCREATE TABLE blockchain.addresses ( address_id text PRIMARY KEY, public_key text, balance numeric )\nCREATE TABLE blockchain.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, PRIMARY KEY (user_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": "我想查看所有检查记录中检查员的ID和检查结果，同时统计每个检查员的检查次数。"}, {"role": "assistant", "content": "db.inspections.aggregate([\n {\n $group: {\n _id: '$inspector_employee_id',\n total_inspections: { $count: {} },\n results: { $push: '$result' }\n }\n },\n {\n $project: {\n inspector_employee_id: '$_id',\n total_inspections: 1,\n results: 1,\n _id: 0\n }\n }\n]);"}, {"role": "user", "content": "如果我想只统计检查结果为'Fail'的次数，应该怎么改？"}, {"role": "assistant", "content": "db.inspections.aggregate([\n {\n $match: {\n result: 'Fail'\n }\n },\n {\n $group: {\n _id: '$inspector_employee_id',\n failed_inspections: { $count: {} }\n }\n },\n {\n $project: {\n inspector_employee_id: '$_id',\n failed_inspections: 1,\n _id: 0\n }\n }\n]);"}], "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\nCollection 'inspections'. Document structure: { _id: , inspection_id: String, build_id: String (reference), component_id: String (reference, optional), step_id: String (reference, optional), inspection_type: String, inspector_employee_id: String (reference), inspection_timestamp: ISODate, result: String, remarks: String }. Required: inspection_id, build_id, inspection_type, inspector_employee_id, inspection_timestamp, result. Indexes on build_id, component_id, step_id, inspector_employee_id, result.\n"} {"conversations": [{"role": "user", "content": "List booking IDs and fares for bookings associated with trips using vehicles that had maintenance logs recorded in the last 90 days."}, {"role": "assistant", "content": "SELECT T1.booking_id , T1.fare FROM transportation.bookings AS T1 JOIN transportation.trips AS T2 ON T1.trip_id = T2.trip_id JOIN transportation.vehicles AS T3 ON T2.vehicle_id = T3.vehicle_id JOIN transportation.maintenance_logs AS T4 ON T3.vehicle_id = T4.vehicle_id WHERE T4.service_date >= date('now', '-90 day')"}, {"role": "user", "content": "Now, only include bookings with a status of 'Pending' and order the results by booking time descending."}, {"role": "assistant", "content": "SELECT T1.booking_id , T1.fare FROM transportation.bookings AS T1 JOIN transportation.trips AS T2 ON T1.trip_id = T2.trip_id JOIN transportation.vehicles AS T3 ON T2.vehicle_id = T3.vehicle_id JOIN transportation.maintenance_logs AS T4 ON T3.vehicle_id = T4.vehicle_id WHERE T1.status = 'Pending' AND T4.service_date >= date('now', '-90 day') ORDER BY T1.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.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 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 posts where the content mentions 'meeting'."}, {"role": "assistant", "content": "SELECT post_id, user_id, content, created_at FROM social_media.posts WHERE content LIKE '%meeting%'"}, {"role": "user", "content": "Also, only include those posts that are public."}, {"role": "assistant", "content": "SELECT post_id, user_id, content, created_at FROM social_media.posts WHERE content LIKE '%meeting%' AND visibility = 'public'"}], "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 PRIMARY KEY, 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 )\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": "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": "Show me the top 5 NFT collections on Sui blockchain with the highest number of unique owners, along with their names and collection types."}, {"role": "assistant", "content": "SELECT name, collection_type, COUNT(DISTINCT owner) AS unique_owners FROM sui_nfts GROUP BY name, collection_type ORDER BY unique_owners DESC LIMIT 5;"}, {"role": "user", "content": "Can you modify the query to only include collections where the package_id starts with '0x' and add the display field to the results?"}, {"role": "assistant", "content": "SELECT name, collection_type, display, COUNT(DISTINCT owner) AS unique_owners FROM sui_nfts WHERE package_id LIKE '0x%' GROUP BY name, collection_type, display ORDER BY unique_owners DESC LIMIT 5;"}, {"role": "user", "content": "Now filter these results to only show collections with 'art' in their collection_type and sort by name alphabetically."}, {"role": "assistant", "content": "SELECT name, collection_type, display, COUNT(DISTINCT owner) AS unique_owners FROM sui_nfts WHERE package_id LIKE '0x%' AND collection_type LIKE '%art%' GROUP BY name, collection_type, display ORDER BY name ASC 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 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_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_coins_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\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 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 ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\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_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(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 )\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": "I need a report of all notification messages sent to users who have at least one wallet, showing the notification message and the address of one wallet for each user."}, {"role": "assistant", "content": "SELECT n.message, w.address\nFROM trading_platform.notifications n\nJOIN trading_platform.wallets w ON n.user_id = w.user_id\nGROUP BY n.notification_id, n.message, w.address;"}, {"role": "user", "content": "There are duplicate rows because some users have multiple wallets. Only show each user once with their notification messages and their earliest created wallet's address."}, {"role": "assistant", "content": "SELECT n.user_id, n.message, w.address\nFROM trading_platform.notifications n\nJOIN (\n SELECT user_id, MIN(created_at) AS min_created_at\n FROM trading_platform.wallets\n GROUP BY user_id\n) mw ON n.user_id = mw.user_id\nJOIN trading_platform.wallets w ON mw.user_id = w.user_id AND mw.min_created_at = w.created_at;"}, {"role": "user", "content": "Actually, for each notification, show the corresponding user's username, the notification message, and their earliest wallet address."}, {"role": "assistant", "content": "SELECT u.username, n.message, w.address\nFROM trading_platform.notifications n\nJOIN trading_platform.users u ON n.user_id = u.user_id\nJOIN (\n SELECT user_id, MIN(created_at) AS min_created_at\n FROM trading_platform.wallets\n GROUP BY user_id\n) mw ON n.user_id = mw.user_id\nJOIN trading_platform.wallets w ON mw.user_id = w.user_id AND mw.min_created_at = w.created_at;"}, {"role": "user", "content": "Now limit the result to notifications sent after '2024-06-01', and order by sent_at descending."}, {"role": "assistant", "content": "SELECT u.username, n.message, w.address\nFROM trading_platform.notifications n\nJOIN trading_platform.users u ON n.user_id = u.user_id\nJOIN (\n SELECT user_id, MIN(created_at) AS min_created_at\n FROM trading_platform.wallets\n GROUP BY user_id\n) mw ON n.user_id = mw.user_id\nJOIN trading_platform.wallets w ON mw.user_id = w.user_id AND mw.min_created_at = w.created_at\nWHERE n.sent_at > '2024-06-01'\nORDER BY n.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 trading_platform.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, created_at timestamp )\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 ( 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 (\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 ( dapp_id.text, name.text, description.text, url.text )\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 (\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 ( kyc_audit_id.text, user_id.text, status.text, reviewed_at.timestamp )\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)\nCREATE TABLE trading_platform.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\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": "Show me the total fuel cost for each trip along with the trip's route number and the type of the route."}, {"role": "assistant", "content": "SELECT t.trip_id, r.route_number, r.type, SUM(f.total_cost) AS total_fuel_cost\nFROM transportation.trips t\nJOIN transportation.routes r ON t.route_id = r.route_id\nJOIN transportation.fuel_logs f ON t.trip_id = f.trip_id\nGROUP BY t.trip_id, r.route_number, r.type;"}, {"role": "user", "content": "Modify the query to only include trips on routes of type 'Express', and show results ordered by total fuel cost descending."}, {"role": "assistant", "content": "SELECT t.trip_id, r.route_number, r.type, SUM(f.total_cost) AS total_fuel_cost\nFROM transportation.trips t\nJOIN transportation.routes r ON t.route_id = r.route_id\nJOIN transportation.fuel_logs f ON t.trip_id = f.trip_id\nWHERE r.type = 'Express'\nGROUP BY t.trip_id, r.route_number, r.type\nORDER BY total_fuel_cost 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.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 )\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": "How many games are available in each genre? List genre and game_count."}, {"role": "assistant", "content": "SELECT genre, COUNT(*) AS game_count\nFROM gaming_technology.games\nGROUP BY genre;"}, {"role": "user", "content": "Now only include genres with at least 5 games."}, {"role": "assistant", "content": "SELECT genre, COUNT(*) AS game_count\nFROM gaming_technology.games\nGROUP BY genre\nHAVING COUNT(*) >= 5;"}, {"role": "user", "content": "Also show the earliest release_date for each of these genres."}, {"role": "assistant", "content": "SELECT genre, COUNT(*) AS game_count, MIN(release_date) AS earliest_release\nFROM gaming_technology.games\nGROUP BY genre\nHAVING COUNT(*) >= 5;"}, {"role": "user", "content": "Sort by game_count descending and limit to top 3."}, {"role": "assistant", "content": "SELECT genre, COUNT(*) AS game_count, MIN(release_date) AS earliest_release\nFROM gaming_technology.games\nGROUP BY genre\nHAVING COUNT(*) >= 5\nORDER BY game_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 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 )\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": "For each user with at least two wallets, calculate the average time difference in hours between consecutive wallet creations. Return user_id and avg_diff_hours."}, {"role": "assistant", "content": "SELECT user_id, AVG(EXTRACT(EPOCH FROM (created_at - prev_created)) / 3600) AS avg_diff_hours FROM (SELECT user_id, created_at, LAG(created_at) OVER (PARTITION BY user_id ORDER BY created_at) AS prev_created FROM web3.wallets) t WHERE prev_created IS NOT NULL GROUP BY user_id;"}, {"role": "user", "content": "Actually, restrict the results to users whose avg_diff_hours is less than 24 hours and sort by avg_diff_hours ascending."}, {"role": "assistant", "content": "WITH diffs AS (SELECT user_id, EXTRACT(EPOCH FROM (created_at - prev_created)) / 3600 AS diff_hours FROM (SELECT user_id, created_at, LAG(created_at) OVER (PARTITION BY user_id ORDER BY created_at) AS prev_created FROM web3.wallets) sub WHERE prev_created IS NOT NULL) SELECT user_id, AVG(diff_hours) AS avg_diff_hours FROM diffs GROUP BY user_id HAVING AVG(diff_hours) < 24 ORDER BY avg_diff_hours;"}], "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.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": "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": "What is the current number of passengers at station with ID 'ST123' right now?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the current number of passengers at a station. The data I have access to only includes static details about stations such as their name, location, and number of platforms, not real-time passenger counts."}], "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 (\n station_id character varying(64) NOT NULL, -- Unique identifier for the station\n station_name character varying(128) NOT NULL, -- Name of the station\n city character varying(100) NOT NULL, -- City where the station is located\n state_province character varying(100), -- State or province\n country_code character varying(3) NOT NULL, -- ISO country code\n address text, -- Full address of the station\n timezone character varying(64) NOT NULL, -- Timezone ID (e.g., 'America/New_York')\n number_of_platforms integer NOT NULL DEFAULT 0, -- Total number of platforms\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- When the station record was created\n last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- When the station record was last updated\n PRIMARY KEY (station_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all auto loans (loan_id, principal_amount, interest_rate) where the current principal balance is less than 40% of the original principal amount, along with the account_id and the difference between principal_amount and current_principal_balance."}, {"role": "assistant", "content": "SELECT loan_id, principal_amount, interest_rate, account_id, (principal_amount - current_principal_balance) AS amount_paid FROM financial_services.loans WHERE loan_type = 'Auto' AND current_principal_balance < (0.4 * principal_amount);"}], "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.loans ( loan_id character varying(64) NOT NULL, account_id character varying(64) NOT NULL UNIQUE, loan_type character varying(50) NOT NULL, principal_amount numeric(19, 4) NOT NULL, current_principal_balance numeric(19, 4) NOT NULL, interest_rate numeric(6, 4) NOT NULL, term_months integer NOT NULL, origination_date date NOT NULL, maturity_date date NOT NULL, monthly_payment numeric(12, 4), collateral_description text, status character varying(32) NOT NULL, PRIMARY KEY (loan_id), FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id) )\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) > 0;"}], "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.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.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": "Retrieve the most recent log entry for each user, including action and logged_at."}, {"role": "assistant", "content": "SELECT l1.user_id,\n l1.action,\n l1.logged_at\nFROM trading_platform.logs l1\nWHERE l1.logged_at = (\n SELECT MAX(l2.logged_at)\n FROM trading_platform.logs l2\n WHERE l2.user_id = l1.user_id\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 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.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.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": "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.contract_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 - the token_prices_latest table isn't in the schema. Can you modify it to use the token_balances table instead?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_balances tb ON tm.contract_address = tb.wallet_address WHERE tm.is_erc20 = 1 AND CAST(tb.amount AS decimal) BETWEEN 1 AND 10;"}, {"role": "user", "content": "That doesn't seem right either. Let's just get the basic ERC20 token information without price filtering for now."}, {"role": "assistant", "content": "SELECT name, symbol, contract_address FROM token_metas WHERE is_erc20 = 1 LIMIT 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 ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\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, 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_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 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 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 token_activities ( 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 mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\nCREATE TABLE token_info_bitcoin ( 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 )\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 (\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": "Show me the appointment ID, subject, and start time for appointments that are linked to a case, along with the case number and case name."}, {"role": "assistant", "content": "SELECT T1.appointment_id, T1.subject, T1.start_time, T2.case_number, T2.case_name FROM legal_services.appointments AS T1 JOIN legal_services.cases AS T2 ON T1.case_id = T2.case_id;"}, {"role": "user", "content": "Restrict this to appointments starting after '2024-01-01' and where the case status is 'Open'."}, {"role": "assistant", "content": "SELECT T1.appointment_id, T1.subject, T1.start_time, T2.case_number, T2.case_name FROM legal_services.appointments AS T1 JOIN legal_services.cases AS T2 ON T1.case_id = T2.case_id WHERE T1.start_time >= '2024-01-01' AND T2.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.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.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 )\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": "Show a list of all game developers with their name and founded year."}, {"role": "assistant", "content": "SELECT\n name,\n founded_year\nFROM gaming_technology.developers;"}, {"role": "user", "content": "Please filter the list to only include developers founded in the year 1998."}, {"role": "assistant", "content": "SELECT\n name,\n founded_year\nFROM gaming_technology.developers\nWHERE\n founded_year = 1998;"}, {"role": "user", "content": "Can you also include the number of games each of these developers has released?"}, {"role": "assistant", "content": "SELECT\n T1.name,\n T1.founded_year,\n COUNT(T2.game_id) AS game_count\nFROM gaming_technology.developers AS T1\nLEFT JOIN gaming_technology.games AS T2\n ON T1.developer_id = T2.developer_id\nWHERE\n T1.founded_year = 1998\nGROUP BY\n T1.developer_id,\n T1.name,\n T1.founded_year;"}, {"role": "user", "content": "Now, only show the developers who have released exactly 2 games."}, {"role": "assistant", "content": "SELECT\n T1.name,\n T1.founded_year,\n COUNT(T2.game_id) AS game_count\nFROM gaming_technology.developers AS T1\nJOIN gaming_technology.games AS T2\n ON T1.developer_id = T2.developer_id\nWHERE\n T1.founded_year = 1998\nGROUP BY\n T1.developer_id,\n T1.name,\n T1.founded_year\nHAVING\n COUNT(T2.game_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 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.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.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)\n"} {"conversations": [{"role": "user", "content": "Show me all wallet addresses that hold more than 100 of any ERC1155 token, along with the token ID and amount."}, {"role": "assistant", "content": "SELECT wallet_address, token_id, amount FROM erc20_balances WHERE CAST(amount AS decimal) > 100 AND contract_address IN (SELECT contract_address FROM token_metas WHERE is_erc1155 = 1);"}, {"role": "user", "content": "Can you also include the name and image URI of each token from the nft_metadata table?"}, {"role": "assistant", "content": "SELECT e.wallet_address, e.token_id, e.amount, m.name, m.image_uri FROM erc20_balances e JOIN nft_metadata m ON e.contract_address = m.contract_address WHERE CAST(e.amount AS decimal) > 100 AND e.contract_address IN (SELECT contract_address FROM token_metas WHERE is_erc1155 = 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_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": "What is the performance review score for employee with ID 'EMP456' for the last quarter?"}, {"role": "assistant", "content": "I'm sorry, but I can't assist with information about performance review scores as this data is not included 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 ( 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(128) NOT NULL, skill_certifications text, hire_date date NOT NULL, assigned_line_id character varying(64), employment_status character varying(50) NOT NULL, supervisor_employee_id character varying(64), PRIMARY KEY (employee_id) )\n"} {"conversations": [{"role": "user", "content": "How many service orders were placed by each staff member (staff_id_ordered)? Show the staff ID and the count."}, {"role": "assistant", "content": "SELECT staff_id_ordered, COUNT(*) FROM hospitality_technology.service_orders GROUP BY staff_id_ordered;"}, {"role": "user", "content": "Only show staff members who placed more than 10 orders."}, {"role": "assistant", "content": "SELECT staff_id_ordered, COUNT(*) FROM hospitality_technology.service_orders GROUP BY staff_id_ordered HAVING COUNT(*) > 10;"}, {"role": "user", "content": "And exclude orders that were cancelled."}, {"role": "assistant", "content": "SELECT staff_id_ordered, COUNT(*) FROM hospitality_technology.service_orders WHERE status != 'Cancelled' GROUP BY staff_id_ordered HAVING COUNT(*) > 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 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 )\n"} {"conversations": [{"role": "user", "content": "Show me all room types with 'King' in the bed_type field, along with their property IDs and base rates."}, {"role": "assistant", "content": "SELECT room_type_id, property_id, type_name, bed_type, base_rate FROM hospitality_technology.room_types WHERE bed_type LIKE '%King%';"}, {"role": "user", "content": "Now, join this with the guests table to show only room types from properties where the guest's country code is 'USA' and the guest is a loyalty member."}, {"role": "assistant", "content": "SELECT rt.room_type_id, rt.property_id, rt.type_name, rt.bed_type, rt.base_rate FROM hospitality_technology.room_types rt JOIN hospitality_technology.guests g ON rt.property_id = g.property_id WHERE rt.bed_type LIKE '%King%' AND g.country_code = 'USA' AND g.loyalty_member_id IS NOT NULL;"}, {"role": "user", "content": "The query is missing the max occupancy. Can you include that as well?"}, {"role": "assistant", "content": "SELECT rt.room_type_id, rt.property_id, rt.type_name, rt.bed_type, rt.base_rate, rt.max_occupancy FROM hospitality_technology.room_types rt JOIN hospitality_technology.guests g ON rt.property_id = g.property_id WHERE rt.bed_type LIKE '%King%' AND g.country_code = 'USA' AND g.loyalty_member_id IS NOT NULL;"}, {"role": "user", "content": "Actually, I need to see only room types with a base rate below $300, and order them by max occupancy in descending order."}, {"role": "assistant", "content": "SELECT rt.room_type_id, rt.property_id, rt.type_name, rt.bed_type, rt.base_rate, rt.max_occupancy FROM hospitality_technology.room_types rt JOIN hospitality_technology.guests g ON rt.property_id = g.property_id WHERE rt.bed_type LIKE '%King%' AND g.country_code = 'USA' AND g.loyalty_member_id IS NOT NULL AND rt.base_rate < 300 ORDER BY rt.max_occupancy 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.room_types ( room_type_id text PRIMARY KEY, property_id text, type_name text, description text, base_rate numeric, max_occupancy int, bed_type text, area_sqft numeric, amenities text )\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 )\n"} {"conversations": [{"role": "user", "content": "List the usernames and user IDs of all users whose bio contains the word 'developer'."}, {"role": "assistant", "content": "SELECT user_id, username\nFROM social_media.users\nWHERE bio ILIKE '%developer%';"}], "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": "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": "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;"}, {"role": "user", "content": "The query should also show the difference between the total amount and the base rate 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, (r.total_amount - rt.base_rate) AS rate_difference FROM hospitality_technology.reservations r LEFT JOIN hospitality_technology.service_orders so ON r.reservation_id = so.reservation_id LEFT JOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_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, rt.base_rate ORDER BY r.check_in_date;"}, {"role": "user", "content": "Actually, I only need reservations where the total amount is at least 50% higher than the base rate, and order them by check-in date."}, {"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, (r.total_amount - rt.base_rate) AS rate_difference FROM hospitality_technology.reservations r LEFT JOIN hospitality_technology.service_orders so ON r.reservation_id = so.reservation_id LEFT JOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_id WHERE r.total_amount > 500 AND r.status = 'Confirmed' AND r.total_amount >= rt.base_rate * 1.5 GROUP BY r.reservation_id, r.guest_id, r.room_id, r.check_in_date, r.total_amount, rt.base_rate 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.properties ( property_id character varying(64) NOT NULL, property_name character varying(255) NOT NULL, address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state_province character varying(100), postal_code character varying(20) NOT NULL, country_code character varying(3) NOT NULL, phone_number character varying(30), email_address character varying(255), property_type character varying(50) NOT NULL, star_rating numeric(2,1), timezone character varying(64) NOT NULL, manager_staff_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 (property_id) )\nCREATE TABLE hospitality_technology.rooms ( room_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, room_number character varying(10) NOT NULL, room_type_id character varying(64) NOT NULL, floor integer, status character varying(50) NOT NULL, is_smoking boolean NOT NULL DEFAULT false, features text, current_condition text, last_cleaned_at timestamp with time zone, PRIMARY KEY (room_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.room_types ( room_type_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, type_name character varying(100) NOT NULL, description text, base_rate numeric(10, 2) NOT NULL, max_occupancy integer NOT NULL, bed_type character varying(50), area_sqft numeric(8,2), amenities text, PRIMARY KEY (room_type_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.reservations (\n reservation_id character varying(64) NOT NULL, -- unique identifier for the booking\n property_id character varying(64) NOT NULL, -- FK to properties table\n guest_id character varying(64) NOT NULL, -- FK to guests table (primary guest)\n room_id character varying(64), -- FK to rooms table (assigned room, might be null initially)\n room_type_id character varying(64) NOT NULL, -- FK to room_types table (booked room type)\n check_in_date date NOT NULL, -- scheduled check-in date\n check_out_date date NOT NULL, -- scheduled check-out date\n actual_check_in_ts timestamp with time zone, -- actual check-in time\n actual_check_out_ts timestamp with time zone, -- actual check-out time\n num_adults integer NOT NULL, -- number of adults\n num_children integer DEFAULT 0, -- number of children\n status character varying(50) NOT NULL, -- e.g., Pending, Confirmed, CheckedIn, CheckedOut, Cancelled, NoShow\n booking_source character varying(100), -- e.g., Website, OTA (Expedia, Booking.com), Phone, WalkIn\n rate_plan_id character varying(64), -- FK to rate_plans table (optional)\n total_amount numeric(12, 2), -- estimated or final total cost\n amount_paid numeric(12, 2) DEFAULT 0.00, -- amount already paid\n special_requests text, -- specific guest requests for this booking\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 (reservation_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id),\n FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.staff ( staff_id text PRIMARY KEY, 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 int, 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.payments ( payment_id text PRIMARY KEY, reservation_id text, guest_id text, bill_id text, amount numeric, currency_code text, payment_method text, card_type text, card_last_four text, transaction_ref text, payment_timestamp timestamp, status text, staff_id_processed text, notes 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": "Show me all rooms that are currently available (status = 'available') and have a non-smoking policy, along with their room type details including base rate and max occupancy."}, {"role": "assistant", "content": "SELECT r.room_id, r.room_number, r.floor, rt.type_name, rt.base_rate, rt.max_occupancy, rt.bed_type, rt.area_sqft FROM hospitality_technology.rooms r JOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_id WHERE r.status = 'available' AND r.is_smoking = false;"}, {"role": "user", "content": "Now, filter these results to only include rooms with a max occupancy of at least 4 people and order them by base rate in ascending order."}, {"role": "assistant", "content": "SELECT r.room_id, r.room_number, r.floor, rt.type_name, rt.base_rate, rt.max_occupancy, rt.bed_type, rt.area_sqft FROM hospitality_technology.rooms r JOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_id WHERE r.status = 'available' AND r.is_smoking = false AND rt.max_occupancy >= 4 ORDER BY rt.base_rate 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.rooms ( room_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, room_number character varying(10) NOT NULL, room_type_id character varying(64) NOT NULL, floor integer, status character varying(50) NOT NULL, is_smoking boolean NOT NULL DEFAULT false, features text, current_condition text, last_cleaned_at timestamp with time zone, PRIMARY KEY (room_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.room_types ( room_type_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, type_name character varying(100) NOT NULL, description text, base_rate numeric(10, 2) NOT NULL, max_occupancy integer NOT NULL, bed_type character varying(50), area_sqft numeric(8,2), amenities text, PRIMARY KEY (room_type_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.reservations ( reservation_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, guest_id character varying(64) NOT NULL, room_id character varying(64), room_type_id character varying(64) NOT NULL, check_in_date date NOT NULL, check_out_date date NOT NULL, actual_check_in_ts timestamp with time zone, actual_check_out_ts timestamp with time zone, num_adults integer NOT NULL, num_children integer DEFAULT 0, status character varying(50) NOT NULL, booking_source character varying(100), rate_plan_id character varying(64), total_amount numeric(12, 2), amount_paid numeric(12, 2) DEFAULT 0.00, special_requests text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (reservation_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.staff ( staff_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, position character varying(100) NOT NULL, work_email character varying(255) UNIQUE, work_phone character varying(30), hire_date date NOT NULL, termination_date date, is_active boolean NOT NULL DEFAULT true, access_level integer NOT NULL, manager_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (staff_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "Get me all unbilled billable time entries with their entry_id, case_id, lawyer_id, hours_spent, and billing_rate."}, {"role": "assistant", "content": "SELECT entry_id,\n case_id,\n lawyer_id,\n hours_spent,\n billing_rate\nFROM legal_services.time_entries\nWHERE is_billable = TRUE\n AND is_billed = FALSE;"}, {"role": "user", "content": "Actually, I only want entries for lawyer 'lawyer_123'."}, {"role": "assistant", "content": "SELECT entry_id,\n case_id,\n lawyer_id,\n hours_spent,\n billing_rate\nFROM legal_services.time_entries\nWHERE is_billable = TRUE\n AND is_billed = FALSE\n AND lawyer_id = 'lawyer_123';"}, {"role": "user", "content": "Also, sort the results by hours_spent in descending order."}, {"role": "assistant", "content": "SELECT entry_id,\n case_id,\n lawyer_id,\n hours_spent,\n billing_rate\nFROM legal_services.time_entries\nWHERE is_billable = TRUE\n AND is_billed = FALSE\n AND lawyer_id = 'lawyer_123'\nORDER BY hours_spent 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.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": "For each reservation, show me the guest's full name, the property name, and the room type name."}, {"role": "assistant", "content": "SELECT r.reservation_id, g.first_name || ' ' || g.last_name AS guest_full_name, p.property_name, rt.type_name AS room_type_name\nFROM hospitality_technology.reservations r\nJOIN hospitality_technology.guests g ON r.guest_id = g.guest_id\nJOIN hospitality_technology.properties p ON r.property_id = p.property_id\nJOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_id;"}, {"role": "user", "content": "Can you only show those reservations where the number of children is at least 2, and order results by guest last name ascending?"}, {"role": "assistant", "content": "SELECT r.reservation_id, g.first_name || ' ' || g.last_name AS guest_full_name, p.property_name, rt.type_name AS room_type_name\nFROM hospitality_technology.reservations r\nJOIN hospitality_technology.guests g ON r.guest_id = g.guest_id\nJOIN hospitality_technology.properties p ON r.property_id = p.property_id\nJOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_id\nWHERE r.num_children >= 2\nORDER BY g.last_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.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.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, 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 )\n"} {"conversations": [{"role": "user", "content": "Show the full names and contact emails of all citizens who have applied for services with a standard fee greater than 100."}, {"role": "assistant", "content": "SELECT c.first_name || ' ' || c.last_name AS full_name, c.contact_email\nFROM government_services.citizens c\nJOIN government_services.services s ON c.citizen_id IS NOT NULL -- Replace with actual application linking table if exists\nWHERE s.standard_fee > 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 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.services ( service_id.text, agency_id.text, service_name.text, description.text, category.text, eligibility_criteria.text, standard_fee.numeric, average_processing_time_days.integer, is_active.boolean, online_application_url.text )\n"} {"conversations": [{"role": "user", "content": "I want to find the total number of ERC1155 \"approval-for-all\" events per contract. Show contract_address and the approval_count."}, {"role": "assistant", "content": "SELECT contract_address, COUNT(*) AS approval_count\nFROM erc1155_approval_for_all\nGROUP BY contract_address;"}, {"role": "user", "content": "Also show the number of unique wallet holders currently holding any token from those contracts by joining to nft_holders."}, {"role": "assistant", "content": "SELECT a.contract_address,\n a.approval_count,\n COALESCE(b.holder_count, 0) AS holder_count\nFROM (\n SELECT contract_address, COUNT(*) AS approval_count\n FROM erc1155_approval_for_all\n GROUP BY contract_address\n) a\nLEFT JOIN (\n SELECT contract_address, COUNT(DISTINCT wallet_address) AS holder_count\n FROM nft_holders\n GROUP BY contract_address\n) b\n ON a.contract_address = b.contract_address;"}, {"role": "user", "content": "Filter to only include contracts where holder_count is greater than 50."}, {"role": "assistant", "content": "SELECT a.contract_address,\n a.approval_count,\n b.holder_count\nFROM (\n SELECT contract_address, COUNT(*) AS approval_count\n FROM erc1155_approval_for_all\n GROUP BY contract_address\n) a\nJOIN (\n SELECT contract_address, COUNT(DISTINCT wallet_address) AS holder_count\n FROM nft_holders\n GROUP BY contract_address\n HAVING COUNT(DISTINCT wallet_address) > 50\n) b\n ON a.contract_address = b.contract_address;"}, {"role": "user", "content": "Sort results by approval_count descending and limit to the top 10."}, {"role": "assistant", "content": "SELECT a.contract_address,\n a.approval_count,\n b.holder_count\nFROM (\n SELECT contract_address, COUNT(*) AS approval_count\n FROM erc1155_approval_for_all\n GROUP BY contract_address\n) a\nJOIN (\n SELECT contract_address, COUNT(DISTINCT wallet_address) AS holder_count\n FROM nft_holders\n GROUP BY contract_address\n HAVING COUNT(DISTINCT wallet_address) > 50\n) b\n ON a.contract_address = b.contract_address\nORDER BY a.approval_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 token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash varchar, transaction_index bigint, from_address varchar, contract_address varchar, symbol varchar, total_supply varchar, name varchar, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info varchar, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address 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_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 (\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 ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_balances_bitcoin ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(255) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply varchar NOT NULL, amount varchar NOT NULL )\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(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": "How many lawyers who are partners were hired in each year? Show the hire year and the count."}, {"role": "assistant", "content": "SELECT strftime('%Y', hire_date) AS hire_year , count(lawyer_id) FROM legal_services.lawyers WHERE is_partner = true GROUP BY hire_year"}], "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 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": "List all SUI coins with status 'exists', including their coin_type, balance, and owner address."}, {"role": "assistant", "content": "SELECT object_id, coin_type, balance, owner\nFROM sui_coins\nWHERE status = 'exists';"}, {"role": "user", "content": "Add their symbol and name by joining with sui_coins_metadata."}, {"role": "assistant", "content": "SELECT sc.object_id, sc.coin_type, sc.balance, sc.owner, scm.symbol, scm.name\nFROM sui_coins sc\nJOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type\nWHERE sc.status = 'exists';"}, {"role": "user", "content": "Only include coins where balance is greater than 1000000 and the metadata status is also 'exists'."}, {"role": "assistant", "content": "SELECT sc.object_id, sc.coin_type, sc.balance, sc.owner, scm.symbol, scm.name\nFROM sui_coins sc\nJOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type\nWHERE sc.status = 'exists' AND scm.status = 'exists' AND CAST(sc.balance AS bigint) > 1000000;"}, {"role": "user", "content": "Add the coin's description from sui_coins_metadata and order the results by balance descending."}, {"role": "assistant", "content": "SELECT sc.object_id, sc.coin_type, sc.balance, sc.owner, scm.symbol, scm.name, scm.description\nFROM sui_coins sc\nJOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type\nWHERE sc.status = 'exists' AND scm.status = 'exists' AND CAST(sc.balance AS bigint) > 1000000\nORDER BY CAST(sc.balance AS bigint) 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_metas ( block_timestamp timestamp, block_number bigint, transaction_hash varchar, transaction_index bigint, from_address varchar, contract_address varchar, symbol varchar, total_supply varchar, name varchar, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info varchar, 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_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\n amount varchar NOT NULL, -- Wallet's on-chain balance at the corresponding block height\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 7200))\n)\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 ( object_id varchar, status varchar, coin_type varchar, balance varchar, owner varchar )\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 token_prices_latest ( blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\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_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_info_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 tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n max_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n lim decimal(38,0) NOT NULL, -- Mint limit: limit per inscription\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 minted decimal(38,0) NOT NULL, -- Sum of minted amount\n holders decimal(38,0) NOT NULL, -- Count of holders\n txs decimal(38,0) NOT NULL, -- Count of transactions\n updated_timestamp timestamp(3) NOT NULL, -- Timestamp of update\n completed_timestamp timestamp(3) NOT NULL, -- Timestamp of minted completed\n id varchar(255) NOT NULL -- id fields for the functionType in contract asc20\n)\n"} {"conversations": [{"role": "user", "content": "How many unique tokens are recorded for each chain in the latest snapshot in cex_token_balance?"}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n)\nSELECT \n chain, \n COUNT(DISTINCT token_symbol) AS unique_token_count\nFROM cex_token_balance c\nJOIN latest_snapshot l ON c.snapshot_time = l.max_time\nGROUP BY chain\nORDER BY unique_token_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 cex_token_balance ( snapshot_time.text, chain.text, address.text, exchange.text, token_address.text, token_symbol.text, balance.numeric, usd_value.numeric, price.numeric )\n"} {"conversations": [{"role": "user", "content": "For each employee, retrieve their full name and the number of appointments scheduled for them in the next 7 days, including employees with no appointments."}, {"role": "assistant", "content": "SELECT e.first_name || ' ' || e.last_name AS full_name,\n COUNT(a.appointment_id) AS appointment_count\nFROM government_services.employees e\nLEFT JOIN government_services.appointments a\n ON e.employee_id = a.employee_id\n AND a.scheduled_start_time BETWEEN now() AND now() + INTERVAL '7 days'\nGROUP BY e.first_name, e.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 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.applications ( application_id text PRIMARY KEY, 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 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.employees ( employee_id text PRIMARY KEY, 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 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": "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": "For each player, show their player_id and the number of unique games they have played sessions on."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT game_id) AS unique_games\nFROM gaming_technology.game_sessions\nGROUP BY player_id;"}, {"role": "user", "content": "Also show the total number of sessions they have played."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT game_id) AS unique_games, COUNT(*) AS total_sessions\nFROM gaming_technology.game_sessions\nGROUP BY player_id;"}, {"role": "user", "content": "Only include players who have played on more than 2 unique games."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT game_id) AS unique_games, COUNT(*) AS total_sessions\nFROM gaming_technology.game_sessions\nGROUP BY player_id\nHAVING COUNT(DISTINCT game_id) > 2;"}, {"role": "user", "content": "For each result, include the player's username as well."}, {"role": "assistant", "content": "SELECT p.player_id, p.username, COUNT(DISTINCT gs.game_id) AS unique_games, COUNT(*) AS total_sessions\nFROM gaming_technology.players p\nJOIN gaming_technology.game_sessions gs ON p.player_id = gs.player_id\nGROUP BY p.player_id, p.username\nHAVING COUNT(DISTINCT gs.game_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 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.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 ( 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.player_achievements ( player_achievement_id.uuid, player_id.uuid, achievement_id.uuid, unlocked_at.timestamptz )\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": "Show the total number of customers in each state."}, {"role": "assistant", "content": "SELECT\n state,\n COUNT(customer_id)\nFROM insurance.customers\nGROUP BY\n 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.customers ( customer_id text, 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.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 (\n product_id character varying(64) NOT NULL, -- unique identifier for the insurance product\n product_name character varying(150) NOT NULL, -- name of the insurance product (e.g., 'Comprehensive Auto Insurance')\n product_type character varying(50) NOT NULL, -- category like 'Auto', 'Home', 'Life', 'Health', 'Travel'\n description text, -- detailed description of the product\n base_premium numeric(10, 2) NOT NULL, -- starting premium before adjustments\n coverage_details text, -- details about what is covered (could be JSON or structured text)\n underwriting_rules text, -- rules used for assessing risk and eligibility\n is_active boolean NOT NULL DEFAULT true, -- whether the product is currently offered\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n updated_at timestamp,\n PRIMARY KEY (product_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": "Show me the number of game servers in each region and the average maximum number of players they can accommodate. Exclude any servers that are currently offline."}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, AVG(max_players) AS average_max_players FROM gaming_technology.servers WHERE status != 'offline' GROUP BY region;"}, {"role": "user", "content": "Please filter the results to only include regions that have more than 5 active servers."}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, AVG(max_players) AS average_max_players FROM gaming_technology.servers WHERE status != 'offline' GROUP BY region HAVING COUNT(server_id) > 5;"}, {"role": "user", "content": "Can you also include the total number of current players across all active servers in each of those regions?"}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, AVG(max_players) AS average_max_players, SUM(current_players) AS total_current_players FROM gaming_technology.servers WHERE status != 'offline' GROUP BY region HAVING COUNT(server_id) > 5;"}, {"role": "user", "content": "Order the final results by the total number of current players in descending order."}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, AVG(max_players) AS average_max_players, SUM(current_players) AS total_current_players FROM gaming_technology.servers WHERE status != 'offline' GROUP BY region HAVING COUNT(server_id) > 5 ORDER 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.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 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": "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": "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 securities (security_id, ticker_symbol, security_name) that have a currency of 'EUR' and were last updated within the last 30 days, along with their exchange and sector information."}, {"role": "assistant", "content": "SELECT security_id, ticker_symbol, security_name, exchange, sector FROM financial_services.securities WHERE currency = 'EUR' AND last_updated >= CURRENT_DATE - INTERVAL '30 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 financial_services.securities (\n security_id character varying(64) NOT NULL, -- unique identifier for the security\n ticker_symbol character varying(20) NOT NULL UNIQUE, -- stock ticker or fund symbol\n isin_code character varying(12) UNIQUE, -- International Securities Identification Number\n cusip_code character varying(9) UNIQUE, -- CUSIP number\n security_name text NOT NULL, -- full name of the security\n security_type character varying(50) NOT NULL, -- e.g., Stock, Bond, ETF, Mutual Fund, Option, Future\n exchange character varying(50), -- primary exchange where traded (e.g., NYSE, NASDAQ)\n currency character varying(3) NOT NULL, -- currency the security is denominated in\n issuer_name character varying(255), -- name of the issuing entity\n sector character varying(100), -- industry sector\n last_updated timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (security_id)\n)\n"} {"conversations": [{"role": "user", "content": "Find all wallets created by users in the last 7 days along with any tokens that have a total supply greater than 10 million, showing the wallet address and token details."}, {"role": "assistant", "content": "SELECT w.address AS wallet_address, t.token_name, t.token_symbol, t.total_supply, t.contract_address FROM web3.wallets w JOIN web3.tokens t ON t.total_supply > 10000000 WHERE w.created_at >= CURRENT_DATE - 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 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) )\nCREATE TABLE web3.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) )\n"} {"conversations": [{"role": "user", "content": "What is the average balance for each account_type among accounts with status 'Open'?"}, {"role": "assistant", "content": "SELECT account_type, AVG(balance) AS avg_balance FROM financial_services.accounts WHERE status = 'Open' GROUP BY account_type;"}, {"role": "user", "content": "Exclude account types with fewer than 3 accounts."}, {"role": "assistant", "content": "SELECT account_type, AVG(balance) AS avg_balance FROM financial_services.accounts WHERE status = 'Open' GROUP BY account_type HAVING COUNT(*) >= 3;"}, {"role": "user", "content": "Sort the results by average balance descending."}, {"role": "assistant", "content": "SELECT account_type, AVG(balance) AS avg_balance FROM financial_services.accounts WHERE status = 'Open' GROUP BY account_type HAVING COUNT(*) >= 3 ORDER BY avg_balance 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 ( 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 )\n"} {"conversations": [{"role": "user", "content": "Which exchanges have a total token USD value greater than 3,000,000 on the Polygon chain? Show the exchange name and their total USD value."}, {"role": "assistant", "content": "SELECT exchange, SUM(usd_value) AS total_usd_value\nFROM cex_token_balance\nWHERE chain = 'Polygon'\nGROUP BY exchange\nHAVING SUM(usd_value) > 3000000;"}], "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 character varying(32) NOT NULL, project_id character varying(32) NOT NULL, project_name character varying(128) NOT NULL, rounds_name character varying(32), investment_value numeric(38,14), investment_date character varying(128), introduction character varying(128), valuation numeric(38,14) )\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, top_3_coins text, price_change_percentage_1h double precision, price_change_percentage_24h double precision, price_change_percentage_7d double precision, market_cap double precision, volume_24h double precision, trend_rank bigint, token_num bigint )\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 cex_token_balance ( snapshot_time character varying(32) NOT NULL, chain character varying(128) NOT NULL, address character varying(128) NOT NULL, exchange character varying(512) NOT NULL, token_address character varying(128) NOT NULL, token_symbol character varying(512), balance numeric(38,10), usd_value numeric(38,14), price double precision )\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) )\nCREATE TABLE smart_money_token_performance ( token_address character varying(100) NOT NULL, token_symbol character varying(100), pnl numeric(38,2), net_flow numeric(38,2), avg_cost numeric(38,16), price double precision, realized_ratio numeric(10,2), roi numeric(10,2), chain character varying(100) )\nCREATE TABLE smart_money_token_inflow ( token_address character varying(100) NOT NULL, token_symbol character varying(100), token_amount numeric(38,2), usd_value numeric(38,2), avg_price numeric(38,6), type int, address_amount integer, narrative character varying(100), chain character varying(100) )\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 the top 10 transactions by gas price, including the from_address, to_address, and block_number, sorted in descending order."}, {"role": "assistant", "content": "SELECT from_address, to_address, block_number, gas_price FROM web3.transactions ORDER BY gas_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 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": "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 wallets holding the NFT with contract_address '0xabc123' and token_id '100' and the amount held."}, {"role": "assistant", "content": "SELECT wallet_address, amount\nFROM nft_holders\nWHERE contract_address = '0xabc123'\n AND token_id = '100';"}, {"role": "user", "content": "Also include the NFT name from nft_metadata by joining on contract_address and token_id."}, {"role": "assistant", "content": "SELECT nh.wallet_address,\n nh.amount,\n nm.name\nFROM nft_holders nh\nJOIN nft_metadata nm ON nh.contract_address = nm.contract_address\n AND nh.token_id = nm.token_id\nWHERE nh.contract_address = '0xabc123'\n AND nh.token_id = '100';"}, {"role": "user", "content": "Finally, add the collection name from nft_collections where blockchain is 'Ethereum'."}, {"role": "assistant", "content": "SELECT nh.wallet_address,\n nh.amount,\n nm.name,\n nc.name AS collection_name\nFROM nft_holders nh\nJOIN nft_metadata nm ON nh.contract_address = nm.contract_address\n AND nh.token_id = nm.token_id\nJOIN nft_collections nc ON nh.contract_address = nc.contract_address\n AND nc.blockchain = 'Ethereum'\nWHERE nh.contract_address = '0xabc123'\n AND nh.token_id = '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 erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\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 ( 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 ( object_id varchar NOT NULL, coin_type varchar NOT NULL, status varchar NOT NULL, decimals bigint NOT NULL, description varchar NOT NULL, icon_url varchar NOT NULL, symbol varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id varchar NOT NULL, status varchar NOT NULL, collection_type varchar NOT NULL, package_id varchar NOT NULL, previous_transaction varchar NOT NULL, display varchar NOT NULL, owner varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE nft_metadata ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer NOT NULL, pk integer NOT NULL )\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 varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\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 NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar 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 ( 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(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 NOT NULL, tick varchar 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 )\nCREATE TABLE mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(255) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply varchar NOT NULL, amount varchar NOT NULL )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(255) 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_bitcoin ( 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(62) NOT NULL, to_address varchar(62) NOT NULL )\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 )\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 )\n"} {"conversations": [{"role": "user", "content": "Count the number of contracts per network and status."}, {"role": "assistant", "content": "SELECT\n network_id,\n status,\n COUNT(*) AS contract_count\nFROM web3.contracts\nGROUP BY network_id, status;"}, {"role": "user", "content": "Actually, please only include statuses with more than 10 contracts."}, {"role": "assistant", "content": "SELECT\n network_id,\n status,\n COUNT(*) AS contract_count\nFROM web3.contracts\nGROUP BY network_id, status\nHAVING COUNT(*) > 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 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)\n"} {"conversations": [{"role": "user", "content": "Which doctors have both a listed email address and a license number that starts with the letter 'A'? Show their ID, full name, specialty, and email."}, {"role": "assistant", "content": "SELECT doctor_id, first_name, last_name, specialty, email\nFROM healthcare.doctors\nWHERE email IS NOT NULL AND email <> '' AND license_number LIKE 'A%';"}, {"role": "user", "content": "Also include the doctor’s phone number and sort the results by first name ascending."}, {"role": "assistant", "content": "SELECT doctor_id, first_name, last_name, specialty, email, phone_number\nFROM healthcare.doctors\nWHERE email IS NOT NULL AND email <> '' AND license_number LIKE 'A%'\nORDER BY first_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 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 )\n"} {"conversations": [{"role": "user", "content": "I need to find all pairs of BUY and SELL trades for the same account that occurred on the same settlement_date."}, {"role": "assistant", "content": "SELECT a.trade_id AS buy_trade_id, b.trade_id AS sell_trade_id, a.account_id, a.settlement_date\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\nWHERE a.trade_type = 'BUY'\n AND b.trade_type = 'SELL';"}, {"role": "user", "content": "Only include pairs where the quantities match between the BUY and SELL trades."}, {"role": "assistant", "content": "SELECT a.trade_id AS buy_trade_id, b.trade_id AS sell_trade_id, a.account_id, a.settlement_date\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\nWHERE a.trade_type = 'BUY'\n AND b.trade_type = 'SELL'\n AND a.quantity = b.quantity;"}, {"role": "user", "content": "Also exclude any pairs where the execution_venue is the same for both trades."}, {"role": "assistant", "content": "SELECT a.trade_id AS buy_trade_id, b.trade_id AS sell_trade_id, a.account_id, a.settlement_date\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\nWHERE a.trade_type = 'BUY'\n AND b.trade_type = 'SELL'\n AND a.quantity = b.quantity\n AND a.execution_venue <> b.execution_venue;"}, {"role": "user", "content": "Finally, order the results by account_id ascending and settlement_date descending."}, {"role": "assistant", "content": "SELECT a.trade_id AS buy_trade_id, b.trade_id AS sell_trade_id, a.account_id, a.settlement_date\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\nWHERE a.trade_type = 'BUY'\n AND b.trade_type = 'SELL'\n AND a.quantity = b.quantity\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.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 )\n"} {"conversations": [{"role": "user", "content": "Provide the total count of unique users who have created wallets."}, {"role": "assistant", "content": "SELECT COUNT(DISTINCT user_id) FROM web3.wallets;"}, {"role": "user", "content": "Now, refine that to show the number of users who own *more than one* wallet."}, {"role": "assistant", "content": "SELECT COUNT(*)\nFROM (\n SELECT user_id\n FROM web3.wallets\n GROUP BY user_id\n HAVING COUNT(*) > 1\n) AS UsersWithMultipleWallets;"}], "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 total fuel quantity and cost for each route, grouped by route number, only for trips that have associated fuel logs."}, {"role": "assistant", "content": "SELECT r.route_number, SUM(f.quantity) AS total_quantity, SUM(f.total_cost) AS total_cost\nFROM transportation.fuel_logs f\nJOIN transportation.routes r ON f.trip_id IS NOT NULL AND f.trip_id IN (\n SELECT DISTINCT trip_id FROM transportation.fuel_logs\n)\nJOIN transportation.bookings b ON f.trip_id = b.trip_id\nWHERE r.route_id = b.trip_id\nGROUP BY r.route_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 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.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.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": "Identify all sender addresses that have transferred tokens in more than 3 distinct transactions. Return from_address and transfer_count, ordered by transfer_count descending."}, {"role": "assistant", "content": "SELECT\n from_address,\n COUNT(DISTINCT transaction_id) AS transfer_count\nFROM web3.token_transfers\nGROUP BY from_address\nHAVING COUNT(DISTINCT transaction_id) > 3\nORDER BY transfer_count DESC;"}, {"role": "user", "content": "Actually, I also want to include the total value of tokens they have transferred."}, {"role": "assistant", "content": "SELECT\n from_address,\n COUNT(DISTINCT transaction_id) AS transfer_count,\n SUM(value) AS total_transferred_value\nFROM web3.token_transfers\nGROUP BY from_address\nHAVING COUNT(DISTINCT transaction_id) > 3\nORDER BY transfer_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 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 (\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": "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": "For each group chat, list its ID, name, creation time, and the creation time of the next group chat created after it, ordered by creation time."}, {"role": "assistant", "content": "SELECT conversation_id, group_name, created_at, LEAD(created_at) OVER (ORDER BY created_at) AS next_group_chat_created_at FROM social_media.conversations WHERE is_group_chat = true ORDER BY created_at;"}, {"role": "user", "content": "Only show pairs where the next group chat was created within 48 hours of the current one, and also include the time difference in hours."}, {"role": "assistant", "content": "WITH RankedGroupChats AS ( SELECT conversation_id, group_name, created_at, LEAD(created_at) OVER (ORDER BY created_at) AS next_group_chat_created_at FROM social_media.conversations WHERE is_group_chat = true ) SELECT conversation_id, group_name, created_at, next_group_chat_created_at, EXTRACT(EPOCH FROM (next_group_chat_created_at - created_at)) / 3600 AS time_difference_hours FROM RankedGroupChats WHERE next_group_chat_created_at IS NOT NULL AND EXTRACT(EPOCH FROM (next_group_chat_created_at - created_at)) <= 48 * 3600 ORDER BY created_at;"}, {"role": "user", "content": "Further refine: Only include group chats whose names contain 'Discuss'."}, {"role": "assistant", "content": "WITH RankedGroupChats AS ( SELECT conversation_id, group_name, created_at, LEAD(created_at) OVER (ORDER BY created_at) AS next_group_chat_created_at FROM social_media.conversations WHERE is_group_chat = true ) SELECT conversation_id, group_name, created_at, next_group_chat_created_at, EXTRACT(EPOCH FROM (next_group_chat_created_at - created_at)) / 3600 AS time_difference_hours FROM RankedGroupChats WHERE next_group_chat_created_at IS NOT NULL AND EXTRACT(EPOCH FROM (next_group_chat_created_at - created_at)) <= 48 * 3600 AND group_name LIKE '%Discuss%' ORDER BY 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 social_media.conversations ( conversation_id character varying(64) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, last_message_at timestamp, is_group_chat boolean NOT NULL DEFAULT false, group_name character varying(100), PRIMARY KEY (conversation_id) )\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": "How many participants are there in each conversation? Return conversation_id and participant_count."}, {"role": "assistant", "content": "SELECT conversation_id,\n COUNT(*) AS participant_count\nFROM social_media.conversation_participants\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.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Can you provide the total number of maintenance records for a specific train with train_id 'train_789'?"}, {"role": "assistant", "content": "MATCH (t:Train {train_id: 'train_789'})<-[:PERFORMED_ON]-(mr:MaintenanceRecord)\nRETURN COUNT(mr) AS total_maintenance_records"}], "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: :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// Node Label: :MaintenanceRecord\n// Properties:\n// record_id: String (Constraint: UNIQUE)\n// asset_type: String // Store type here for easier querying if assets are different labels\n// maintenance_type: String\n// start_datetime: DateTime\n// end_datetime: DateTime\n// description: String\n// cost: Float\n// status: String\n// Relationships:\n// (:MaintenanceRecord)-[:PERFORMED_ON]->(:Train or :TrainCar or :Platform) // Polymorphic or separate relationships\n// (:MaintenanceRecord)-[:PERFORMED_BY]->(:Staff)\n// Example Cypher CREATE:\n// MATCH (asset:Train {train_id: 'train_789'}), (st:Staff {staff_id: 'staff_xyz'})\n// CREATE (mr:MaintenanceRecord {record_id: 'maint_rec_001', asset_type: 'Train', ...})\n// CREATE (mr)-[:PERFORMED_ON]->(asset)\n// CREATE (mr)-[:PERFORMED_BY]->(st)\n"} {"conversations": [{"role": "user", "content": "Find all PDF claim documents uploaded in May 2024, showing document_id, claim_id, and file_size_bytes, and also list who uploaded each document."}, {"role": "assistant", "content": "SELECT document_id, claim_id, file_size_bytes, uploaded_by FROM insurance.claim_documents WHERE mime_type = 'application/pdf' AND uploaded_at >= '2024-05-01' AND uploaded_at < '2024-06-01';"}, {"role": "user", "content": "Can you also include the file_name of each document?"}, {"role": "assistant", "content": "SELECT document_id, claim_id, file_name, file_size_bytes, uploaded_by FROM insurance.claim_documents WHERE mime_type = 'application/pdf' AND uploaded_at >= '2024-05-01' AND uploaded_at < '2024-06-01';"}, {"role": "user", "content": "Actually, only include documents where the file size is greater than 1 MB."}, {"role": "assistant", "content": "SELECT document_id, claim_id, file_name, file_size_bytes, uploaded_by FROM insurance.claim_documents WHERE mime_type = 'application/pdf' AND uploaded_at >= '2024-05-01' AND uploaded_at < '2024-06-01' AND file_size_bytes > 1048576;"}], "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 employees who are managers and list the number of employees they directly manage. Show the manager's full name and the count of their direct reports."}, {"role": "assistant", "content": "SELECT m.first_name || ' ' || m.last_name AS manager_full_name, COUNT(e.employee_id) AS number_of_direct_reports FROM government_services.employees AS e JOIN government_services.employees AS m ON e.manager_employee_id = m.employee_id GROUP BY m.employee_id, manager_full_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 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": "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": "Count the number of law firms founded in each decade. Show the decade (e.g., 1990s, 2000s) and the count."}, {"role": "assistant", "content": "SELECT CONCAT(FLOOR(EXTRACT(YEAR FROM founded_date) / 10) * 10, 's') AS decade, COUNT(*) AS firm_count FROM law_firms WHERE founded_date IS NOT NULL GROUP BY decade ORDER BY decade;"}], "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.documents ( document_id text PRIMARY KEY, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version int, description text )\n"} {"conversations": [{"role": "user", "content": "List usernames and the length of their 'bio' field for users whose 'is_verified' status is true."}, {"role": "assistant", "content": "SELECT username, LENGTH(bio) AS bio_length FROM social_media.users WHERE is_verified IS 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.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": "For each token, show its token_id, decimals, and the average total_supply of all tokens with the same decimals."}, {"role": "assistant", "content": "SELECT t.token_id,\n t.decimals,\n avg_data.avg_total_supply\nFROM web3.tokens t\nJOIN (\n SELECT decimals,\n AVG(total_supply) AS avg_total_supply\n FROM web3.tokens\n GROUP BY decimals\n) AS avg_data\n ON t.decimals = avg_data.decimals;"}], "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": "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": "Show the total number of policies in each status."}, {"role": "assistant", "content": "SELECT status, COUNT(*) FROM insurance.policies GROUP BY status"}], "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, 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 (\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.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.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": "Show each asset's symbol and the number of unique addresses that have UTXOs associated with it."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol;"}, {"role": "user", "content": "Now show only assets with more than 5 unique addresses."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol\nHAVING COUNT(DISTINCT u.address) > 5;"}, {"role": "user", "content": "Please also include the total amount for each asset in the result."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses, COALESCE(SUM(u.amount), 0) AS total_amount\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol\nHAVING COUNT(DISTINCT u.address) > 5;"}, {"role": "user", "content": "Order the results by total_amount ascending and limit to the top 3."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses, COALESCE(SUM(u.amount), 0) AS total_amount\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol\nHAVING COUNT(DISTINCT u.address) > 5\nORDER BY total_amount ASC\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 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.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.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 ERC20 token transfers where the amount is over 5000, including the sender and receiver addresses."}, {"role": "assistant", "content": "SELECT from_address, to_address, amt, tick, tx_hash FROM token_activities WHERE type = 'transfer' AND CAST(amt AS DECIMAL) > 5000;"}, {"role": "user", "content": "Add the token symbol and decimals for each transfer by joining to the latest token price table."}, {"role": "assistant", "content": "SELECT ta.from_address, ta.to_address, ta.amt, ta.tick, ta.tx_hash, tpl.symbol, tpl.decimals FROM token_activities ta JOIN token_prices_latest tpl ON ta.tick = tpl.symbol WHERE ta.type = 'transfer' AND CAST(ta.amt AS DECIMAL) > 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 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 varchar, wallet_address varchar, amount varchar, pk integer )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk integer )\nCREATE TABLE sui_coins ( object_id varchar, status varchar, coin_type varchar, balance varchar, owner 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 ( blockchain varchar, contract_address varchar, token_id varchar, contract_name varchar, erc_type varchar, amount bigint, minter varchar, owner varchar, mint_block_number bigint, mint_time bigint, mint_transaction_hash varchar, mint_price varchar, token_uri varchar, metadata varchar, name varchar, image_uri varchar, traits varchar, updated_at bigint, status varchar, 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_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar, pk integer )\nCREATE TABLE token_activities ( 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 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_info_bitcoin ( 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 )\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": "For each service location, find its nearest accessible location by geographic distance."}, {"role": "assistant", "content": "SELECT sl.location_id,\n sl.location_name,\n nearest.location_id AS nearest_location_id,\n nearest.location_name AS nearest_location_name\nFROM government_services.service_locations sl\nJOIN LATERAL (\n SELECT sl2.location_id,\n sl2.location_name\n FROM government_services.service_locations sl2\n WHERE sl2.is_accessible = TRUE\n AND sl2.location_id <> sl.location_id\n ORDER BY ((sl.latitude - sl2.latitude)^2 + (sl.longitude - sl2.longitude)^2) ASC\n LIMIT 1\n) AS nearest ON 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.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 )\n"} {"conversations": [{"role": "user", "content": "For each reservation, list the guest ID, property name, and the total amount booked. Only include reservations where the total amount is greater than 300."}, {"role": "assistant", "content": "SELECT r.reservation_id, r.guest_id, p.property_name, r.total_amount\nFROM hospitality_technology.reservations r\nJOIN hospitality_technology.properties p ON r.property_id = p.property_id\nWHERE r.total_amount > 300;"}], "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 character varying(64) NOT NULL, property_name character varying(255) NOT NULL, address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state_province character varying(100), postal_code character varying(20) NOT NULL, country_code character varying(3) NOT NULL, phone_number character varying(30), email_address character varying(255), property_type character varying(50) NOT NULL, star_rating numeric(2,1), timezone character varying(64) NOT NULL, manager_staff_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 (property_id) )\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.reservations ( reservation_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, guest_id character varying(64) NOT NULL, room_id character varying(64), room_type_id character varying(64) NOT NULL, check_in_date date NOT NULL, check_out_date date NOT NULL, actual_check_in_ts timestamp with time zone, actual_check_out_ts timestamp with time zone, num_adults integer NOT NULL, num_children integer DEFAULT 0, status character varying(50) NOT NULL, booking_source character varying(100), rate_plan_id character varying(64), total_amount numeric(12, 2), amount_paid numeric(12, 2) DEFAULT 0.00, special_requests text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (reservation_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.service_orders ( order_id text PRIMARY KEY, reservation_id text, guest_id text, service_id text, staff_id_ordered text, staff_id_delivered text, order_timestamp timestamp, delivery_timestamp timestamp, quantity int, unit_price numeric, total_price numeric, status text, notes text, bill_id text )\n"} {"conversations": [{"role": "user", "content": "Give me a list of all specializations available at each law firm."}, {"role": "assistant", "content": "SELECT DISTINCT firm_id, specialization\nFROM legal_services.lawyers;"}, {"role": "user", "content": "For each specialization, show the number of lawyers in the firm who have that specialization."}, {"role": "assistant", "content": "SELECT firm_id, specialization, COUNT(*) AS lawyer_count\nFROM legal_services.lawyers\nGROUP BY firm_id, specialization;"}], "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": "I want to see a list of insurance plans along with the full names of all doctors whose hospital affiliation ID matches the plan ID. For each entry, include the plan name, insurance provider, doctor ID, and the doctor's first and last name."}, {"role": "assistant", "content": "SELECT ip.plan_name, ip.insurance_provider, d.doctor_id, d.first_name, d.last_name\nFROM healthcare.insurance_plans ip\nJOIN healthcare.doctors d ON ip.plan_id = d.hospital_affiliation_id"}, {"role": "user", "content": "Additionally, show only doctors who have an email address on file."}, {"role": "assistant", "content": "SELECT ip.plan_name, ip.insurance_provider, d.doctor_id, d.first_name, d.last_name\nFROM healthcare.insurance_plans ip\nJOIN healthcare.doctors d ON ip.plan_id = d.hospital_affiliation_id\nWHERE d.email IS NOT NULL AND d.email <> ''"}, {"role": "user", "content": "Sort the results by insurance provider in ascending order, then by the doctor's last name in descending order."}, {"role": "assistant", "content": "SELECT ip.plan_name, ip.insurance_provider, d.doctor_id, d.first_name, d.last_name\nFROM healthcare.insurance_plans ip\nJOIN healthcare.doctors d ON ip.plan_id = d.hospital_affiliation_id\nWHERE d.email IS NOT NULL AND d.email <> ''\nORDER BY ip.insurance_provider ASC, d.last_name 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 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.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": "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": "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": "List each claim_handler_id along with the number of claims they've handled and the total settlement_amount they've paid out."}, {"role": "assistant", "content": "SELECT claim_handler_id,\n COUNT(*) AS total_claims,\n SUM(settlement_amount) AS total_settlement\nFROM insurance.claims\nGROUP BY claim_handler_id;"}, {"role": "user", "content": "In addition, include the claim_id of the single claim with the highest settlement_amount for each handler."}, {"role": "assistant", "content": "SELECT ag.claim_handler_id,\n ag.total_claims,\n ag.total_settlement,\n c_max.claim_id AS max_settlement_claim_id,\n c_max.settlement_amount AS max_settlement_amount\nFROM (\n SELECT claim_handler_id,\n COUNT(*) AS total_claims,\n SUM(settlement_amount) AS total_settlement\n FROM insurance.claims\n GROUP BY claim_handler_id\n) ag\nJOIN insurance.claims c_max\n ON c_max.claim_handler_id = ag.claim_handler_id\n AND c_max.settlement_amount = (\n SELECT MAX(settlement_amount)\n FROM insurance.claims\n WHERE claim_handler_id = ag.claim_handler_id\n );"}, {"role": "user", "content": "Only include handlers who have managed at least 3 claims and have a non-null claim_handler_id."}, {"role": "assistant", "content": "SELECT ag.claim_handler_id,\n ag.total_claims,\n ag.total_settlement,\n c_max.claim_id AS max_settlement_claim_id,\n c_max.settlement_amount AS max_settlement_amount\nFROM (\n SELECT claim_handler_id,\n COUNT(*) AS total_claims,\n SUM(settlement_amount) AS total_settlement\n FROM insurance.claims\n GROUP BY claim_handler_id\n HAVING COUNT(*) >= 3\n AND claim_handler_id IS NOT NULL\n) ag\nJOIN insurance.claims c_max\n ON c_max.claim_handler_id = ag.claim_handler_id\n AND c_max.settlement_amount = (\n SELECT MAX(settlement_amount)\n FROM insurance.claims\n WHERE claim_handler_id = ag.claim_handler_id\n );"}, {"role": "user", "content": "Finally, sort the results by total_settlement in descending order."}, {"role": "assistant", "content": "SELECT ag.claim_handler_id,\n ag.total_claims,\n ag.total_settlement,\n c_max.claim_id AS max_settlement_claim_id,\n c_max.settlement_amount AS max_settlement_amount\nFROM (\n SELECT claim_handler_id,\n COUNT(*) AS total_claims,\n SUM(settlement_amount) AS total_settlement\n FROM insurance.claims\n GROUP BY claim_handler_id\n HAVING COUNT(*) >= 3\n AND claim_handler_id IS NOT NULL\n) ag\nJOIN insurance.claims c_max\n ON c_max.claim_handler_id = ag.claim_handler_id\n AND c_max.settlement_amount = (\n SELECT MAX(settlement_amount)\n FROM insurance.claims\n WHERE claim_handler_id = ag.claim_handler_id\n )\nORDER BY ag.total_settlement 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 (\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": "Show the plan name and insurance provider for all insurance plans along with the total number of unique patients enrolled in each plan."}, {"role": "assistant", "content": "SELECT ip.plan_name, ip.insurance_provider, COUNT(DISTINCT pi.patient_id) AS enrolled_patient_count\nFROM healthcare.insurance_plans ip\nJOIN healthcare.patients_insurance pi ON ip.plan_id = pi.plan_id\nGROUP BY ip.plan_name, ip.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.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.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 (\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 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 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 (\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 ( 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": "For each Avalanche token tick, calculate the total transfer volume and transaction count over the past 7 days using token_activities_avalanche. Include the token tick, total_volume, and tx_count."}, {"role": "assistant", "content": "SELECT\n tick,\n SUM(amt) AS total_volume,\n COUNT(*) AS tx_count\nFROM token_activities_avalanche\nWHERE block_timestamp >= CURRENT_DATE - INTERVAL '7 days'\nGROUP BY tick;"}, {"role": "user", "content": "Also include the creator address from token_info for each tick, and filter where total_volume > 1000 and creator starts with '0x1'."}, {"role": "assistant", "content": "SELECT\n a.tick,\n SUM(a.amt) AS total_volume,\n COUNT(*) AS tx_count,\n i.creator\nFROM token_activities_avalanche a\nJOIN token_info i\n ON a.tick = i.tick\nWHERE a.block_timestamp >= CURRENT_DATE - INTERVAL '7 days'\nGROUP BY a.tick, i.creator\nHAVING SUM(a.amt) > 1000\n AND i.creator LIKE '0x1%';"}, {"role": "user", "content": "Sort the results by total_volume descending and limit to the top 5 tokens."}, {"role": "assistant", "content": "SELECT\n a.tick,\n SUM(a.amt) AS total_volume,\n COUNT(*) AS tx_count,\n i.creator\nFROM token_activities_avalanche a\nJOIN token_info i\n ON a.tick = i.tick\nWHERE a.block_timestamp >= CURRENT_DATE - INTERVAL '7 days'\nGROUP BY a.tick, i.creator\nHAVING SUM(a.amt) > 1000\n AND i.creator LIKE '0x1%'\nORDER BY total_volume 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 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_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 (\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_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 varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer NOT NULL, pk integer NOT NULL )\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 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_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 )\n"} {"conversations": [{"role": "user", "content": "Find the contract address and name for all NFT collections listed on the 'Ethereum' blockchain."}, {"role": "assistant", "content": "SELECT contract_address, name FROM nft_collections WHERE blockchain = 'Ethereum'"}, {"role": "user", "content": "For these collections, can you show the count of unique wallet addresses holding NFTs in each collection by joining with nft_holders?"}, {"role": "assistant", "content": "SELECT T1.contract_address, T1.name, COUNT(DISTINCT T2.wallet_address) AS unique_holder_count FROM nft_collections AS T1 JOIN nft_holders AS T2 ON T1.contract_address = T2.contract_address WHERE T1.blockchain = 'Ethereum' GROUP BY T1.contract_address, T1.name"}, {"role": "user", "content": "Please filter the results to only include collections that have more than 100 unique holders."}, {"role": "assistant", "content": "SELECT T1.contract_address, T1.name, COUNT(DISTINCT T2.wallet_address) AS unique_holder_count FROM nft_collections AS T1 JOIN nft_holders AS T2 ON T1.contract_address = T2.contract_address WHERE T1.blockchain = 'Ethereum' GROUP BY T1.contract_address, T1.name HAVING COUNT(DISTINCT T2.wallet_address) > 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(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 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 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 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 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 varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\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(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 NOT NULL, tick varchar 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 )\nCREATE TABLE token_balances_bitcoin ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(255) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply varchar NOT NULL, amount varchar NOT NULL )\nCREATE TABLE token_activities_bitcoin ( 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(62) NOT NULL, to_address varchar(62) NOT NULL )\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 )\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(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(20) 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, minted decimal(38,0) NOT NULL, holders decimal(38,0) NOT NULL, txs decimal(38,0) NOT NULL, updated_timestamp timestamp(3) NOT NULL, completed_timestamp timestamp(3) NOT NULL, id varchar(255) NOT NULL )\n"} {"conversations": [{"role": "user", "content": "List all active drivers with their license expiry dates and contact information."}, {"role": "assistant", "content": "SELECT driver_id, first_name, last_name, license_number, license_expiry_date, contact_number, email FROM transportation.drivers WHERE status = 'active';"}, {"role": "user", "content": "Now include the count of trips each driver has completed in the last 3 months."}, {"role": "assistant", "content": "SELECT d.driver_id, d.first_name, d.last_name, d.license_number, d.license_expiry_date, d.contact_number, d.email, COUNT(t.trip_id) AS completed_trips FROM transportation.drivers d LEFT JOIN transportation.trips t ON d.driver_id = t.driver_id WHERE d.status = 'active' AND t.status = 'Completed' AND t.actual_arrival >= CURRENT_DATE - INTERVAL '3 months' GROUP BY d.driver_id, d.first_name, d.last_name, d.license_number, d.license_expiry_date, d.contact_number, d.email;"}, {"role": "user", "content": "Filter this to only show drivers whose licenses expire in the next 60 days."}, {"role": "assistant", "content": "SELECT d.driver_id, d.first_name, d.last_name, d.license_number, d.license_expiry_date, d.contact_number, d.email, COUNT(t.trip_id) AS completed_trips FROM transportation.drivers d LEFT JOIN transportation.trips t ON d.driver_id = t.driver_id WHERE d.status = 'active' AND t.status = 'Completed' AND t.actual_arrival >= CURRENT_DATE - INTERVAL '3 months' AND d.license_expiry_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '60 days' GROUP BY d.driver_id, d.first_name, d.last_name, d.license_number, d.license_expiry_date, d.contact_number, d.email;"}, {"role": "user", "content": "Now order the results by license expiry date with the soonest expiring first."}, {"role": "assistant", "content": "SELECT d.driver_id, d.first_name, d.last_name, d.license_number, d.license_expiry_date, d.contact_number, d.email, COUNT(t.trip_id) AS completed_trips FROM transportation.drivers d LEFT JOIN transportation.trips t ON d.driver_id = t.driver_id WHERE d.status = 'active' AND t.status = 'Completed' AND t.actual_arrival >= CURRENT_DATE - INTERVAL '3 months' AND d.license_expiry_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '60 days' GROUP BY d.driver_id, d.first_name, d.last_name, d.license_number, d.license_expiry_date, d.contact_number, d.email ORDER BY d.license_expiry_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 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": "For each event, display its event_id, the event_id of the previous event in the same transaction (if any), and the log_index of both events."}, {"role": "assistant", "content": "SELECT curr.event_id AS current_event_id,\n prev.event_id AS previous_event_id,\n curr.log_index AS current_log_index,\n prev.log_index AS previous_log_index,\n curr.transaction_id\nFROM web3.events curr\nLEFT JOIN web3.events prev\n ON curr.transaction_id = prev.transaction_id\n AND curr.log_index = prev.log_index + 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 web3.events ( event_id character varying(64) NOT NULL, contract_id character varying(64) NOT NULL, event_name character varying(128) NOT NULL, data text NOT NULL, emitted_at timestamp NOT NULL, transaction_id character varying(64) NOT NULL, log_index integer NOT NULL, PRIMARY KEY (event_id) )\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": "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": "List the first and last names of employees and the full name of the citizens for whom they have scheduled appointments."}, {"role": "assistant", "content": "SELECT T1.first_name , T1.last_name , T3.first_name , T3.last_name FROM government_services.employees AS T1 JOIN government_services.appointments AS T2 ON T1.employee_id = T2.employee_id JOIN government_services.citizens AS T3 ON T2.citizen_id = T3.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.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.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 text PRIMARY KEY, 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 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.employees ( employee_id text PRIMARY KEY, 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.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 )\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": "Show me the top 5 users who had their KYC status reviewed most recently, along with their review status."}, {"role": "assistant", "content": "SELECT user_id, status, reviewed_at FROM trading_platform.kyc_audit ORDER BY reviewed_at DESC LIMIT 5;"}, {"role": "user", "content": "Now modify the query to only show users whose KYC status was approved."}, {"role": "assistant", "content": "SELECT user_id, status, reviewed_at FROM trading_platform.kyc_audit WHERE status = 'approved' ORDER BY reviewed_at DESC LIMIT 5;"}, {"role": "user", "content": "Actually, I want to see all users whose KYC was reviewed in the last 7 days, not just the top 5."}, {"role": "assistant", "content": "SELECT user_id, status, reviewed_at FROM trading_platform.kyc_audit WHERE reviewed_at >= NOW() - INTERVAL '7 days' ORDER BY reviewed_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.kyc_audit ( kyc_audit_id.text, user_id.text, status.text, reviewed_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me all insurance plans that have more than 5 patients enrolled, along with the provider name and count of patients, sorted by patient count in descending order."}, {"role": "assistant", "content": "SELECT i.plan_name, i.insurance_provider, COUNT(p.patient_id) AS patient_count FROM healthcare.insurance_plans i JOIN healthcare.patients p ON i.plan_id = p.primary_insurance_id GROUP BY i.plan_id HAVING COUNT(p.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.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.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)\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": "Show me each service order along with the next order placed by the same guest, including both order IDs and the time difference in minutes between the two orders."}, {"role": "assistant", "content": "SELECT a.order_id,\n b.order_id AS next_order_id,\n EXTRACT(EPOCH FROM (b.order_timestamp - a.order_timestamp)) / 60 AS diff_minutes\nFROM hospitality_technology.service_orders a\nJOIN hospitality_technology.service_orders b\n ON a.guest_id = b.guest_id\n AND b.order_timestamp > a.order_timestamp;"}], "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.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 )\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": "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": "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": "How many active insurance policies does each patient have? Return patient_id and active_policy_count."}, {"role": "assistant", "content": "SELECT patient_id,\n COUNT(*) AS active_policy_count\nFROM healthcare.patient_insurance\nWHERE expiration_date IS NULL\n OR expiration_date >= CURRENT_DATE\nGROUP BY patient_id;"}, {"role": "user", "content": "Actually, only include patients who have more than one active insurance policy."}, {"role": "assistant", "content": "SELECT patient_id,\n COUNT(*) AS active_policy_count\nFROM healthcare.patient_insurance\nWHERE expiration_date IS NULL\n OR expiration_date >= CURRENT_DATE\nGROUP BY patient_id\nHAVING COUNT(*) > 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 (\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": "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 recipient address, count how many token transfers they have received."}, {"role": "assistant", "content": "SELECT to_address, COUNT(*) AS received_transfer_count FROM web3.token_transfers GROUP BY to_address;"}, {"role": "user", "content": "Only show addresses that have received more than 100 transfers."}, {"role": "assistant", "content": "SELECT to_address, COUNT(*) AS received_transfer_count FROM web3.token_transfers GROUP BY to_address HAVING 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 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 )\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": "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": "List all maintenance logs for vehicles acquired in the year 2023. Include log ID, vehicle make, model, service date, and cost."}, {"role": "assistant", "content": "SELECT ml.log_id, v.make, v.model, ml.service_date, ml.cost FROM transportation.maintenance_logs AS ml JOIN transportation.vehicles AS v ON ml.vehicle_id = v.vehicle_id WHERE EXTRACT(YEAR FROM v.acquisition_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 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)\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.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.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": "Which exchanges hold the largest total USD value of tokens on the BSC chain in the most recent snapshot, and what is the top token (by usd_value) held by each exchange?"}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n),\nexchange_totals AS (\n SELECT \n c.exchange, \n SUM(c.usd_value) AS total_usd_value\n FROM cex_token_balance c\n JOIN latest_snapshot l ON c.snapshot_time = l.max_time\n WHERE c.chain = 'BSC'\n GROUP BY c.exchange\n),\ntop_token_per_exchange AS (\n SELECT c.exchange, c.token_symbol, c.usd_value, ROW_NUMBER() OVER (PARTITION BY c.exchange ORDER BY c.usd_value DESC) AS rn\n FROM cex_token_balance c\n JOIN latest_snapshot l ON c.snapshot_time = l.max_time\n WHERE c.chain = 'BSC'\n)\nSELECT \n t.exchange, \n e.total_usd_value, \n t.token_symbol AS top_token_symbol, \n t.usd_value AS top_token_usd_value\nFROM exchange_totals e\nJOIN top_token_per_exchange t ON e.exchange = t.exchange AND t.rn = 1\nORDER BY e.total_usd_value DESC;"}, {"role": "user", "content": "Can you add the number of distinct tokens each exchange holds on BSC in the latest snapshot to the result?"}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n),\nexchange_totals AS (\n SELECT \n c.exchange, \n SUM(c.usd_value) AS total_usd_value,\n COUNT(DISTINCT c.token_symbol) AS token_count\n FROM cex_token_balance c\n JOIN latest_snapshot l ON c.snapshot_time = l.max_time\n WHERE c.chain = 'BSC'\n GROUP BY c.exchange\n),\ntop_token_per_exchange AS (\n SELECT c.exchange, c.token_symbol, c.usd_value, ROW_NUMBER() OVER (PARTITION BY c.exchange ORDER BY c.usd_value DESC) AS rn\n FROM cex_token_balance c\n JOIN latest_snapshot l ON c.snapshot_time = l.max_time\n WHERE c.chain = 'BSC'\n)\nSELECT \n t.exchange, \n e.total_usd_value, \n e.token_count,\n t.token_symbol AS top_token_symbol, \n t.usd_value AS top_token_usd_value\nFROM exchange_totals e\nJOIN top_token_per_exchange t ON e.exchange = t.exchange AND t.rn = 1\nORDER BY e.total_usd_value DESC;"}, {"role": "user", "content": "I'd like the results filtered so only exchanges holding more than $2,000,000 in total on BSC are included."}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n),\nexchange_totals AS (\n SELECT \n c.exchange, \n SUM(c.usd_value) AS total_usd_value,\n COUNT(DISTINCT c.token_symbol) AS token_count\n FROM cex_token_balance c\n JOIN latest_snapshot l ON c.snapshot_time = l.max_time\n WHERE c.chain = 'BSC'\n GROUP BY c.exchange\n HAVING SUM(c.usd_value) > 2000000\n),\ntop_token_per_exchange AS (\n SELECT c.exchange, c.token_symbol, c.usd_value, ROW_NUMBER() OVER (PARTITION BY c.exchange ORDER BY c.usd_value DESC) AS rn\n FROM cex_token_balance c\n JOIN latest_snapshot l ON c.snapshot_time = l.max_time\n WHERE c.chain = 'BSC'\n)\nSELECT \n t.exchange, \n e.total_usd_value, \n e.token_count,\n t.token_symbol AS top_token_symbol, \n t.usd_value AS top_token_usd_value\nFROM exchange_totals e\nJOIN top_token_per_exchange t ON e.exchange = t.exchange AND t.rn = 1\nORDER BY e.total_usd_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 cex_token_balance ( snapshot_time.text, chain.text, address.text, exchange.text, token_address.text, token_symbol.text, balance.numeric, usd_value.numeric, price.numeric )\n"} {"conversations": [{"role": "user", "content": "Show me the list of hashtags that have been used, along with the time they were first used."}, {"role": "assistant", "content": "SELECT tag_name, created_at \nFROM social_media.hashtags;"}], "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.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 (\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": "Show me how many achievements each player has unlocked."}, {"role": "assistant", "content": "SELECT player_id,\n COUNT(*) AS total_unlocked\nFROM gaming_technology.player_achievements\nGROUP BY player_id;"}, {"role": "user", "content": "Now only include players who have unlocked at least 5 achievements."}, {"role": "assistant", "content": "SELECT player_id,\n COUNT(*) AS total_unlocked\nFROM gaming_technology.player_achievements\nGROUP BY player_id\nHAVING COUNT(*) >= 5;"}, {"role": "user", "content": "Sort the results by total_unlocked in descending order."}, {"role": "assistant", "content": "SELECT player_id,\n COUNT(*) AS total_unlocked\nFROM gaming_technology.player_achievements\nGROUP BY player_id\nHAVING COUNT(*) >= 5\nORDER BY total_unlocked DESC;"}, {"role": "user", "content": "Limit the output to the top 10 players."}, {"role": "assistant", "content": "SELECT player_id,\n COUNT(*) AS total_unlocked\nFROM gaming_technology.player_achievements\nGROUP BY player_id\nHAVING COUNT(*) >= 5\nORDER BY total_unlocked 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 gaming_technology.player_achievements ( player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, achievement_id uuid NOT NULL, unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (player_achievement_id), UNIQUE (player_id, achievement_id) )\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": "I need to identify pairs of verified documents submitted by the same citizen. For each pair, display the citizen_id, the earlier document_id with its verification timestamp, and the later document_id with its verification timestamp."}, {"role": "assistant", "content": "SELECT\n d1.citizen_id,\n d1.document_id AS earlier_document_id,\n d1.verification_timestamp AS earlier_verification,\n d2.document_id AS later_document_id,\n d2.verification_timestamp AS later_verification\nFROM government_services.documents d1\nJOIN government_services.documents d2\n ON d1.citizen_id = d2.citizen_id\n AND d1.verification_timestamp < d2.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": "How many unread notifications are there with the type 'mention'?"}, {"role": "assistant", "content": "SELECT COUNT(*) FROM social_media.notifications WHERE read_at IS NULL AND notification_type = 'mention';"}], "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.conversations ( conversation_id text PRIMARY KEY, created_at timestamp, last_message_at timestamp, is_group_chat bool, group_name text )\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 all properties in California with a star rating above 4.0, along with their room types and base rates."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, rt.type_name, rt.base_rate FROM hospitality_technology.properties p JOIN hospitality_technology.room_types rt ON p.property_id = rt.property_id WHERE p.state_province = 'California' AND p.star_rating > 4.0 ORDER BY p.star_rating DESC;"}, {"role": "user", "content": "Now, filter the results to only include room types with a max occupancy of at least 4 people and a base rate below $300."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, rt.type_name, rt.base_rate, rt.max_occupancy FROM hospitality_technology.properties p JOIN hospitality_technology.room_types rt ON p.property_id = rt.property_id WHERE p.state_province = 'California' AND p.star_rating > 4.0 AND rt.max_occupancy >= 4 AND rt.base_rate < 300 ORDER BY p.star_rating 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.properties ( property_id character varying(64) NOT NULL, property_name character varying(255) NOT NULL, address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state_province character varying(100), postal_code character varying(20) NOT NULL, country_code character varying(3) NOT NULL, phone_number character varying(30), email_address character varying(255), property_type character varying(50) NOT NULL, star_rating numeric(2,1), timezone character varying(64) NOT NULL, manager_staff_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 (property_id) )\nCREATE TABLE hospitality_technology.rooms ( room_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, room_number character varying(10) NOT NULL, room_type_id character varying(64) NOT NULL, floor integer, status character varying(50) NOT NULL, is_smoking boolean NOT NULL DEFAULT false, features text, current_condition text, last_cleaned_at timestamp with time zone, PRIMARY KEY (room_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.room_types ( room_type_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, type_name character varying(100) NOT NULL, description text, base_rate numeric(10, 2) NOT NULL, max_occupancy integer NOT NULL, bed_type character varying(50), area_sqft numeric(8,2), amenities text, PRIMARY KEY (room_type_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\nCREATE TABLE hospitality_technology.reservations ( reservation_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, guest_id character varying(64) NOT NULL, room_id character varying(64), room_type_id character varying(64) NOT NULL, check_in_date date NOT NULL, check_out_date date NOT NULL, actual_check_in_ts timestamp with time zone, actual_check_out_ts timestamp with time zone, num_adults integer NOT NULL, num_children integer DEFAULT 0, status character varying(50) NOT NULL, booking_source character varying(100), rate_plan_id character varying(64), total_amount numeric(12, 2), amount_paid numeric(12, 2) DEFAULT 0.00, special_requests text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (reservation_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.services ( service_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, service_name character varying(150) NOT NULL, description text, category character varying(100), price numeric(10, 2) NOT NULL, unit character varying(30), is_available boolean NOT NULL DEFAULT true, department character varying(100), PRIMARY KEY (service_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\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 ( payment_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, bill_id character varying(64), amount numeric(12,2) NOT NULL, currency_code character varying(3) NOT NULL, payment_method character varying(50) NOT NULL, card_type character varying(50), card_last_four character varying(4), transaction_ref character varying(128), payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, status character varying(50) NOT NULL, staff_id_processed character varying(64), notes text, PRIMARY KEY (payment_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (staff_id_processed) 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 all appointments that are currently scheduled and show their appointment time."}, {"role": "assistant", "content": "SELECT appointment_id, patient_id, doctor_id, appointment_time FROM healthcare.appointments WHERE status = 'Scheduled';"}], "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 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.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": "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": "List all pairs of cases that share the same court jurisdiction, including both case names and their common jurisdiction."}, {"role": "assistant", "content": "SELECT c1.case_name AS case_name_1, c2.case_name AS case_name_2, c1.court_jurisdiction\nFROM legal_services.cases c1\nJOIN legal_services.cases c2\n ON c1.court_jurisdiction = c2.court_jurisdiction\n AND c1.case_id < c2.case_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.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": "How many primary insurance policies are currently active for each plan_id? Show plan_id and active_count."}, {"role": "assistant", "content": "SELECT plan_id,\n COUNT(*) AS active_count\nFROM healthcare.patient_insurance\nWHERE is_primary = TRUE\n AND (expiration_date IS NULL OR expiration_date > CURRENT_DATE)\nGROUP BY 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.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": "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": "Show me the name of all NFTs and their collection names for collections named 'CryptoPunks'."}, {"role": "assistant", "content": "SELECT t1.name AS nft_name, t2.name AS collection_name FROM nft_metadata AS t1 JOIN nft_collections AS t2 ON t1.contract_address = t2.contract_address WHERE t2.name = 'CryptoPunks'"}, {"role": "user", "content": "Okay, now filter that list to only include NFTs with a rarity rank less than 50."}, {"role": "assistant", "content": "SELECT t1.name AS nft_name, t2.name AS collection_name FROM nft_metadata AS t1 JOIN nft_collections AS t2 ON t1.contract_address = t2.contract_address WHERE t2.name = 'CryptoPunks' AND t1.rarity_rank < 50"}, {"role": "user", "content": "For those specific NFTs, also show the owner and the mint price. And only include those owned by address '0xdef...456'."}, {"role": "assistant", "content": "SELECT t1.name AS nft_name, t2.name AS collection_name, t1.owner, t1.mint_price FROM nft_metadata AS t1 JOIN nft_collections AS t2 ON t1.contract_address = t2.contract_address WHERE t2.name = 'CryptoPunks' AND t1.rarity_rank < 50 AND t1.owner = '0xdef...456'"}, {"role": "user", "content": "Instead of listing them, just tell me how many NFTs meet all these criteria."}, {"role": "assistant", "content": "SELECT COUNT(*) FROM nft_metadata AS t1 JOIN nft_collections AS t2 ON t1.contract_address = t2.contract_address WHERE t2.name = 'CryptoPunks' AND t1.rarity_rank < 50 AND t1.owner = '0xdef...456'"}], "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 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 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_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\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 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_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_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 )\n"} {"conversations": [{"role": "user", "content": "List each port along with the count of distinct IP addresses observed on that port."}, {"role": "assistant", "content": "SELECT port, COUNT(DISTINCT ip_address) AS unique_ip_count FROM blockchain.nodes GROUP BY port;"}, {"role": "user", "content": "Only include ports that have more than 3 unique IP addresses."}, {"role": "assistant", "content": "SELECT port, COUNT(DISTINCT ip_address) AS unique_ip_count FROM blockchain.nodes GROUP BY port HAVING COUNT(DISTINCT ip_address) > 3;"}, {"role": "user", "content": "Also include the latest last_seen timestamp for each of these ports."}, {"role": "assistant", "content": "SELECT port, COUNT(DISTINCT ip_address) AS unique_ip_count, MAX(last_seen) AS last_seen_latest FROM blockchain.nodes GROUP BY port HAVING COUNT(DISTINCT ip_address) > 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.nodes ( node_id character varying(64) NOT NULL, ip_address character varying(15) NOT NULL, port integer NOT NULL, last_seen timestamp NOT NULL, PRIMARY KEY (node_id) )\n"}