{"conversations": [{"role": "user", "content": "Can you show, for each employee, the full name and job title of their direct manager, as well as the employee's department and branch_id?"}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name AS employee_first_name, e.last_name AS employee_last_name, e.department AS employee_department, e.branch_id AS employee_branch_id, m.first_name AS manager_first_name, m.last_name AS manager_last_name, m.job_title AS manager_job_title\nFROM financial_services.employees e\nLEFT JOIN financial_services.employees m ON e.manager_id = m.employee_id;"}, {"role": "user", "content": "Actually, show only employees who have a manager assigned, and include only those where the manager works at a different branch than the employee."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name AS employee_first_name, e.last_name AS employee_last_name, e.department AS employee_department, e.branch_id AS employee_branch_id, m.first_name AS manager_first_name, m.last_name AS manager_last_name, m.job_title AS manager_job_title, m.branch_id AS manager_branch_id\nFROM financial_services.employees e\nINNER JOIN financial_services.employees m ON e.manager_id = m.employee_id\nWHERE e.branch_id IS DISTINCT FROM m.branch_id;"}, {"role": "user", "content": "Now, only include employees who were hired after 2021-01-01."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name AS employee_first_name, e.last_name AS employee_last_name, e.department AS employee_department, e.branch_id AS employee_branch_id, m.first_name AS manager_first_name, m.last_name AS manager_last_name, m.job_title AS manager_job_title, m.branch_id AS manager_branch_id\nFROM financial_services.employees e\nINNER JOIN financial_services.employees m ON e.manager_id = m.employee_id\nWHERE e.branch_id IS DISTINCT FROM m.branch_id\n  AND e.hire_date > '2021-01-01';"}], "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 financial_services.accounts ( account_id text, customer_id text, account_number text, account_type text, balance numeric, currency text, opened_date date, status text, interest_rate numeric, last_updated_at timestamp )\nCREATE TABLE financial_services.transactions (\n    transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n    account_id character varying(64) NOT NULL, -- account involved in the transaction\n    related_account_id character varying(64), -- counterpart account for transfers\n    transaction_type character varying(50) NOT NULL, -- e.g., Deposit, Withdrawal, Transfer, Payment, Fee, Interest\n    amount numeric(19, 4) NOT NULL, -- transaction amount\n    currency character varying(3) NOT NULL, -- transaction currency\n    transaction_date timestamp NOT NULL, -- exact time of the transaction\n    effective_date date NOT NULL, -- date the transaction affects the balance\n    description text, -- description or memo of the transaction\n    status character varying(32) NOT NULL, -- e.g., Pending, Completed, Failed, Reversed\n    reference_number character varying(128), -- external reference if applicable (e.g., check number)\n    PRIMARY KEY (transaction_id),\n    FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id),\n    FOREIGN KEY (related_account_id) REFERENCES financial_services.accounts(account_id)\n)\nCREATE TABLE financial_services.trades ( trade_id text PRIMARY KEY, account_id text, security_id text, order_id text, trade_type text, quantity numeric, price_per_unit numeric, total_amount numeric, commission numeric, trade_timestamp timestamp, settlement_date date, status text, execution_venue text )\nCREATE TABLE financial_services.market_data ( data_point_id.bigint, security_id.text, data_timestamp.timestamp, open_price.numeric, high_price.numeric, low_price.numeric, close_price.numeric, adjusted_close_price.numeric, volume.bigint, source.text )\nCREATE TABLE financial_services.employees (\n    employee_id character varying(64) NOT NULL,  -- unique identifier for the employee\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(100) NOT NULL, -- e.g., Teller, Branch Manager, Financial Advisor, Analyst\n    department character varying(100), -- e.g., Retail Banking, Wealth Management, IT\n    branch_id character varying(64), -- Identifier for the branch they work at (if applicable)\n    email character varying(128) NOT NULL UNIQUE,\n    phone_extension character varying(20),\n    hire_date date NOT NULL,\n    termination_date date, -- Date of termination, null if currently employed\n    manager_id character varying(64), -- Self-referencing key for manager relationship\n    status character varying(32) NOT NULL, -- e.g., Active, Terminated, On Leave\n    PRIMARY KEY (employee_id),\n    FOREIGN KEY (branch_id) REFERENCES financial_services.branches(branch_id), -- Assuming a branches table exists\n    FOREIGN KEY (manager_id) REFERENCES financial_services.employees(employee_id)\n)\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": "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": "Get the number of documents for each case, showing case_id and document count, ordered by count descending."}, {"role": "assistant", "content": "SELECT case_id,\n       COUNT(*) AS document_count\nFROM legal_services.documents\nGROUP BY case_id\nORDER BY document_count DESC;"}, {"role": "user", "content": "Actually, only count documents of type 'Evidence'."}, {"role": "assistant", "content": "SELECT case_id,\n       COUNT(*) AS evidence_count\nFROM legal_services.documents\nWHERE document_type = 'Evidence'\nGROUP BY case_id\nORDER BY evidence_count DESC;"}, {"role": "user", "content": "Also, include the case_name from the cases table."}, {"role": "assistant", "content": "SELECT d.case_id,\n       c.case_name,\n       COUNT(*) AS evidence_count\nFROM legal_services.documents d\nJOIN legal_services.cases c ON d.case_id = c.case_id\nWHERE d.document_type = 'Evidence'\nGROUP BY d.case_id, c.case_name\nORDER BY evidence_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.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.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\nCREATE TABLE legal_services.documents ( document_id.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\nCREATE TABLE legal_services.time_entries ( entry_id text PRIMARY KEY, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable bool, is_billed bool, invoice_id text, created_at timestamp )\nCREATE TABLE legal_services.invoices ( invoice_id text PRIMARY KEY, invoice_number text UNIQUE, client_id text, case_id text, issue_date date, due_date date, total_amount numeric, amount_paid numeric, status text, payment_date timestamp, notes text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Find currently employed employees whose direct manager has been terminated. Display the employee's full name, hire date, manager's full name, and manager's termination date."}, {"role": "assistant", "content": "SELECT e.employee_id,\n       CONCAT(e.first_name, ' ', e.last_name) AS employee_full_name,\n       e.hire_date,\n       CONCAT(m.first_name, ' ', m.last_name) AS manager_full_name,\n       m.termination_date\nFROM government_services.employees e\nJOIN government_services.employees m ON e.manager_employee_id = m.employee_id\nWHERE e.termination_date IS NULL\n  AND m.termination_date IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees (\n    employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(150) NOT NULL,\n    department character varying(100),\n    work_email character varying(128) NOT NULL UNIQUE,\n    work_phone character varying(32),\n    hire_date date NOT NULL,\n    termination_date date, -- null if currently employed\n    access_level character varying(50), -- Role or permission level\n    manager_employee_id character varying(64), -- FK to self for reporting structure\n    PRIMARY KEY (employee_id)\n)\nCREATE TABLE government_services.service_locations ( location_id text PRIMARY KEY, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"}
{"conversations": [{"role": "user", "content": "Which states have the highest number of customers? Provide the top 5 states along with their customer counts, ordered by count descending."}, {"role": "assistant", "content": "SELECT\n  state,\n  COUNT(*) AS customer_count\nFROM insurance.customers\nGROUP BY state\nORDER BY customer_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 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)\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": "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": "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": "For each premium payment, list all previous payments made by the same customer. Show customer_id, previous_payment_id, previous_payment_date, current_payment_id, current_payment_date, and amount difference."}, {"role": "assistant", "content": "SELECT p1.customer_id,\n       p1.payment_id AS previous_payment_id,\n       p1.payment_date AS previous_payment_date,\n       p2.payment_id AS current_payment_id,\n       p2.payment_date AS current_payment_date,\n       p2.amount_paid - p1.amount_paid AS amount_diff\nFROM insurance.premium_payments p1\nJOIN insurance.premium_payments p2\n  ON p1.customer_id = p2.customer_id\n  AND p1.payment_date < p2.payment_date;"}, {"role": "user", "content": "Actually, only include pairs where the current payment date is in 2024."}, {"role": "assistant", "content": "SELECT p1.customer_id,\n       p1.payment_id AS previous_payment_id,\n       p1.payment_date AS previous_payment_date,\n       p2.payment_id AS current_payment_id,\n       p2.payment_date AS current_payment_date,\n       p2.amount_paid - p1.amount_paid AS amount_diff\nFROM insurance.premium_payments p1\nJOIN insurance.premium_payments p2\n  ON p1.customer_id = p2.customer_id\n  AND p1.payment_date < p2.payment_date\nWHERE p2.payment_date BETWEEN '2024-01-01' AND '2024-12-31';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.premium_payments ( payment_id text, policy_id text, customer_id text, payment_date timestamp, amount_paid numeric, payment_method text, transaction_reference text, due_date date, payment_period_start date, payment_period_end date, status text )\n"}
{"conversations": [{"role": "user", "content": "Show me all distinct dosage forms used in prescriptions."}, {"role": "assistant", "content": "SELECT DISTINCT dosage FROM healthcare.prescriptions;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.prescriptions ( prescription_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed int, prescription_date timestamp )\n"}
{"conversations": [{"role": "user", "content": "Find all NFTs with a rarity rank less than 100 and show their name and the name of their collection."}, {"role": "assistant", "content": "SELECT nm.name AS nft_name, nc.name AS collection_name FROM nft_metadata nm JOIN nft_collections nc ON nm.contract_address = nc.contract_address WHERE nm.rarity_rank < 100;"}, {"role": "user", "content": "Filter that further to only include NFTs from collections named 'Bored Ape Yacht Club'."}, {"role": "assistant", "content": "SELECT nm.name AS nft_name, nc.name AS collection_name FROM nft_metadata nm JOIN nft_collections nc ON nm.contract_address = nc.contract_address WHERE nm.rarity_rank < 100 AND nc.name = 'Bored Ape Yacht Club';"}], "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 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 ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\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 ( 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_nfts ( object_id varchar, status varchar, collection_type varchar, package_id varchar, previous_transaction varchar, display varchar, owner 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 ( uuid varchar, blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\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_balances ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( 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 ( 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_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, 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 ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\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 each patient's first_name, last_name, and the plan_name and policy_number of their primary insurance plan."}, {"role": "assistant", "content": "SELECT p.first_name,\n       p.last_name,\n       ip.plan_name,\n       pi.policy_number\nFROM healthcare.patients p\nJOIN healthcare.patient_insurance pi ON p.patient_id = pi.patient_id AND pi.is_primary = TRUE\nJOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id.text, record_id.text, patient_id.text, doctor_id.text, diagnosis_code.text, code_type.text, description.text, diagnosis_date.date, status.text, is_chronic.boolean )\nCREATE TABLE healthcare.prescriptions ( prescription_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, medication_id character varying(64) NOT NULL, dosage character varying(100) NOT NULL, frequency character varying(100) NOT NULL, route character varying(50), start_date date NOT NULL, end_date date, quantity_dispensed numeric(10,2), refills_allowed integer NOT NULL DEFAULT 0, prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (prescription_id) )\nCREATE TABLE healthcare.insurance_plans (\n    plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n    plan_name character varying(200) NOT NULL, -- name of the insurance plan\n    insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n    plan_type character varying(50), -- e.g., PPO, HMO, EPO\n    contact_phone character varying(20), -- provider contact number\n    website character varying(255), -- provider website\n    PRIMARY KEY (plan_id)\n)\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text PRIMARY KEY, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"}
{"conversations": [{"role": "user", "content": "Get the total fuel cost per route, showing route_number and the sum of total_cost for all fuel logs associated with trips on that route."}, {"role": "assistant", "content": "SELECT r.route_number,\n       SUM(fl.total_cost) AS total_fuel_cost\nFROM transportation.routes r\nJOIN transportation.trips t ON r.route_id = t.route_id\nJOIN transportation.fuel_logs fl ON t.trip_id = fl.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.vehicles ( vehicle_id.text, license_plate.text, vin.text, make.text, model.text, year.integer, type.text, capacity.integer, fuel_type.text, status.text, depot_id.text, acquisition_date.date )\nCREATE TABLE transportation.routes ( route_id.text, route_number.text, description.text, origin_location_id.text, destination_location_id.text, distance_km.numeric, estimated_duration_minutes.integer, type.text )\nCREATE TABLE transportation.trips ( trip_id.text, route_id.text, vehicle_id.text, driver_id.text, scheduled_departure.timestamp, actual_departure.timestamp, scheduled_arrival.timestamp, actual_arrival.timestamp, origin_location_id.text, destination_location_id.text, status.text, passenger_count.integer, cargo_manifest_id.text )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\nCREATE TABLE transportation.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": "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": "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": "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": "Which chain has the highest total trading volume in the last 24 hours, and what is the top token by volume on that chain?"}, {"role": "assistant", "content": "WITH chain_volume AS (SELECT chain, SUM(volume_24h) AS total_volume_24h FROM token_dexpool_info GROUP BY chain), top_chain AS (SELECT chain FROM chain_volume ORDER BY total_volume_24h DESC LIMIT 1), top_token AS (SELECT token_symbol, volume_24h FROM token_dexpool_info WHERE chain = (SELECT chain FROM top_chain) ORDER BY volume_24h DESC LIMIT 1) SELECT c.chain, c.total_volume_24h, t.token_symbol, t.volume_24h AS top_token_volume FROM chain_volume c JOIN top_chain tc ON c.chain = tc.chain JOIN top_token t ON TRUE;"}, {"role": "user", "content": "Can you show the top 3 tokens by trading volume for that chain as well, including their price?"}, {"role": "assistant", "content": "WITH top_chain AS (SELECT chain FROM token_dexpool_info GROUP BY chain ORDER BY SUM(volume_24h) DESC LIMIT 1) SELECT token_symbol, price, volume_24h FROM token_dexpool_info WHERE chain = (SELECT chain FROM top_chain) ORDER BY volume_24h DESC LIMIT 3;"}, {"role": "user", "content": "Actually, please include the market cap for each of those top 3 tokens."}, {"role": "assistant", "content": "WITH top_chain AS (SELECT chain FROM token_dexpool_info GROUP BY chain ORDER BY SUM(volume_24h) DESC LIMIT 1) SELECT token_symbol, price, volume_24h, market_cap FROM token_dexpool_info WHERE chain = (SELECT chain FROM top_chain) ORDER BY volume_24h DESC LIMIT 3;"}, {"role": "user", "content": "I only want tokens where the market cap is above 100 million. Show those top 3 tokens by volume for the chain."}, {"role": "assistant", "content": "WITH top_chain AS (SELECT chain FROM token_dexpool_info GROUP BY chain ORDER BY SUM(volume_24h) DESC LIMIT 1) SELECT token_symbol, price, volume_24h, market_cap FROM token_dexpool_info WHERE chain = (SELECT chain FROM top_chain) AND market_cap > 100000000 ORDER BY volume_24h DESC LIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, -- the id of dexpool token_name character varying(100) NOT NULL, -- the name of the token in the dexpool token_symbol character varying(100) NOT NULL, -- the token's symbol chain text, -- the chain that the dexpool resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_6h double precision, -- change in value divided by the absolute price value of the original token price in 6 hours price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours makers_24h double precision, -- the makers of the dex pool in 24 hours volume_24h double precision, -- the trade volume of the dex pool in 24 hours liquidity double precision, -- the liquidity of the dex pool market_cap double precision, -- the market cap of the token trend_rank bigint, -- the rank of token in the dex pool of recent trending, value 1 expresses the most popular token. ,PRIMARY KEY (pair_address, chain) )\n"}
{"conversations": [{"role": "user", "content": "I need to get the inventory quantity and location for a specific batch number. Can you help with that?"}, {"role": "assistant", "content": "HGETALL inv:<inventory_record_id>"}, {"role": "user", "content": "Can you also show me the component ID associated with this batch?"}, {"role": "assistant", "content": "HGETALL inv:<inventory_record_id>"}, {"role": "user", "content": "If I want to retrieve multiple inventory records for the same component ID, how can I do that?"}, {"role": "assistant", "content": "ZRANGE component_expiry:<component_id> 0 -1"}, {"role": "user", "content": "Can you sort those records by expiry date in ascending order?"}, {"role": "assistant", "content": "ZRANGE component_expiry:<component_id> 0 -1 WITHSCORES"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nUse Hashes. Key pattern: 'inv:<inventory_record_id>'. Example: HSET inv:INVREC500 component_id \"component:WINGBOLT\" quantity 5000 location_warehouse \"WH3\" batch_number \"BCH778899\" ... Consider Sorted Set by expiry date: ZADD component_expiry:<component_id> <expiry_timestamp> <inventory_record_id>.\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": "Can you show me the total number of passengers registered in the database?"}, {"role": "assistant", "content": "db.passengers.countDocuments({})"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// db.createCollection('passengers')\n// Optional: db.passengers.createIndex({ passenger_id: 1 }, { unique: true })\n// Optional: db.passengers.createIndex({ email: 1 }, { unique: true, sparse: true })\n// Optional: db.passengers.createIndex({ phone_number: 1 }, { unique: true, sparse: true })\n{\n  _id: ObjectId(),\n  passenger_id: \"pass_pqr\", // String (unique)\n  first_name: \"Alice\", // String\n  last_name: \"Smith\", // String\n  email: \"alice.smith@example.com\", // String (unique, sparse)\n  phone_number: \"+15551234567\", // String (unique, sparse)\n  date_of_birth: ISODate(\"1990-03-20\"), // Date\n  loyalty_program_id: \"LOYALTY123\", // String\n  created_at: ISODate(\"2023-02-01T11:00:00Z\") // Date\n}\n"}
{"conversations": [{"role": "user", "content": "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 tokens had a net positive flow according to smart_money_token_performance, and what is their average ROI?"}, {"role": "assistant", "content": "SELECT COUNT(*) AS token_count, AVG(roi) AS avg_roi\nFROM smart_money_token_performance\nWHERE net_flow > 0;"}, {"role": "user", "content": "Now, break this down by chain, and order the results by avg_roi descending."}, {"role": "assistant", "content": "SELECT chain, COUNT(*) AS token_count, AVG(roi) AS avg_roi\nFROM smart_money_token_performance\nWHERE net_flow > 0\nGROUP BY chain\nORDER BY avg_roi DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\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 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": "Find all patients who have been prescribed medications with dosage greater than 50mg, along with their medication details and prescribing doctor's name."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name, p.last_name, pr.dosage, pr.medication_id, pr.start_date, doc.first_name AS doctor_first_name, doc.last_name AS doctor_last_name FROM healthcare.patients p JOIN healthcare.prescriptions pr ON p.patient_id = pr.patient_id JOIN healthcare.doctors doc ON pr.doctor_id = doc.doctor_id WHERE CAST(SUBSTRING_INDEX(pr.dosage, 'mg', 1) AS UNSIGNED) > 50;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id.text, first_name.text, last_name.text, date_of_birth.date, gender.text, address.text, phone_number.text, email.text, emergency_contact_name.text, emergency_contact_phone.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id.text, record_id.text, patient_id.text, doctor_id.text, diagnosis_code.text, code_type.text, description.text, diagnosis_date.date, status.text, is_chronic.boolean )\nCREATE TABLE healthcare.prescriptions ( prescription_id.text, record_id.text, patient_id.text, doctor_id.text, medication_id.text, dosage.text, frequency.text, route.text, start_date.date, end_date.date, quantity_dispensed.numeric, refills_allowed.integer, prescription_date.timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\n"}
{"conversations": [{"role": "user", "content": "List the full name of citizens who have appointments scheduled for services in the 'Licensing' category."}, {"role": "assistant", "content": "SELECT T1.full_name FROM government_services.citizens AS T1 JOIN government_services.appointments AS T2 ON T1.citizen_id = T2.citizen_id JOIN government_services.services AS T3 ON T2.service_id = T3.service_id WHERE T3.category = 'Licensing'"}], "system": "You are an SQL statement expert. Given the table structure 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.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": "List all guests who have never left a review, including their full name and email."}, {"role": "assistant", "content": "SELECT g.guest_id, g.first_name, g.last_name, g.email \nFROM hospitality_technology.guests g \nLEFT JOIN hospitality_technology.reviews r ON g.guest_id = r.guest_id \nWHERE r.review_id IS NULL;"}, {"role": "user", "content": "Can you also include their phone number?"}, {"role": "assistant", "content": "SELECT g.guest_id, g.first_name, g.last_name, g.email, g.phone_number \nFROM hospitality_technology.guests g \nLEFT JOIN hospitality_technology.reviews r ON g.guest_id = r.guest_id \nWHERE r.review_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 hospitality_technology.properties ( property_id text PRIMARY KEY, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.rooms ( room_id text PRIMARY KEY, property_id text, room_number text, room_type_id text, floor int, status text, is_smoking boolean, features text, current_condition text, last_cleaned_at timestamp )\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 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 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 ( 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 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 )\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 text PRIMARY KEY, property_id text, reservation_id text, guest_id text, rating_overall int, rating_cleanliness int, rating_service int, rating_location int, rating_value int, 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": "List each citizen's first and last name alongside the first and last name of another citizen born in the same year but with a different national ID number."}, {"role": "assistant", "content": "SELECT c1.first_name  AS first_name_1,\n       c1.last_name   AS last_name_1,\n       c2.first_name  AS first_name_2,\n       c2.last_name   AS last_name_2,\n       EXTRACT(YEAR FROM c1.date_of_birth) AS birth_year\nFROM government_services.citizens c1\nJOIN government_services.citizens c2\n  ON EXTRACT(YEAR FROM c1.date_of_birth) = EXTRACT(YEAR FROM c2.date_of_birth)\n AND c1.national_id_number <> c2.national_id_number\n AND c1.citizen_id < c2.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, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\n"}
{"conversations": [{"role": "user", "content": "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<String> 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": "Find all room types that have 'sofa' mentioned in their amenities."}, {"role": "assistant", "content": "SELECT * FROM hospitality_technology.room_types WHERE amenities LIKE '%sofa%'"}, {"role": "user", "content": "Also include the max_occupancy and filter to only show those with a base_rate less than 300."}, {"role": "assistant", "content": "SELECT type_name ,  max_occupancy ,  base_rate ,  amenities FROM hospitality_technology.room_types WHERE amenities LIKE '%sofa%' AND base_rate  <  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.room_types (\n    room_type_id character varying(64) NOT NULL, -- unique identifier for the room type\n    property_id character varying(64) NOT NULL, -- FK to properties table (type might be property-specific)\n    type_name character varying(100) NOT NULL, -- e.g., Standard King, Deluxe Queen, Executive Suite\n    description text, -- description of the room type\n    base_rate numeric(10, 2) NOT NULL, -- standard price per night\n    max_occupancy integer NOT NULL, -- maximum number of guests\n    bed_type character varying(50), -- e.g., King, Queen, 2 Doubles, Twin\n    area_sqft numeric(8,2), -- size of the room in square feet\n    amenities text, -- comma-separated list or JSON of amenities\n    PRIMARY KEY (room_type_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\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": "List all tokens on the 'Ethereum' chain with DEX 24h volume over 1000000. Show token_symbol, price, and volume_24h."}, {"role": "assistant", "content": "SELECT token_symbol, price, volume_24h\nFROM token_dexpool_info\nWHERE chain = 'Ethereum' AND volume_24h > 1000000;"}, {"role": "user", "content": "Also show the total USD inflow from smart money (type=1) for each token."}, {"role": "assistant", "content": "SELECT t.token_symbol, t.price, t.volume_24h, COALESCE(SUM(i.usd_value),0) AS total_usd_inflow\nFROM token_dexpool_info t\nLEFT JOIN smart_money_token_inflow i\n  ON t.token_symbol = i.token_symbol\n  AND t.chain = i.chain\n  AND i.type = 1\nWHERE t.chain = 'Ethereum' AND t.volume_24h > 1000000\nGROUP BY t.token_symbol, t.price, t.volume_24h;"}, {"role": "user", "content": "Filter to only include tokens with total USD inflow greater than 500000."}, {"role": "assistant", "content": "SELECT t.token_symbol, t.price, t.volume_24h, COALESCE(SUM(i.usd_value),0) AS total_usd_inflow\nFROM token_dexpool_info t\nLEFT JOIN smart_money_token_inflow i\n  ON t.token_symbol = i.token_symbol\n  AND t.chain = i.chain\n  AND i.type = 1\nWHERE t.chain = 'Ethereum' AND t.volume_24h > 1000000\nGROUP BY t.token_symbol, t.price, t.volume_24h\nHAVING COALESCE(SUM(i.usd_value),0) > 500000;"}, {"role": "user", "content": "Order the results by total USD inflow descending and limit to top 5."}, {"role": "assistant", "content": "SELECT t.token_symbol, t.price, t.volume_24h, COALESCE(SUM(i.usd_value),0) AS total_usd_inflow\nFROM token_dexpool_info t\nLEFT JOIN smart_money_token_inflow i\n  ON t.token_symbol = i.token_symbol\n  AND t.chain = i.chain\n  AND i.type = 1\nWHERE t.chain = 'Ethereum' AND t.volume_24h > 1000000\nGROUP BY t.token_symbol, t.price, t.volume_24h\nHAVING COALESCE(SUM(i.usd_value),0) > 500000\nORDER BY total_usd_inflow 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 project_fundraising_record ( id.text, project_id.text, project_name.text, rounds_name.text, investment_value.numeric, investment_date.text, introduction.text, valuation.numeric )\nCREATE TABLE narrative_info ( narrative.text, top_3_coins.text, price_change_percentage_1h.numeric, price_change_percentage_24h.numeric, price_change_percentage_7d.numeric, market_cap.numeric, volume_24h.numeric, trend_rank.numeric, token_num.numeric )\nCREATE TABLE token_dexpool_info ( pair_address 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) )\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  \"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": "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 the usernames and emails of users who have set a location in their profile."}, {"role": "assistant", "content": "SELECT username, email\nFROM social_media.users\nWHERE location IS NOT NULL AND location != '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.comments ( comment_id text, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.follows ( follow_id text, follower_user_id text, following_user_id text, created_at timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text, post_id text, hashtag_id text )\nCREATE TABLE social_media.messages ( message_id text, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\nCREATE TABLE social_media.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications ( notification_id text, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\nCREATE TABLE social_media.user_settings ( setting_id text, user_id text, theme text, email_notifications_enabled boolean, push_notifications_enabled boolean, private_profile boolean, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "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": "Show me the top 3 smart money addresses by profit across all chains, along with their most profitable token and chain information."}, {"role": "assistant", "content": "SELECT address, profit, most_profit_token, chain\nFROM smart_money_profit\nORDER BY profit DESC\nLIMIT 3;"}, {"role": "user", "content": "Actually, I only want to see addresses from Ethereum chain with ROI over 30%."}, {"role": "assistant", "content": "SELECT address, profit, most_profit_token, roi\nFROM smart_money_profit\nWHERE chain = 'Ethereum' AND roi > 30\nORDER BY profit DESC\nLIMIT 3;"}, {"role": "user", "content": "Can you add their realized profit ratio and filter to only show results with profit over $100,000?"}, {"role": "assistant", "content": "SELECT address, profit, most_profit_token, roi, realized_ratio\nFROM smart_money_profit\nWHERE chain = 'Ethereum' AND roi > 30 AND profit > 100000\nORDER BY profit DESC\nLIMIT 3;"}, {"role": "user", "content": "Now order these results by ROI in descending order instead of profit."}, {"role": "assistant", "content": "SELECT address, profit, most_profit_token, roi, realized_ratio\nFROM smart_money_profit\nWHERE chain = 'Ethereum' AND roi > 30 AND profit > 100000\nORDER BY roi 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 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 )\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 smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\n"}
{"conversations": [{"role": "user", "content": "What is the total USD value held across all wallets for the ERC20 token with symbol 'DAI'?"}, {"role": "assistant", "content": "SELECT SUM((eb.amount::numeric / POWER(10, tm.decimals)) * tpl.price) AS total_usd\nFROM erc20_balances eb\nJOIN token_metas tm ON eb.contract_address = tm.contract_address AND tm.symbol = 'DAI'\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum';"}, {"role": "user", "content": "Could you break it down to show the top 5 wallets by USD value for this token?"}, {"role": "assistant", "content": "SELECT eb.wallet_address,\n       SUM((eb.amount::numeric / POWER(10, tm.decimals)) * tpl.price) AS usd_value\nFROM erc20_balances eb\nJOIN token_metas tm ON eb.contract_address = tm.contract_address AND tm.symbol = 'DAI'\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum'\nGROUP BY eb.wallet_address\nORDER BY usd_value DESC\nLIMIT 5;"}, {"role": "user", "content": "I received a type error because amount is stored as text. Can you cast the fields to numeric explicitly in the query?"}, {"role": "assistant", "content": "SELECT eb.wallet_address,\n       SUM((CAST(eb.amount AS numeric) / POWER(10, tm.decimals)) * CAST(tpl.price AS numeric)) AS usd_value\nFROM erc20_balances eb\nJOIN token_metas tm ON eb.contract_address = tm.contract_address AND tm.symbol = 'DAI'\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum'\nGROUP BY eb.wallet_address\nORDER BY usd_value DESC\nLIMIT 5;"}, {"role": "user", "content": "Also include the latest price timestamp alongside the USD value for each wallet."}, {"role": "assistant", "content": "SELECT eb.wallet_address,\n       SUM((CAST(eb.amount AS numeric) / POWER(10, tm.decimals)) * tpl.price) AS usd_value,\n       MAX(tpl.timestamp) AS price_timestamp\nFROM erc20_balances eb\nJOIN token_metas tm ON eb.contract_address = tm.contract_address AND tm.symbol = 'DAI'\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum'\nGROUP BY eb.wallet_address\nORDER BY usd_value 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 ( 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, 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_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 varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\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 (\n    blockchain varchar NOT NULL, -- blockchain fields for the functionType  in contract\n    contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n    name varchar NOT NULL, -- name fields for the functionType  in contract\n    symbol varchar NOT NULL, -- symbol fields for the functionType  in contract\n    deploy_block_number bigint NOT NULL, -- deploy_block_number fields for the functionType  in contract\n    deploy_block_time bigint NOT NULL, -- deploy_block_time fields for the functionType  in contract\n    erc_type varchar NOT NULL, -- The type of token\n    owner varchar NOT NULL, -- owner fields for the functionType  in contract\n    traits varchar NOT NULL, -- traits fields for the functionType  in contract\n    description varchar NOT NULL, -- description fields for the functionType  in contract\n    slug varchar NOT NULL, -- slug fields for the functionType  in contract\n    media_info varchar NOT NULL, -- media_info fields for the functionType  in contract\n    image_url varchar NOT NULL, -- image_url fields for the functionType  in contract\n    banner_image_url varchar NOT NULL, -- banner_image_url fields for the functionType  in contract\n    updated_at bigint NOT NULL, -- updated_at fields for the functionType  in contract\n    banner varchar NOT NULL, -- banner fields for the functionType  in contract\n    token_count bigint NOT NULL, -- token_count fields for the functionType  in contract\n    floor_price varchar NOT NULL, -- floor_price fields for the functionType  in contract\n    floor_price_symbol varchar NOT NULL, -- floor_price_symbol fields for the functionType  in contract\n    floor_price_contract varchar NOT NULL, -- floor_price_contract fields for the functionType  in contract\n    pk integer NOT NULL  -- Partition key for the table(floor(deploy_block_time / 1000 / 86400 / 30))\n)\nCREATE TABLE token_prices ( uuid varchar, blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest (\n    blockchain varchar(36) NOT NULL, -- blockchain fields for the functionType  in contract\n    address varchar(42) NOT NULL, -- address fields for the functionType  in contract\n    decimals bigint NOT NULL, -- decimals fields for the functionType  in contract\n    symbol varchar(36) NOT NULL, -- symbol fields for the functionType  in contract\n    price real NOT NULL, -- price fields for the functionType  in contract\n    timestamp timestamp(6) NOT NULL  -- timestamp fields for the functionType  in contract\n)\nCREATE TABLE erc20_approval ( block_number bigint, 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_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_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": "What is the history of incidents or accidents that occurred on platform 5 at station GHI?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about the history of incidents or accidents on platform 5 at station GHI. My data is limited to the structural and operational details of the platforms, such as platform ID, station ID, and status. For incident history, you may need to consult a different database or contact the relevant authorities."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.platforms ( platform_id.text, station_id.text, platform_number.text, track_number.text, status.text, length_meters.numeric, accessible.boolean )\n"}
{"conversations": [{"role": "user", "content": "How many documents of each type exist in the system? Show the document type and the count."}, {"role": "assistant", "content": "SELECT document_type, COUNT(*) AS document_count\nFROM legal_services.documents\ngroup BY document_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text, first_name text, last_name text, company_name text, email text, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.law_firms ( firm_id text, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\nCREATE TABLE legal_services.documents ( document_id text, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version integer, description text )\nCREATE TABLE legal_services.time_entries ( entry_id text, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable boolean, is_billed boolean, invoice_id text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "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": "Find all contracts where the deployer address is the same as the contract address, indicating self-deployed contracts, and show their network IDs and deployment timestamps."}, {"role": "assistant", "content": "SELECT address, network_id, deployed_at FROM web3.contracts WHERE address = deployer_address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id character varying(64) NOT NULL, address character varying(128) NOT NULL, abi text NOT NULL, bytecode text NOT NULL, deployer_address character varying(128) NOT NULL, deployed_at timestamp NOT NULL, network_id character varying(64) NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (contract_id) )\n"}
{"conversations": [{"role": "user", "content": "List all events and any token transfers that occurred in the same transaction, showing event_id, event_name, transfer_id, and token_symbol."}, {"role": "assistant", "content": "SELECT\n  e.event_id,\n  e.event_name,\n  tt.transfer_id,\n  tk.token_symbol\nFROM web3.events e\nLEFT JOIN web3.token_transfers tt\n  ON e.transaction_id = tt.transaction_id\nLEFT JOIN web3.tokens tk\n  ON tt.token_id = tk.token_id\nORDER BY e.transaction_id, e.log_index;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id character varying(64) NOT NULL, address character varying(128) NOT NULL, abi text NOT NULL, bytecode text NOT NULL, deployer_address character varying(128) NOT NULL, deployed_at timestamp NOT NULL, network_id character varying(64) NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (contract_id) )\nCREATE TABLE web3.events ( event_id.text, contract_id.text, event_name.text, data.text, emitted_at.timestamp, transaction_id.text, log_index.integer )\nCREATE TABLE web3.tokens (\n    token_id character varying(64) NOT NULL,  -- unique identifier for the token\n    contract_address character varying(128) NOT NULL, -- address of the token contract\n    token_name character varying(128) NOT NULL, -- name of the token\n    token_symbol character varying(32) NOT NULL, -- symbol of the token\n    decimals integer NOT NULL, -- number of decimals for the token\n    total_supply numeric(38,14) NOT NULL, -- total supply of the token\n    PRIMARY KEY (token_id)\n)\nCREATE TABLE web3.token_transfers ( transfer_id text PRIMARY KEY, token_id text, from_address text, to_address text, value numeric, transaction_id text, log_index int )\nCREATE TABLE web3.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List the names and rarity of all items with a cost above 50."}, {"role": "assistant", "content": "SELECT item_name, rarity\nFROM gaming_technology.in_game_items\nWHERE cost_amount > 50;"}, {"role": "user", "content": "Now, only include items where the rarity is 'Epic' or 'Legendary'."}, {"role": "assistant", "content": "SELECT item_name, rarity\nFROM gaming_technology.in_game_items\nWHERE cost_amount > 50\nAND rarity IN ('Epic', 'Legendary');"}, {"role": "user", "content": "Also show the item_type and order by cost_amount descending."}, {"role": "assistant", "content": "SELECT item_name, item_type, rarity, cost_amount\nFROM gaming_technology.in_game_items\nWHERE cost_amount > 50\nAND rarity IN ('Epic', 'Legendary')\nORDER BY cost_amount DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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)\n"}
{"conversations": [{"role": "user", "content": "Show me all customers who have missing contact information (either phone number or email is null), along with their state and city."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city FROM insurance.customers WHERE phone_number IS NULL OR email IS NULL;"}, {"role": "user", "content": "Now filter these to only show customers from Florida or New York who were created in the last year."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '1 year';"}, {"role": "user", "content": "I also want to see when these customers were last updated (updated_at field)."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city, updated_at FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '1 year';"}, {"role": "user", "content": "Finally, order the results by state first, then by the most recently updated customers first."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city, updated_at FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '1 year' ORDER BY state, updated_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.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)\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": "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": "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": "What is the average investment_value and total number of projects for each rounds_name in project_fundraising_record?"}, {"role": "assistant", "content": "SELECT rounds_name,\n       AVG(investment_value) AS avg_investment,\n       COUNT(DISTINCT project_id) AS project_count\nFROM project_fundraising_record\nGROUP BY rounds_name;"}, {"role": "user", "content": "Please show only rounds where project_count > 5, and order by avg_investment descending."}, {"role": "assistant", "content": "SELECT rounds_name,\n       AVG(investment_value) AS avg_investment,\n       COUNT(DISTINCT project_id) AS project_count\nFROM project_fundraising_record\nGROUP BY rounds_name\nHAVING COUNT(DISTINCT project_id) > 5\nORDER BY avg_investment DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id text, project_id text, project_name text, rounds_name text, investment_value numeric, investment_date text, introduction text, valuation numeric )\nCREATE TABLE token_basic_info ( coin_id text, token_name text, token_symbol text, token_address text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, highest_price_24h numeric, lowest_price_24h numeric, market_cap numeric, market_cap_rank numeric, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank numeric )\nCREATE TABLE narrative_info ( narrative text, top_3_coins text, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, market_cap numeric, volume_24h numeric, trend_rank numeric, token_num numeric )\nCREATE TABLE token_dexpool_info ( pair_address text, token_name text, token_symbol text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_6h numeric, price_change_percentage_24h numeric, makers_24h numeric, volume_24h numeric, liquidity numeric, market_cap numeric, trend_rank numeric )\nCREATE TABLE smart_money_token_performance ( token_address text, token_symbol text, pnl numeric, net_flow numeric, avg_cost numeric, price numeric, realized_ratio numeric, roi numeric, chain text )\n"}
{"conversations": [{"role": "user", "content": "For each type of entity a notification can be related to, how many notifications have been successfully sent?"}, {"role": "assistant", "content": "SELECT related_entity_type, COUNT(*) AS sent_notification_count FROM government_services.notifications WHERE status = 'Sent' GROUP BY related_entity_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.services ( service_id text PRIMARY KEY, agency_id text, service_name text, description text, category text, eligibility_criteria text, standard_fee numeric, average_processing_time_days int, is_active boolean, online_application_url text )\nCREATE TABLE government_services.documents (\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.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees (\n    employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(150) NOT NULL,\n    department character varying(100),\n    work_email character varying(128) NOT NULL UNIQUE,\n    work_phone character varying(32),\n    hire_date date NOT NULL,\n    termination_date date, -- null if currently employed\n    access_level character varying(50), -- Role or permission level\n    manager_employee_id character varying(64), -- FK to self for reporting structure\n    PRIMARY KEY (employee_id)\n)\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"}
{"conversations": [{"role": "user", "content": "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": "Show me each patient's full name along with the name of every doctor they've had an appointment with."}, {"role": "assistant", "content": "SELECT p.first_name || ' ' || p.last_name AS patient_full_name, d.first_name || ' ' || d.last_name AS doctor_full_name\nFROM healthcare.appointments a\nJOIN healthcare.patients p ON a.patient_id = p.patient_id\nJOIN healthcare.doctors d ON a.doctor_id = d.doctor_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.doctors ( doctor_id text PRIMARY KEY, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id text PRIMARY KEY, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes int, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medications ( medication_id text PRIMARY KEY, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed int, prescription_date timestamp )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text PRIMARY KEY, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"}
{"conversations": [{"role": "user", "content": "Show me all wallet addresses that belong to user_id 'U12345'."}, {"role": "assistant", "content": "SELECT address_id FROM blockchain.wallets WHERE user_id = 'U12345';"}, {"role": "user", "content": "Now join this with another table to show the private_key for these addresses."}, {"role": "assistant", "content": "SELECT w.address_id, w.private_key FROM blockchain.wallets w WHERE w.user_id = 'U12345';"}], "system": "You are an SQL statement expert. Given the table structure 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": "Find the names of service locations where services categorized as 'Licensing' have had appointments scheduled."}, {"role": "assistant", "content": "SELECT DISTINCT T1.location_name FROM service_locations AS T1 JOIN appointments AS T2 ON T1.location_id = T2.location_id JOIN services AS T3 ON T2.service_id = T3.service_id WHERE T3.category = 'Licensing';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.services (\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.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.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)\n"}
{"conversations": [{"role": "user", "content": "List the names of employees and the agency they work for who have scheduled at least one appointment. Show the employee's first name, last name, and agency_id."}, {"role": "assistant", "content": "SELECT DISTINCT e.first_name, e.last_name, e.agency_id\nFROM government_services.employees e\nJOIN government_services.appointments a ON e.employee_id = a.employee_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.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.applications ( application_id text, citizen_id text, service_id text, submitted_at timestamp, status text, last_updated_at timestamp, assigned_employee_id text, decision_date date, notes text, reference_number text )\nCREATE TABLE government_services.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.appointments ( appointment_id text, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\nCREATE TABLE government_services.notifications ( notification_id text, 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": "For each user, show their username and how many unique conversations they have sent at least one message in where the conversation is a group chat."}, {"role": "assistant", "content": "SELECT u.username, COUNT(DISTINCT m.conversation_id) AS group_chats_messaged_in\nFROM social_media.users u\nJOIN social_media.messages m ON u.user_id = m.sender_user_id\nJOIN social_media.conversations c ON m.conversation_id = c.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY u.username;"}, {"role": "user", "content": "Instead, show only users who have sent messages in more than one group chat, and include their email addresses."}, {"role": "assistant", "content": "SELECT u.username, u.email, COUNT(DISTINCT m.conversation_id) AS group_chats_messaged_in\nFROM social_media.users u\nJOIN social_media.messages m ON u.user_id = m.sender_user_id\nJOIN social_media.conversations c ON m.conversation_id = c.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY u.username, u.email\nHAVING COUNT(DISTINCT m.conversation_id) > 1;"}, {"role": "user", "content": "Also add the most recent message time sent by each user in these group chats."}, {"role": "assistant", "content": "SELECT u.username, u.email, COUNT(DISTINCT m.conversation_id) AS group_chats_messaged_in, MAX(m.sent_at) AS last_message_time\nFROM social_media.users u\nJOIN social_media.messages m ON u.user_id = m.sender_user_id\nJOIN social_media.conversations c ON m.conversation_id = c.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY u.username, u.email\nHAVING COUNT(DISTINCT m.conversation_id) > 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id.text, user_id.text, content.text, media_url.text, media_type.text, created_at.timestamp, updated_at.timestamp, visibility.text, location_lat.numeric, location_lon.numeric )\nCREATE TABLE social_media.comments (\n    comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n    post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n    user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n    parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n    content text NOT NULL, -- textual content of the comment\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n    PRIMARY KEY (comment_id)\n)\nCREATE TABLE social_media.likes ( like_id text, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.follows ( follow_id character varying(64) NOT NULL, follower_user_id character varying(64) NOT NULL, following_user_id character varying(64) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (follow_id), CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) )\nCREATE TABLE social_media.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id character varying(64) NOT NULL, post_id character varying(64) NOT NULL, hashtag_id character varying(64) NOT NULL, PRIMARY KEY (post_hashtag_id), CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) )\nCREATE TABLE social_media.messages (\n    message_id character varying(64) NOT NULL, -- unique identifier for the message\n    conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n    sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n    content text, -- textual content of the message\n    media_url text, -- URL to attached media (image/video)\n    media_type character varying(20), -- type of media ('image', 'video', null)\n    sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n    read_at timestamp, -- timestamp when message was read by recipient(s)\n    PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversations ( conversation_id text PRIMARY KEY, created_at timestamp, last_message_at timestamp, is_group_chat bool, group_name text )\nCREATE TABLE social_media.conversation_participants (\n    participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n    conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n    user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n    joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n    last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n    PRIMARY KEY (participant_id),\n    CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications ( notification_id.text, recipient_user_id.text, sender_user_id.text, notification_type.text, target_entity_id.text, target_entity_type.text, created_at.timestamp, read_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Calculate the total and average cost per service_type in maintenance_logs."}, {"role": "assistant", "content": "SELECT\n  service_type,\n  SUM(cost) AS total_cost,\n  AVG(cost) AS avg_cost\nFROM transportation.maintenance_logs\nGROUP BY service_type;"}, {"role": "user", "content": "Now filter to only service types where total_cost > 5000."}, {"role": "assistant", "content": "SELECT\n  service_type,\n  SUM(cost) AS total_cost,\n  AVG(cost) AS avg_cost\nFROM transportation.maintenance_logs\nGROUP BY service_type\nHAVING SUM(cost) > 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 transportation.maintenance_logs ( log_id text, vehicle_id text, service_date date, odometer_reading integer, service_type text, description text, cost numeric, mechanic_name text, next_service_due_date date )\n"}
{"conversations": [{"role": "user", "content": "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": "I need to get the most recent message each verified user has sent in any group chat, showing username, group_name, message_id, and sent_at."}, {"role": "assistant", "content": "WITH user_recent AS (\n  SELECT m.sender_user_id, m.message_id, m.conversation_id, m.sent_at,\n         ROW_NUMBER() OVER (PARTITION BY m.sender_user_id ORDER BY m.sent_at DESC) AS rn\n  FROM social_media.messages m\n  JOIN social_media.conversations c ON m.conversation_id = c.conversation_id\n  WHERE c.is_group_chat = true\n)\nSELECT u.username, c.group_name, ur.message_id, ur.sent_at\nFROM user_recent ur\nJOIN social_media.users u ON ur.sender_user_id = u.user_id\nJOIN social_media.conversations c ON ur.conversation_id = c.conversation_id\nWHERE ur.rn = 1\n  AND u.is_verified = true;"}, {"role": "user", "content": "Actually, I only want messages sent in the past 30 days."}, {"role": "assistant", "content": "WITH user_recent AS (\n  SELECT m.sender_user_id, m.message_id, m.conversation_id, m.sent_at,\n         ROW_NUMBER() OVER (PARTITION BY m.sender_user_id ORDER BY m.sent_at DESC) AS rn\n  FROM social_media.messages m\n  JOIN social_media.conversations c ON m.conversation_id = c.conversation_id\n  WHERE c.is_group_chat = true\n    AND m.sent_at >= NOW() - INTERVAL '30 days'\n)\nSELECT u.username, c.group_name, ur.message_id, ur.sent_at\nFROM user_recent ur\nJOIN social_media.users u ON ur.sender_user_id = u.user_id\nJOIN social_media.conversations c ON ur.conversation_id = c.conversation_id\nWHERE ur.rn = 1\n  AND u.is_verified = true;"}, {"role": "user", "content": "Also, exclude any users who have disabled push notifications."}, {"role": "assistant", "content": "WITH user_recent AS (\n  SELECT m.sender_user_id, m.message_id, m.conversation_id, m.sent_at,\n         ROW_NUMBER() OVER (PARTITION BY m.sender_user_id ORDER BY m.sent_at DESC) AS rn\n  FROM social_media.messages m\n  JOIN social_media.conversations c ON m.conversation_id = c.conversation_id\n  WHERE c.is_group_chat = true\n    AND m.sent_at >= NOW() - INTERVAL '30 days'\n)\nSELECT u.username, c.group_name, ur.message_id, ur.sent_at\nFROM user_recent ur\nJOIN social_media.users u ON ur.sender_user_id = u.user_id\nJOIN social_media.conversations c ON ur.conversation_id = c.conversation_id\nJOIN social_media.user_settings s ON s.user_id = u.user_id\nWHERE ur.rn = 1\n  AND u.is_verified = true\n  AND s.push_notifications_enabled = true;"}, {"role": "user", "content": "And order the results by sent_at descending."}, {"role": "assistant", "content": "WITH user_recent AS (\n  SELECT m.sender_user_id, m.message_id, m.conversation_id, m.sent_at,\n         ROW_NUMBER() OVER (PARTITION BY m.sender_user_id ORDER BY m.sent_at DESC) AS rn\n  FROM social_media.messages m\n  JOIN social_media.conversations c ON m.conversation_id = c.conversation_id\n  WHERE c.is_group_chat = true\n    AND m.sent_at >= NOW() - INTERVAL '30 days'\n)\nSELECT u.username, c.group_name, ur.message_id, ur.sent_at\nFROM user_recent ur\nJOIN social_media.users u ON ur.sender_user_id = u.user_id\nJOIN social_media.conversations c ON ur.conversation_id = c.conversation_id\nJOIN social_media.user_settings s ON s.user_id = u.user_id\nWHERE ur.rn = 1\n  AND u.is_verified = true\n  AND s.push_notifications_enabled = true\nORDER BY ur.sent_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.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.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id character varying(64) NOT NULL, post_id character varying(64) NOT NULL, hashtag_id character varying(64) NOT NULL, PRIMARY KEY (post_hashtag_id), CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) )\nCREATE TABLE social_media.messages ( message_id character varying(64) NOT NULL, conversation_id character varying(64) NOT NULL, sender_user_id character varying(64) NOT NULL, content text, media_url text, media_type character varying(20), sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, read_at timestamp, PRIMARY KEY (message_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.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, user_id text, theme text, email_notifications_enabled boolean, push_notifications_enabled boolean, private_profile boolean, updated_at timestamp )\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": "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": "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": "Retrieve the username and email for every user, along with the wallet ID and associated address ID for any wallets they own."}, {"role": "assistant", "content": "SELECT\n    u.username,\n    u.email,\n    w.wallet_id,\n    w.address_id\nFROM\n    blockchain.users AS u\nLEFT JOIN\n    blockchain.wallets AS w ON u.user_id = w.user_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.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 character varying(128) NOT NULL, public_key text NOT NULL, balance numeric(38,14) NOT NULL, PRIMARY KEY (address_id) )\nCREATE TABLE blockchain.wallets ( wallet_id.text, user_id.text, address_id.text, private_key.text )\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) )\nCREATE TABLE blockchain.smart_contracts ( contract_id character varying(64) NOT NULL, creator_address character varying(128) NOT NULL, code text NOT NULL, timestamp timestamp NOT NULL, PRIMARY KEY (contract_id) )\n"}
{"conversations": [{"role": "user", "content": "Show me the conversation ID and creation time for all conversations that are not group chats and have a recorded last message time."}, {"role": "assistant", "content": "SELECT conversation_id, created_at FROM social_media.conversations WHERE is_group_chat = FALSE AND last_message_at 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 social_media.comments ( comment_id.text, post_id.text, user_id.text, parent_comment_id.text, content.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE social_media.follows ( follow_id.text, follower_user_id.text, following_user_id.text, created_at.timestamp )\nCREATE TABLE social_media.conversations ( conversation_id.text, created_at.timestamp, last_message_at.timestamp, is_group_chat.boolean, group_name.text )\nCREATE TABLE social_media.notifications ( notification_id.text, recipient_user_id.text, sender_user_id.text, notification_type.text, target_entity_id.text, target_entity_type.text, created_at.timestamp, read_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "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": "Can you help me retrieve the list of components made of a specific material along with their supplier details?"}, {"role": "assistant", "content": "SMEMBERS material_components:mat:TI64\nHGETALL component:<component_id>\nHGET component:<component_id> supplier_id"}, {"role": "user", "content": "Can you also include the part number for each component in the result?"}, {"role": "assistant", "content": "SMEMBERS material_components:mat:TI64\nHGETALL component:<component_id>\nHGET component:<component_id> supplier_id\nHGET component:<component_id> part_number"}, {"role": "user", "content": "If I want to filter out components from a specific supplier, how can I modify the query?"}, {"role": "assistant", "content": "SMEMBERS material_components:mat:TI64\nHGETALL component:<component_id>\nHGET component:<component_id> supplier_id\nHGET component:<component_id> part_number\nIF HGET component:<component_id> supplier_id != 'sup:ACME_AERO' THEN INCLUDE"}, {"role": "user", "content": "Can you also sort the results based on the part number?"}, {"role": "assistant", "content": "SMEMBERS material_components:mat:TI64\nHGETALL component:<component_id>\nHGET component:<component_id> supplier_id\nHGET component:<component_id> part_number\nIF HGET component:<component_id> supplier_id != 'sup:ACME_AERO' THEN INCLUDE\nSORT BY part_number ASC"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nUse Hashes. Key pattern: 'component:<component_id>'. Example: HSET component:LGSTRUT01 part_number \"PN-5521-A\" component_name \"Landing Gear Strut\" material_id \"mat:TI64\" supplier_id \"sup:ACME_AERO\" ... Consider Sets for reverse lookups (e.g., 'material_components:<material_id>' -> Set<component_id>).\n"}
{"conversations": [{"role": "user", "content": "List all patient insurance entries where the subscriber name is different from the patient's last name. Include patient ID, subscriber name, and patient last name."}, {"role": "assistant", "content": "SELECT T1.patient_id, T1.subscriber_name, T2.last_name FROM healthcare.patient_insurance AS T1 JOIN healthcare.patients AS T2 ON T1.patient_id = T2.patient_id WHERE T1.subscriber_name <> T2.last_name;"}, {"role": "user", "content": "Also, only show entries where the policy is marked as primary."}, {"role": "assistant", "content": "SELECT T1.patient_id, T1.subscriber_name, T2.last_name FROM healthcare.patient_insurance AS T1 JOIN healthcare.patients AS T2 ON T1.patient_id = T2.patient_id WHERE T1.subscriber_name <> T2.last_name AND T1.is_primary = 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 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 ( doctor_id text PRIMARY KEY, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table\n    appointment_time timestamp with time zone NOT NULL, -- date and time of the appointment\n    duration_minutes integer NOT NULL, -- expected duration in minutes\n    reason text, -- reason for the visit\n    status character varying(32) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-show\n    location_id character varying(64), -- FK to a potential locations/clinics table\n    notes text, -- notes related to scheduling\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (appointment_id)\n)\nCREATE TABLE healthcare.medical_records ( record_id.text, patient_id.text, appointment_id.text, doctor_id.text, record_date.timestamp, chief_complaint.text, present_illness_history.text, past_medical_history.text, physical_examination_notes.text, assessment.text, treatment_plan.text, vitals.json, created_at.timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, diagnosis_code character varying(20) NOT NULL, code_type character varying(10) NOT NULL DEFAULT 'ICD-10', description text, diagnosis_date date NOT NULL, status character varying(32) NOT NULL, is_chronic boolean DEFAULT false, PRIMARY KEY (diagnosis_id) )\nCREATE TABLE healthcare.medications ( medication_id text PRIMARY KEY, 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 (\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 all beneficiaries with their policy numbers, including beneficiary first and last name, relationship, and the policy end date."}, {"role": "assistant", "content": "SELECT pb.beneficiary_id, pb.first_name, pb.last_name, pb.relationship, p.policy_number, p.end_date\nFROM insurance.policy_beneficiaries pb\nJOIN insurance.policies p ON pb.policy_id = p.policy_id;"}, {"role": "user", "content": "Actually, I only need beneficiaries whose percentage share is greater than 20% and sorted by percentage share in descending order."}, {"role": "assistant", "content": "SELECT pb.beneficiary_id, pb.first_name, pb.last_name, pb.relationship, p.policy_number, p.end_date, pb.percentage_share\nFROM insurance.policy_beneficiaries pb\nJOIN insurance.policies p ON pb.policy_id = p.policy_id\nWHERE pb.percentage_share > 20\nORDER BY pb.percentage_share DESC;"}, {"role": "user", "content": "Also include the policy status and only show records where the policy is still active."}, {"role": "assistant", "content": "SELECT pb.beneficiary_id, pb.first_name, pb.last_name, pb.relationship, p.policy_number, p.end_date, p.status AS policy_status, pb.percentage_share\nFROM insurance.policy_beneficiaries pb\nJOIN insurance.policies p ON pb.policy_id = p.policy_id\nWHERE pb.percentage_share > 20\n  AND p.status = 'Active'\nORDER BY pb.percentage_share DESC;"}, {"role": "user", "content": "Limit the results to the top 5 beneficiaries."}, {"role": "assistant", "content": "SELECT pb.beneficiary_id, pb.first_name, pb.last_name, pb.relationship, p.policy_number, p.end_date, p.status AS policy_status, pb.percentage_share\nFROM insurance.policy_beneficiaries pb\nJOIN insurance.policies p ON pb.policy_id = p.policy_id\nWHERE pb.percentage_share > 20\n  AND p.status = 'Active'\nORDER BY pb.percentage_share 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 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 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, 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, 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": "Retrieve each agent's ID, full name, and the count of 'Pending' policies they have sold with a premium_amount greater than 2000. Order the results by the policy count descending."}, {"role": "assistant", "content": "SELECT a.agent_id,\n       a.first_name || ' ' || a.last_name AS agent_name,\n       COUNT(p.policy_id) AS pending_policy_count\nFROM insurance.agents a\nJOIN insurance.policies p ON a.agent_id = p.agent_id\nWHERE p.status = 'Pending'\n  AND p.premium_amount > 2000\nGROUP BY a.agent_id, agent_name\nORDER BY pending_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 insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\nCREATE TABLE insurance.claims (\n    claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n    policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n    incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n    reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n    description text NOT NULL, -- detailed description of the incident and claim\n    estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n    status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n    settlement_amount numeric(15, 2), -- final amount paid out\n    settlement_date date,\n    claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n    police_report_number character varying(100),\n    PRIMARY KEY (claim_id)\n)\nCREATE TABLE insurance.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": "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 pairs of smoking and non-smoking rooms on the same floor for each property, showing the property_id, floor, smoking room_number, and non_smoking room_number."}, {"role": "assistant", "content": "SELECT r1.property_id,\n       r1.floor,\n       r1.room_number AS smoking_room,\n       r2.room_number AS non_smoking_room\nFROM hospitality_technology.rooms r1\nJOIN hospitality_technology.rooms r2\n  ON r1.property_id = r2.property_id\n AND r1.floor = r2.floor\n AND r1.is_smoking = TRUE\n AND r2.is_smoking = FALSE;"}], "system": "You are an SQL statement expert. Given the table structure 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": "Show me the top 5 buyers by total trade volume (quantity * price) in the last 30 days, along with their trade count."}, {"role": "assistant", "content": "SELECT buyer_id, COUNT(trade_id) AS trade_count, SUM(quantity * price) AS total_volume FROM trading_platform.trades WHERE traded_at >= NOW() - INTERVAL '30 days' GROUP BY buyer_id ORDER BY total_volume DESC LIMIT 5"}, {"role": "user", "content": "Now modify the query to also include the average trade price for each buyer."}, {"role": "assistant", "content": "SELECT buyer_id, COUNT(trade_id) AS trade_count, SUM(quantity * price) AS total_volume, AVG(price) AS avg_price FROM trading_platform.trades WHERE traded_at >= NOW() - INTERVAL '30 days' GROUP BY buyer_id ORDER BY total_volume DESC LIMIT 5"}, {"role": "user", "content": "Actually, I want to see the results for sellers instead of buyers, and include the distinct asset count they traded."}, {"role": "assistant", "content": "SELECT seller_id, COUNT(trade_id) AS trade_count, COUNT(DISTINCT asset_id) AS distinct_assets, SUM(quantity * price) AS total_volume, AVG(price) AS avg_price FROM trading_platform.trades WHERE traded_at >= NOW() - INTERVAL '30 days' GROUP BY seller_id ORDER BY total_volume DESC LIMIT 5"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.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) )\n"}
{"conversations": [{"role": "user", "content": "List the first name, last name, email, and phone number of all clients who have a case of type 'Bankruptcy', along with the name of the case."}, {"role": "assistant", "content": "SELECT T1.first_name ,  T1.last_name ,  T1.email ,  T1.phone ,  T2.case_name FROM legal_services.clients AS T1 JOIN legal_services.cases AS T2 ON T1.client_id  =  T2.client_id WHERE T2.case_type  =  'Bankruptcy'"}], "system": "You are an SQL statement expert. Given the table structure 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 (\n    firm_id character varying(64) NOT NULL,  -- unique identifier for the law firm\n    firm_name character varying(200) NOT NULL, -- official name of the law firm\n    address text NOT NULL, -- primary address of the firm\n    phone character varying(32), -- firm's main phone number\n    website character varying(255), -- firm's website URL\n    founded_date date, -- date the firm was established\n    managing_partner_id character varying(64), -- FK to lawyers table (optional)\n    PRIMARY KEY (firm_id)\n)\nCREATE TABLE legal_services.cases ( 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.time_entries ( entry_id text PRIMARY KEY, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable bool, is_billed bool, invoice_id 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": "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": "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": "List all patients who have a current prescription that was prescribed by a doctor with a specialty of 'Endocrinology'. Show patient full name, prescription ID, medication name, and prescription date."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name || ' ' || p.last_name AS full_name, pr.prescription_id, m.medication_name, pr.prescription_date\nFROM healthcare.prescriptions pr\nJOIN healthcare.medications m ON pr.medication_id = m.medication_id\nJOIN healthcare.patients p ON pr.patient_id = p.patient_id\nJOIN healthcare.doctors d ON pr.doctor_id = d.doctor_id\nWHERE d.specialty = 'Endocrinology' AND pr.end_date IS NULL OR pr.end_date > CURRENT_DATE;"}, {"role": "user", "content": "Include prescriptions that ended within the past 7 days as well."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name || ' ' || p.last_name AS full_name, pr.prescription_id, m.medication_name, pr.prescription_date\nFROM healthcare.prescriptions pr\nJOIN healthcare.medications m ON pr.medication_id = m.medication_id\nJOIN healthcare.patients p ON pr.patient_id = p.patient_id\nJOIN healthcare.doctors d ON pr.doctor_id = d.doctor_id\nWHERE d.specialty = 'Endocrinology' AND (pr.end_date IS NULL OR pr.end_date > CURRENT_DATE OR pr.end_date >= CURRENT_DATE - INTERVAL '7 days');"}, {"role": "user", "content": "I got an error: relation \"healthcare.patients\" does not exist. Can you fix it using existing tables only?"}, {"role": "assistant", "content": "SELECT pr.patient_id, pr.prescription_id, m.medication_name, pr.prescription_date\nFROM healthcare.prescriptions pr\nJOIN healthcare.medications m ON pr.medication_id = m.medication_id\nJOIN healthcare.doctors d ON pr.doctor_id = d.doctor_id\nWHERE d.specialty = 'Endocrinology' AND (pr.end_date IS NULL OR pr.end_date > CURRENT_DATE OR pr.end_date >= 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 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 trades with their corresponding ticker_symbol and security_name for trades executed in the last 7 days."}, {"role": "assistant", "content": "SELECT tr.trade_id, tr.account_id, tr.trade_type, tr.quantity, tr.price_per_unit, tr.total_amount,\n       tr.commission, tr.trade_timestamp,\n       s.ticker_symbol, s.security_name\nFROM financial_services.trades tr\nJOIN financial_services.securities s ON tr.security_id = s.security_id\nWHERE tr.trade_timestamp >= now() - INTERVAL '7 days';"}, {"role": "user", "content": "Only include trades where commission is greater than 50 and status is 'Completed'."}, {"role": "assistant", "content": "SELECT tr.trade_id, tr.account_id, tr.trade_type, tr.quantity, tr.price_per_unit, tr.total_amount,\n       tr.commission, tr.trade_timestamp,\n       s.ticker_symbol, s.security_name\nFROM financial_services.trades tr\nJOIN financial_services.securities s ON tr.security_id = s.security_id\nWHERE tr.trade_timestamp >= now() - INTERVAL '7 days'\n  AND tr.commission > 50\n  AND tr.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 financial_services.customers ( customer_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, ssn_hash character varying(128), address text NOT NULL, city character varying(100) NOT NULL, state character varying(50) NOT NULL, zip_code character varying(20) NOT NULL, country character varying(50) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, status character varying(32) NOT NULL, risk_profile character varying(50), PRIMARY KEY (customer_id) )\nCREATE TABLE financial_services.accounts (\n    account_id character varying(64) NOT NULL, -- unique identifier for the account\n    customer_id character varying(64) NOT NULL, -- foreign key linking to the customer\n    account_number character varying(128) NOT NULL UNIQUE, -- unique account number visible to customer\n    account_type character varying(50) NOT NULL, -- e.g., Checking, Savings, Investment, Loan, Credit Card\n    balance numeric(19, 4) NOT NULL DEFAULT 0.00, -- current account balance\n    currency character varying(3) NOT NULL, -- currency code (e.g., USD, EUR)\n    opened_date date NOT NULL, -- date the account was opened\n    status character varying(32) NOT NULL, -- e.g., Open, Closed, Frozen\n    interest_rate numeric(5, 4), -- annual interest rate, if applicable\n    last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last account update\n    PRIMARY KEY (account_id),\n    FOREIGN KEY (customer_id) REFERENCES financial_services.customers(customer_id)\n)\nCREATE TABLE financial_services.transactions (\n    transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n    account_id character varying(64) NOT NULL, -- account involved in the transaction\n    related_account_id character varying(64), -- counterpart account for transfers\n    transaction_type character varying(50) NOT NULL, -- e.g., Deposit, Withdrawal, Transfer, Payment, Fee, Interest\n    amount numeric(19, 4) NOT NULL, -- transaction amount\n    currency character varying(3) NOT NULL, -- transaction currency\n    transaction_date timestamp NOT NULL, -- exact time of the transaction\n    effective_date date NOT NULL, -- date the transaction affects the balance\n    description text, -- description or memo of the transaction\n    status character varying(32) NOT NULL, -- e.g., Pending, Completed, Failed, Reversed\n    reference_number character varying(128), -- external reference if applicable (e.g., check number)\n    PRIMARY KEY (transaction_id),\n    FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id),\n    FOREIGN KEY (related_account_id) REFERENCES financial_services.accounts(account_id)\n)\nCREATE TABLE financial_services.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)\nCREATE TABLE financial_services.trades ( trade_id text PRIMARY KEY, account_id text, security_id text, order_id text, trade_type text, quantity numeric, price_per_unit numeric, total_amount numeric, commission numeric, trade_timestamp timestamp, settlement_date date, status text, execution_venue text )\nCREATE TABLE financial_services.market_data ( data_point_id.bigint, security_id.text, data_timestamp.timestamp, open_price.numeric, high_price.numeric, low_price.numeric, close_price.numeric, adjusted_close_price.numeric, volume.bigint, source.text )\nCREATE TABLE financial_services.employees ( 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": "What is the fuel efficiency of the train car with car_id 'TC456'?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to information about the fuel efficiency of specific train cars. The data available in the train_cars table only includes details such as car_id, train_id, car_number, car_type, class, capacity, and features. If you have another question or need assistance with something else, I'm happy to help."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.train_cars ( car_id.text, train_id.text, car_number.text, car_type.text, class.text, capacity.integer, features.text )\n"}
{"conversations": [{"role": "user", "content": "Show me all trips that were delayed by more than 1 hour, including their vehicle and driver IDs, along with the origin and destination location IDs."}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, origin_location_id, destination_location_id FROM transportation.trips WHERE EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/3600 > 1 AND status = 'Completed';"}, {"role": "user", "content": "Now include the passenger count for these trips, but only show trips that had more than 5 passengers."}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, origin_location_id, destination_location_id, passenger_count FROM transportation.trips WHERE EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/3600 > 1 AND status = 'Completed' AND passenger_count > 5;"}, {"role": "user", "content": "Can you order these results by the delay time in descending order, showing the longest delays first?"}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, origin_location_id, destination_location_id, passenger_count, (actual_departure - scheduled_departure) AS delay_time FROM transportation.trips WHERE EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/3600 > 1 AND status = 'Completed' AND passenger_count > 5 ORDER BY delay_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.trips (\n    trip_id character varying(64) NOT NULL,  -- unique identifier for a specific trip instance\n    route_id character varying(64), -- identifier of the route being followed (can be null for ad-hoc trips)\n    vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle used\n    driver_id character varying(64) NOT NULL, -- identifier of the driver operating\n    scheduled_departure timestamp with time zone NOT NULL, -- planned departure time\n    actual_departure timestamp with time zone, -- actual departure time\n    scheduled_arrival timestamp with time zone NOT NULL, -- planned arrival time\n    actual_arrival timestamp with time zone, -- actual arrival time\n    origin_location_id character varying(64) NOT NULL, -- actual starting location (could differ from route origin)\n    destination_location_id character varying(64) NOT NULL, -- actual ending location (could differ from route destination)\n    status character varying(32) NOT NULL, -- e.g., Scheduled, In Progress, Completed, Delayed, Cancelled\n    passenger_count integer, -- number of passengers (if applicable)\n    cargo_manifest_id character varying(64), -- link to cargo details (if applicable)\n    PRIMARY KEY (trip_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all accounts opened in the last 18 months, including the account number, account type, and the full name of the customer."}, {"role": "assistant", "content": "SELECT a.account_number, a.account_type, c.first_name, c.last_name, a.opened_date FROM financial_services.accounts a JOIN financial_services.customers c ON a.customer_id = c.customer_id WHERE a.opened_date >= CURRENT_DATE - INTERVAL '18 months' ORDER BY a.opened_date DESC;"}, {"role": "user", "content": "Additionally, filter this list to only include accounts with a status of 'Open'."}, {"role": "assistant", "content": "SELECT a.account_number, a.account_type, c.first_name, c.last_name, a.opened_date FROM financial_services.accounts a JOIN financial_services.customers c ON a.customer_id = c.customer_id WHERE a.opened_date >= CURRENT_DATE - INTERVAL '18 months' AND a.status = 'Open' ORDER BY a.opened_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.accounts (\n    account_id character varying(64) NOT NULL, -- unique identifier for the account\n    customer_id character varying(64) NOT NULL, -- foreign key linking to the customer\n    account_number character varying(128) NOT NULL UNIQUE, -- unique account number visible to customer\n    account_type character varying(50) NOT NULL, -- e.g., Checking, Savings, Investment, Loan, Credit Card\n    balance numeric(19, 4) NOT NULL DEFAULT 0.00, -- current account balance\n    currency character varying(3) NOT NULL, -- currency code (e.g., USD, EUR)\n    opened_date date NOT NULL, -- date the account was opened\n    status character varying(32) NOT NULL, -- e.g., Open, Closed, Frozen\n    interest_rate numeric(5, 4), -- annual interest rate, if applicable\n    last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last account update\n    PRIMARY KEY (account_id),\n    FOREIGN KEY (customer_id) REFERENCES financial_services.customers(customer_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show me all tokens with their contract addresses and total supply, but only include tokens where the decimals are greater than 6, sorted by total supply in descending order."}, {"role": "assistant", "content": "SELECT token_name, contract_address, total_supply FROM web3.tokens WHERE decimals > 6 ORDER BY total_supply DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.tokens ( token_id.text, contract_address.text, token_name.text, token_symbol.text, decimals.integer, total_supply.numeric )\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": "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": "Show me all clients whose company name contains 'Tech' and display their email and date of registration."}, {"role": "assistant", "content": "SELECT first_name, last_name, company_name, email, date_registered FROM legal_services.clients WHERE company_name ILIKE '%Tech%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, company_name character varying(200), email character varying(128) UNIQUE NOT NULL, phone character varying(32), address text, date_registered timestamp NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (client_id) )\n"}
{"conversations": [{"role": "user", "content": "Could you show me each employee's full name along with their manager's full name?"}, {"role": "assistant", "content": "SELECT e.employee_id,\n       e.first_name || ' ' || e.last_name AS employee_name,\n       m.employee_id AS manager_id,\n       m.first_name || ' ' || m.last_name AS manager_name\nFROM government_services.employees e\nLEFT JOIN government_services.employees m ON e.manager_employee_id = m.employee_id;"}, {"role": "user", "content": "Actually, only include employees who were hired after January 1, 2020."}, {"role": "assistant", "content": "SELECT e.employee_id,\n       e.first_name || ' ' || e.last_name AS employee_name,\n       m.employee_id AS manager_id,\n       m.first_name || ' ' || m.last_name AS manager_name\nFROM government_services.employees e\nLEFT JOIN government_services.employees m ON e.manager_employee_id = m.employee_id\nWHERE e.hire_date > '2020-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.employees (\n    employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(150) NOT NULL,\n    department character varying(100),\n    work_email character varying(128) NOT NULL UNIQUE,\n    work_phone character varying(32),\n    hire_date date NOT NULL,\n    termination_date date, -- null if currently employed\n    access_level character varying(50), -- Role or permission level\n    manager_employee_id character varying(64), -- FK to self for reporting structure\n    PRIMARY KEY (employee_id)\n)\n"}
{"conversations": [{"role": "user", "content": "For each vehicle, show the vehicle_id, license_plate, date of its most recent trip (actual_arrival), and the odometer_reading at its latest maintenance service."}, {"role": "assistant", "content": "SELECT\n    v.vehicle_id,\n    v.license_plate,\n    (\n        SELECT MAX(t.actual_arrival)\n        FROM transportation.trips t\n        WHERE t.vehicle_id = v.vehicle_id\n    ) AS last_trip_arrival,\n    ml.odometer_reading\nFROM transportation.vehicles v\nLEFT JOIN LATERAL (\n    SELECT odometer_reading\n    FROM transportation.maintenance_logs ml\n    WHERE ml.vehicle_id = v.vehicle_id\n    ORDER BY ml.service_date DESC\n    LIMIT 1\n) ml 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 transportation.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id text, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.trips ( trip_id text PRIMARY KEY, route_id text, vehicle_id text, driver_id text, scheduled_departure timestamp, actual_departure timestamp, scheduled_arrival timestamp, actual_arrival timestamp, origin_location_id text, destination_location_id text, status text, passenger_count int, cargo_manifest_id text )\nCREATE TABLE transportation.locations ( location_id text PRIMARY KEY, name text, type text, address_line1 text, city text, state_province text, postal_code text, country text, latitude numeric, longitude numeric, timezone text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.passengers (\n    passenger_id character varying(64) NOT NULL,  -- unique identifier for the passenger\n    first_name character varying(128) NOT NULL, -- passenger's first name\n    last_name character varying(128) NOT NULL, -- passenger's last name\n    email character varying(128) UNIQUE, -- email address\n    phone_number character varying(32) UNIQUE, -- phone number\n    date_of_birth date, -- passenger's date of birth\n    loyalty_program_id character varying(64), -- identifier for loyalty program membership\n    created_at timestamp with time zone NOT NULL, -- time when the passenger record was created\n    PRIMARY KEY (passenger_id)\n)\nCREATE TABLE transportation.bookings ( booking_id text, passenger_id text, trip_id text, seat_number text, booking_time timestamp, status text, fare numeric, payment_transaction_id text, special_requests text )\n"}
{"conversations": [{"role": "user", "content": "Find all medical records where the vitals JSON field contains a blood pressure reading higher than 140/90, and show the patient_id, record_date, and vitals."}, {"role": "assistant", "content": "SELECT patient_id, record_date, vitals FROM healthcare.medical_records WHERE (vitals->>'systolic')::int > 140 AND (vitals->>'diastolic')::int > 90;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.medical_records ( record_id.text, patient_id.text, appointment_id.text, doctor_id.text, record_date.timestamp, chief_complaint.text, present_illness_history.text, past_medical_history.text, physical_examination_notes.text, assessment.text, treatment_plan.text, vitals.json, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Which users have commented on posts created by the users they follow? Please show the commenter user_ids and the followed user_ids."}, {"role": "assistant", "content": "SELECT DISTINCT c.user_id AS commenter_user_id, f.following_user_id AS followed_user_id FROM social_media.comments c JOIN social_media.follows f ON c.user_id = f.follower_user_id AND c.post_id IN (SELECT post_id FROM social_media.comments WHERE user_id = f.following_user_id);"}, {"role": "user", "content": "Can you also include the post_id in the results?"}, {"role": "assistant", "content": "SELECT DISTINCT c.user_id AS commenter_user_id, f.following_user_id AS followed_user_id, c.post_id FROM social_media.comments c JOIN social_media.follows f ON c.user_id = f.follower_user_id AND c.post_id IN (SELECT post_id FROM social_media.comments WHERE user_id = f.following_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 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.follows ( follow_id text PRIMARY KEY, follower_user_id text, following_user_id text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Find all chronic diagnoses made by Cardiology doctors in the last year, including patient ID, diagnosis description, and doctor's full name."}, {"role": "assistant", "content": "SELECT di.patient_id, di.description, d.first_name || ' ' || d.last_name AS doctor_name, di.diagnosis_date FROM healthcare.diagnoses di JOIN healthcare.doctors d ON di.doctor_id = d.doctor_id WHERE di.is_chronic = true AND d.specialty = 'Cardiology' AND di.diagnosis_date >= CURRENT_DATE - INTERVAL '1 year' ORDER BY di.diagnosis_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.doctors ( doctor_id text PRIMARY KEY, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id text, 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 character varying(64) NOT NULL, medication_name character varying(255) NOT NULL, generic_name character varying(255), manufacturer character varying(100), ndc_code character varying(20) UNIQUE, description text, PRIMARY KEY (medication_id) )\nCREATE TABLE healthcare.prescriptions ( prescription_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, medication_id character varying(64) NOT NULL, dosage character varying(100) NOT NULL, frequency character varying(100) NOT NULL, route character varying(50), start_date date NOT NULL, end_date date, quantity_dispensed numeric(10,2), refills_allowed integer NOT NULL DEFAULT 0, prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (prescription_id) )\n"}
{"conversations": [{"role": "user", "content": "For each server, show its name and the total number of achievements available for the game it hosts."}, {"role": "assistant", "content": "SELECT s.server_name, s.region, COUNT(a.achievement_id) AS achievement_count\nFROM gaming_technology.servers s\nLEFT JOIN gaming_technology.achievements a ON s.game_id = a.game_id\nGROUP BY s.server_name, s.region;"}, {"role": "user", "content": "Exclude servers hosting games with no achievements."}, {"role": "assistant", "content": "SELECT s.server_name, s.region, COUNT(a.achievement_id) AS achievement_count\nFROM gaming_technology.servers s\nLEFT JOIN gaming_technology.achievements a ON s.game_id = a.game_id\nGROUP BY s.server_name, s.region\nHAVING COUNT(a.achievement_id) > 0;"}, {"role": "user", "content": "Also include each server's current_players and max_players."}, {"role": "assistant", "content": "SELECT s.server_name, s.region, s.current_players, s.max_players, COUNT(a.achievement_id) AS achievement_count\nFROM gaming_technology.servers s\nLEFT JOIN gaming_technology.achievements a ON s.game_id = a.game_id\nGROUP BY s.server_name, s.region, s.current_players, s.max_players\nHAVING COUNT(a.achievement_id) > 0;"}, {"role": "user", "content": "Sort by usage ratio (current_players divided by max_players) in descending order."}, {"role": "assistant", "content": "SELECT s.server_name, s.region, s.current_players, s.max_players, COUNT(a.achievement_id) AS achievement_count\nFROM gaming_technology.servers s\nLEFT JOIN gaming_technology.achievements a ON s.game_id = a.game_id\nGROUP BY s.server_name, s.region, s.current_players, s.max_players\nHAVING COUNT(a.achievement_id) > 0\nORDER BY (s.current_players::numeric / s.max_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.developers ( developer_id uuid NOT NULL DEFAULT gen_random_uuid(), name character varying(150) NOT NULL UNIQUE, country character varying(100), founded_year integer, website character varying(255), created_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (developer_id) )\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, game_id uuid NOT NULL, server_id uuid, start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, end_time timestamp with time zone, duration_seconds integer, score integer, session_data jsonb, PRIMARY KEY (session_id) )\nCREATE TABLE gaming_technology.servers ( server_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, server_name character varying(150), region character varying(50) NOT NULL, ip_address character varying(45), port integer, current_players integer NOT NULL DEFAULT 0, max_players integer NOT NULL, status character varying(30) NOT NULL DEFAULT 'offline', last_heartbeat timestamp with time zone, PRIMARY KEY (server_id) )\nCREATE TABLE gaming_technology.achievements ( achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, name character varying(150) NOT NULL, description text NOT NULL, icon_url character varying(255), points integer DEFAULT 0, hidden boolean DEFAULT false, PRIMARY KEY (achievement_id) )\n"}
{"conversations": [{"role": "user", "content": "Which staff members ordered more than 5 service orders in total? List their staff_id, full name, and the total number of orders they've placed."}, {"role": "assistant", "content": "SELECT s.staff_id, s.first_name, s.last_name, COUNT(so.order_id) AS total_orders\nFROM hospitality_technology.staff s\nJOIN hospitality_technology.service_orders so ON s.staff_id = so.staff_id_ordered\nGROUP BY s.staff_id, s.first_name, s.last_name\nHAVING COUNT(so.order_id) > 5;"}, {"role": "user", "content": "Actually, I'd like to only include staff members who are currently active."}, {"role": "assistant", "content": "SELECT s.staff_id, s.first_name, s.last_name, COUNT(so.order_id) AS total_orders\nFROM hospitality_technology.staff s\nJOIN hospitality_technology.service_orders so ON s.staff_id = so.staff_id_ordered\nWHERE s.is_active = TRUE\nGROUP BY s.staff_id, s.first_name, s.last_name\nHAVING COUNT(so.order_id) > 5;"}, {"role": "user", "content": "Can you also include the property_id and show the results ordered by total_orders descending?"}, {"role": "assistant", "content": "SELECT s.staff_id, s.first_name, s.last_name, s.property_id, COUNT(so.order_id) AS total_orders\nFROM hospitality_technology.staff s\nJOIN hospitality_technology.service_orders so ON s.staff_id = so.staff_id_ordered\nWHERE s.is_active = TRUE\nGROUP BY s.staff_id, s.first_name, s.last_name, s.property_id\nHAVING COUNT(so.order_id) > 5\nORDER BY total_orders 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.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.reservations ( reservation_id text, property_id text, guest_id text, room_id text, room_type_id text, check_in_date date, check_out_date date, actual_check_in_ts timestamp, actual_check_out_ts timestamp, num_adults integer, num_children integer, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id text, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level integer, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.services (\n    service_id character varying(64) NOT NULL, -- unique identifier for a chargeable service\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    service_name character varying(150) NOT NULL, -- e.g., Room Service - Burger, Spa - Massage 60min, Laundry - Shirt\n    description text,\n    category character varying(100), -- e.g., Food & Beverage, Wellness, Business Center, Activities\n    price numeric(10, 2) NOT NULL, -- price per unit/instance\n    unit character varying(30), -- e.g., Per Item, Per Hour, Per Day\n    is_available boolean NOT NULL DEFAULT true, -- is the service currently offered?\n    department character varying(100), -- department responsible (e.g., F&B, Spa, Housekeeping)\n    PRIMARY KEY (service_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\n"}
{"conversations": [{"role": "user", "content": "For each player, show the timestamp of their first achievement unlock. Include player_id and the timestamp."}, {"role": "assistant", "content": "SELECT player_id, MIN(unlocked_at) as first_unlock_at FROM gaming_technology.player_achievements GROUP BY player_id ORDER BY first_unlock_at;"}, {"role": "user", "content": "For each player, show the timestamp of their second earliest achievement unlock, if they have at least two. Include player_id and the timestamp."}, {"role": "assistant", "content": "WITH RankedUnlocks AS ( SELECT player_id, unlocked_at, ROW_NUMBER() OVER(PARTITION BY player_id ORDER BY unlocked_at) as rn FROM gaming_technology.player_achievements ) SELECT player_id, unlocked_at as second_unlock_at FROM RankedUnlocks WHERE rn = 2 ORDER BY player_id, second_unlock_at;"}, {"role": "user", "content": "List the player_id for players who unlocked their second achievement within 10 minutes of their first."}, {"role": "assistant", "content": "WITH PlayerFirstUnlock AS ( SELECT player_id, MIN(unlocked_at) as first_unlock_at FROM gaming_technology.player_achievements GROUP BY player_id ), RankedUnlocks AS ( SELECT player_id, unlocked_at, ROW_NUMBER() OVER(PARTITION BY player_id ORDER BY unlocked_at) as rn FROM gaming_technology.player_achievements ) SELECT pfu.player_id FROM PlayerFirstUnlock pfu JOIN RankedUnlocks ru ON pfu.player_id = ru.player_id WHERE ru.rn = 2 AND ru.unlocked_at <= pfu.first_unlock_at + INTERVAL '10 minute' ORDER BY pfu.player_id;"}, {"role": "user", "content": "For the players identified in the previous query (those whose second unlock was within 10 minutes of the first), list the achievement_id of their first and second unlocks."}, {"role": "assistant", "content": "WITH PlayerFirstUnlock AS ( SELECT player_id, MIN(unlocked_at) as first_unlock_at FROM gaming_technology.player_achievements GROUP BY player_id ), RankedUnlocks AS ( SELECT player_id, achievement_id, unlocked_at, ROW_NUMBER() OVER(PARTITION BY player_id ORDER BY unlocked_at) as rn FROM gaming_technology.player_achievements ), PlayersWithFastSecondUnlock AS ( SELECT pfu.player_id FROM PlayerFirstUnlock pfu JOIN RankedUnlocks ru ON pfu.player_id = ru.player_id WHERE ru.rn = 2 AND ru.unlocked_at <= pfu.first_unlock_at + INTERVAL '10 minute' ) SELECT pfl.player_id, ru_first.achievement_id as first_achievement_id, ru_second.achievement_id as second_achievement_id FROM PlayersWithFastSecondUnlock pfl JOIN RankedUnlocks ru_first ON pfl.player_id = ru_first.player_id AND ru_first.rn = 1 JOIN RankedUnlocks ru_second ON pfl.player_id = ru_second.player_id AND ru_second.rn = 2 ORDER BY pfl.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.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": "For each agency, how many services are currently inactive? Return the agency_id and the count of inactive services."}, {"role": "assistant", "content": "SELECT\n  agency_id,\n  COUNT(*) AS inactive_service_count\nFROM government_services.services\nWHERE is_active = FALSE\nGROUP BY 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.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": "Give me the number of patient insurance policies for each plan where the policy is currently active. Return plan_id and policy_count."}, {"role": "assistant", "content": "SELECT\n  plan_id,\n  COUNT(*) AS policy_count\nFROM healthcare.patient_insurance\nWHERE (expiration_date IS NULL OR expiration_date >= CURRENT_DATE)\nGROUP BY plan_id;"}, {"role": "user", "content": "Now, only include plans where the count is greater than 5 and sort by policy_count descending."}, {"role": "assistant", "content": "SELECT\n  plan_id,\n  COUNT(*) AS policy_count\nFROM healthcare.patient_insurance\nWHERE (expiration_date IS NULL OR expiration_date >= CURRENT_DATE)\nGROUP BY plan_id\nHAVING COUNT(*) > 5\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.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 all patients who have both primary and non-primary insurance plans, along with their policy numbers and expiration dates."}, {"role": "assistant", "content": "SELECT p1.patient_id, p1.policy_number AS primary_policy, p1.expiration_date AS primary_expiry, p2.policy_number AS non_primary_policy, p2.expiration_date AS non_primary_expiry FROM healthcare.patient_insurance p1 JOIN healthcare.patient_insurance p2 ON p1.patient_id = p2.patient_id WHERE p1.is_primary = true AND p2.is_primary = false;"}], "system": "You are an SQL statement expert. Given the table structure 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": "Count the number of patients whose address includes the word 'Street' and are male."}, {"role": "assistant", "content": "SELECT COUNT(*) FROM healthcare.patients WHERE address LIKE '%Street%' AND gender = 'Male';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "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 all lawyers' full names, their bar number, and if they are partners, the full name of another partner from their firm."}, {"role": "assistant", "content": "SELECT l1.first_name || ' ' || l1.last_name AS lawyer_full_name, l1.bar_number,\n       CASE WHEN l1.is_partner = TRUE THEN (\n           SELECT l2.first_name || ' ' || l2.last_name\n           FROM legal_services.lawyers l2\n           WHERE l2.firm_id = l1.firm_id AND l2.is_partner = TRUE AND l2.lawyer_id <> l1.lawyer_id\n           LIMIT 1\n       ) ELSE NULL END AS another_partner_full_name\nFROM legal_services.lawyers l1;"}, {"role": "user", "content": "Only include lawyers who have an email address specified."}, {"role": "assistant", "content": "SELECT l1.first_name || ' ' || l1.last_name AS lawyer_full_name, l1.bar_number,\n       CASE WHEN l1.is_partner = TRUE THEN (\n           SELECT l2.first_name || ' ' || l2.last_name\n           FROM legal_services.lawyers l2\n           WHERE l2.firm_id = l1.firm_id AND l2.is_partner = TRUE AND l2.lawyer_id <> l1.lawyer_id\n           LIMIT 1\n       ) ELSE NULL END AS another_partner_full_name\nFROM legal_services.lawyers l1\nWHERE l1.email IS NOT NULL AND l1.email <> '';"}, {"role": "user", "content": "Actually, restrict it to lawyers hired in or after 2023."}, {"role": "assistant", "content": "SELECT l1.first_name || ' ' || l1.last_name AS lawyer_full_name, l1.bar_number,\n       CASE WHEN l1.is_partner = TRUE THEN (\n           SELECT l2.first_name || ' ' || l2.last_name\n           FROM legal_services.lawyers l2\n           WHERE l2.firm_id = l1.firm_id AND l2.is_partner = TRUE AND l2.lawyer_id <> l1.lawyer_id\n           LIMIT 1\n       ) ELSE NULL END AS another_partner_full_name\nFROM legal_services.lawyers l1\nWHERE l1.email IS NOT NULL AND l1.email <> '' AND l1.hire_date >= '2023-01-01';"}, {"role": "user", "content": "Sort the results by the lawyer's last name in descending order."}, {"role": "assistant", "content": "SELECT l1.first_name || ' ' || l1.last_name AS lawyer_full_name, l1.bar_number,\n       CASE WHEN l1.is_partner = TRUE THEN (\n           SELECT l2.first_name || ' ' || l2.last_name\n           FROM legal_services.lawyers l2\n           WHERE l2.firm_id = l1.firm_id AND l2.is_partner = TRUE AND l2.lawyer_id <> l1.lawyer_id\n           LIMIT 1\n       ) ELSE NULL END AS another_partner_full_name\nFROM legal_services.lawyers l1\nWHERE l1.email IS NOT NULL AND l1.email <> '' AND l1.hire_date >= '2023-01-01'\nORDER BY l1.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 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": "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": "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": "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": "What are the safety ratings or crash statistics for the Boeing 787 Dreamliner?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to safety ratings or crash statistics for specific aircraft models like the Boeing 787 Dreamliner. My data is limited to the information in the aircraft_models table, which includes details such as model name, manufacturer, passenger capacity, and technical specifications. For safety-related information, I recommend consulting official aviation authorities or safety reports."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models ( model_id text, model_name text, manufacturer text, passenger_capacity integer, max_range_km integer, engine_type text, wingspan_m numeric, status text, first_flight_date date )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 ERC20 tokens with the highest total supply, along with their names and contract addresses, but only include tokens where the price is greater than $0.10."}, {"role": "assistant", "content": "SELECT tm.name, tm.contract_address, tm.total_supply FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price > 0.10 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the symbol and decimals for these tokens?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tm.total_supply, tm.decimals FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price > 0.10 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Now filter these results to only show tokens with decimals equal to 18."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tm.total_supply, tm.decimals FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price > 0.10 AND tm.decimals = 18 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc1155_approval_for_all ( 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 nft_holder_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_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_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": "Show me the top 5 NFT collections with the highest floor price on Ethereum, along with their names and contract addresses."}, {"role": "assistant", "content": "SELECT name, contract_address, floor_price FROM nft_collections WHERE blockchain = 'ethereum' ORDER BY CAST(floor_price AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the banner image URL and filter to only show ERC721 collections?"}, {"role": "assistant", "content": "SELECT name, contract_address, floor_price, banner_image_url FROM nft_collections WHERE blockchain = 'ethereum' AND erc_type = 'ERC721' ORDER BY CAST(floor_price AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "I think there's a typo in your query - it should be 'nft_collections' not 'nft_collections'. Also, can you join this with the nft_metadata table to include the average rarity score for these collections?"}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, nc.floor_price, nc.banner_image_url, AVG(nm.rarity_score) as avg_rarity_score FROM nft_collections nc JOIN nft_metadata nm ON nc.contract_address = nm.contract_address WHERE nc.blockchain = 'ethereum' AND nc.erc_type = 'ERC721' GROUP BY nc.name, nc.contract_address, nc.floor_price, nc.banner_image_url ORDER BY CAST(nc.floor_price AS decimal) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.text )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_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 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 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 erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone (\n    address varchar NOT NULL, -- address fields for the functionType  in contract\n    table_id varchar NOT NULL, -- table_id fields for the functionType  in contract\n    key_bytes varchar NOT NULL, -- key_bytes fields for the functionType  in contract\n    key0 varchar NOT NULL, -- key0 fields for the functionType  in contract\n    key1 varchar NOT NULL, -- key1 fields for the functionType  in contract\n    static_data varchar NOT NULL, -- static_data fields for the functionType  in contract\n    encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType  in contract\n    dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType  in contract\n    is_deleted boolean NOT NULL, -- is_deleted fields for the functionType  in contract\n    block_number bigint NOT NULL, -- Block number uniquely identifying the block\n    log_index bigint NOT NULL  -- Index of the log within the transaction\n)\nCREATE TABLE token_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 text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"}
{"conversations": [{"role": "user", "content": "Show me the total billable hours and total billed amount for each lawyer who worked on 'Civil Litigation' cases in 2023, sorted by billed amount descending."}, {"role": "assistant", "content": "SELECT te.lawyer_id,\n       SUM(te.hours_spent) AS total_billable_hours,\n       SUM(te.hours_spent * te.billing_rate) AS total_billed_amount\nFROM legal_services.time_entries te\nJOIN legal_services.cases c ON te.case_id = c.case_id\nWHERE te.is_billable = true\n  AND te.is_billed = true\n  AND c.case_type = 'Civil Litigation'\n  AND te.date_worked BETWEEN '2023-01-01' AND '2023-12-31'\nGROUP BY te.lawyer_id\nORDER BY total_billed_amount DESC;"}, {"role": "user", "content": "Actually, I'd like to include only those lawyers who have at least 10 billable entries in that period."}, {"role": "assistant", "content": "SELECT te.lawyer_id,\n       SUM(te.hours_spent) AS total_billable_hours,\n       SUM(te.hours_spent * te.billing_rate) AS total_billed_amount\nFROM legal_services.time_entries te\nJOIN legal_services.cases c ON te.case_id = c.case_id\nWHERE te.is_billable = true\n  AND te.is_billed = true\n  AND c.case_type = 'Civil Litigation'\n  AND te.date_worked BETWEEN '2023-01-01' AND '2023-12-31'\nGROUP BY te.lawyer_id\nHAVING COUNT(*) >= 10\nORDER BY total_billed_amount DESC;"}, {"role": "user", "content": "Also break down the report by case, listing each lawyer and case_number along with their billable hours and billed amount per case, sorted by billed amount descending."}, {"role": "assistant", "content": "SELECT te.lawyer_id,\n       c.case_number,\n       SUM(te.hours_spent) AS case_billable_hours,\n       SUM(te.hours_spent * te.billing_rate) AS case_billed_amount\nFROM legal_services.time_entries te\nJOIN legal_services.cases c ON te.case_id = c.case_id\nWHERE te.is_billable = true\n  AND te.is_billed = true\n  AND c.case_type = 'Civil Litigation'\n  AND te.date_worked BETWEEN '2023-01-01' AND '2023-12-31'\nGROUP BY te.lawyer_id, c.case_number\nORDER BY case_billed_amount DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text, first_name text, last_name text, company_name text, email text, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.law_firms ( firm_id text, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\nCREATE TABLE legal_services.time_entries ( entry_id text, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable boolean, is_billed boolean, invoice_id text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me all business center services (category = 'Business Center') along with their property IDs and descriptions, where the service is available."}, {"role": "assistant", "content": "SELECT service_name, property_id, description FROM hospitality_technology.services WHERE category = 'Business Center' AND is_available = true;"}, {"role": "user", "content": "Now, join this with another query to include the property names from the properties table (assuming properties table has property_id and property_name columns)."}, {"role": "assistant", "content": "SELECT s.service_name, s.property_id, s.description, p.property_name FROM hospitality_technology.services s JOIN hospitality_technology.properties p ON s.property_id = p.property_id WHERE s.category = 'Business Center' AND s.is_available = true;"}, {"role": "user", "content": "The query is missing the price information. Can you include that as well?"}, {"role": "assistant", "content": "SELECT s.service_name, s.property_id, s.description, p.property_name, s.price FROM hospitality_technology.services s JOIN hospitality_technology.properties p ON s.property_id = p.property_id WHERE s.category = 'Business Center' AND s.is_available = true;"}, {"role": "user", "content": "Actually, I need to see only services priced per hour (unit = 'Per Hour'), and order them by property name in alphabetical order."}, {"role": "assistant", "content": "SELECT s.service_name, s.property_id, s.description, p.property_name, s.price FROM hospitality_technology.services s JOIN hospitality_technology.properties p ON s.property_id = p.property_id WHERE s.category = 'Business Center' AND s.is_available = true AND s.unit = 'Per Hour' ORDER BY p.property_name ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.services (\n    service_id character varying(64) NOT NULL, -- unique identifier for a chargeable service\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    service_name character varying(150) NOT NULL, -- e.g., Room Service - Burger, Spa - Massage 60min, Laundry - Shirt\n    description text,\n    category character varying(100), -- e.g., Food & Beverage, Wellness, Business Center, Activities\n    price numeric(10, 2) NOT NULL, -- price per unit/instance\n    unit character varying(30), -- e.g., Per Item, Per Hour, Per Day\n    is_available boolean NOT NULL DEFAULT true, -- is the service currently offered?\n    department character varying(100), -- department responsible (e.g., F&B, Spa, Housekeeping)\n    PRIMARY KEY (service_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all 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": "Give me a breakdown of the number of reviews per day for the last 14 days, including the review_date and review count."}, {"role": "assistant", "content": "SELECT DATE(review_date) AS review_day, COUNT(*) AS review_count\nFROM hospitality_technology.reviews\nWHERE review_date >= CURRENT_DATE - INTERVAL '14 days'\nGROUP BY DATE(review_date)\nORDER BY review_day ASC;"}, {"role": "user", "content": "Add the number of public reviews for each day in a separate column named public_review_count."}, {"role": "assistant", "content": "SELECT DATE(review_date) AS review_day,\n       COUNT(*) AS review_count,\n       SUM(CASE WHEN is_public THEN 1 ELSE 0 END) AS public_review_count\nFROM hospitality_technology.reviews\nWHERE review_date >= CURRENT_DATE - INTERVAL '14 days'\nGROUP BY DATE(review_date)\nORDER BY review_day ASC;"}, {"role": "user", "content": "Now, also include the number of reviews per day with a rating_overall below 3 as a column called low_rating_count."}, {"role": "assistant", "content": "SELECT DATE(review_date) AS review_day,\n       COUNT(*) AS review_count,\n       SUM(CASE WHEN is_public THEN 1 ELSE 0 END) AS public_review_count,\n       SUM(CASE WHEN rating_overall < 3 THEN 1 ELSE 0 END) AS low_rating_count\nFROM hospitality_technology.reviews\nWHERE review_date >= CURRENT_DATE - INTERVAL '14 days'\nGROUP BY DATE(review_date)\nORDER BY review_day 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.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": "I need to find all components associated with a specific supplier. Can you help with that?"}, {"role": "assistant", "content": "HGETALL component:<component_id>\nIF HGET component:<component_id> supplier_id = 'sup:ACME_AERO' THEN INCLUDE"}, {"role": "user", "content": "Can you also show me the material ID for each of these components?"}, {"role": "assistant", "content": "HGETALL component:<component_id>\nIF HGET component:<component_id> supplier_id = 'sup:ACME_AERO' THEN INCLUDE\nHGET component:<component_id> material_id"}, {"role": "user", "content": "What if I want to exclude components with a specific material ID?"}, {"role": "assistant", "content": "HGETALL component:<component_id>\nIF HGET component:<component_id> supplier_id = 'sup:ACME_AERO' THEN INCLUDE\nHGET component:<component_id> material_id\nIF HGET component:<component_id> material_id != 'mat:TI64' THEN INCLUDE"}, {"role": "user", "content": "Can you add the component name to the result as well?"}, {"role": "assistant", "content": "HGETALL component:<component_id>\nIF HGET component:<component_id> supplier_id = 'sup:ACME_AERO' THEN INCLUDE\nHGET component:<component_id> material_id\nIF HGET component:<component_id> material_id != 'mat:TI64' THEN INCLUDE\nHGET component:<component_id> component_name"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nUse Hashes. Key pattern: 'component:<component_id>'. Example: HSET component:LGSTRUT01 part_number \"PN-5521-A\" component_name \"Landing Gear Strut\" material_id \"mat:TI64\" supplier_id \"sup:ACME_AERO\" ... Consider Sets for reverse lookups (e.g., 'material_components:<material_id>' -> Set<component_id>).\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 me the top 3 tokens by trend rank in the 'NFT' narrative, along with their price and 24-hour trading volume."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, price, total_volume FROM token_basic_info WHERE narrative = 'NFT' ORDER BY trend_rank ASC LIMIT 3;"}, {"role": "user", "content": "Can you also include their 1-hour and 7-day price change percentages?"}, {"role": "assistant", "content": "SELECT token_name, token_symbol, price, total_volume, price_change_percentage_1h, price_change_percentage_7d FROM token_basic_info WHERE narrative = 'NFT' ORDER BY trend_rank ASC LIMIT 3;"}, {"role": "user", "content": "Actually, I only want tokens with positive price changes in both time frames."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, price, total_volume, price_change_percentage_1h, price_change_percentage_7d FROM token_basic_info WHERE narrative = 'NFT' AND price_change_percentage_1h > 0 AND price_change_percentage_7d > 0 ORDER BY trend_rank ASC LIMIT 3;"}, {"role": "user", "content": "Now order the results by 24-hour trading volume instead of trend rank."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, price, total_volume, price_change_percentage_1h, price_change_percentage_7d FROM token_basic_info WHERE narrative = 'NFT' AND price_change_percentage_1h > 0 AND price_change_percentage_7d > 0 ORDER BY total_volume::numeric DESC LIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, token_name character varying(100) NOT NULL, token_symbol character varying(100) NOT NULL, token_address character varying(100) NOT NULL, chain text, price double precision, price_change_percentage_1h double precision, price_change_percentage_24h double precision, price_change_percentage_7d double precision, highest_price_24h double precision, lowest_price_24h double precision, market_cap double precision, market_cap_rank bigint, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank bigint )\n"}
{"conversations": [{"role": "user", "content": "List service orders placed in the last 7 days, showing order_id, service_name, guest full name, and order_timestamp."}, {"role": "assistant", "content": "SELECT so.order_id, s.service_name, g.first_name || ' ' || g.last_name AS guest_name, so.order_timestamp\nFROM hospitality_technology.service_orders so\nJOIN hospitality_technology.services s ON so.service_id = s.service_id\nJOIN hospitality_technology.guests g ON so.guest_id = g.guest_id\nWHERE so.order_timestamp >= current_date - INTERVAL '7 days';"}, {"role": "user", "content": "Filter to only those orders with status 'Delivered' and sort by delivery_timestamp ascending."}, {"role": "assistant", "content": "SELECT so.order_id, s.service_name, g.first_name || ' ' || g.last_name AS guest_name, so.order_timestamp, so.delivery_timestamp\nFROM hospitality_technology.service_orders so\nJOIN hospitality_technology.services s ON so.service_id = s.service_id\nJOIN hospitality_technology.guests g ON so.guest_id = g.guest_id\nWHERE so.order_timestamp >= current_date - INTERVAL '7 days'\n  AND so.status = 'Delivered'\nORDER BY so.delivery_timestamp ASC;"}, {"role": "user", "content": "Also include the staff member who delivered the service as delivered_by (full name) and limit to 10 records."}, {"role": "assistant", "content": "SELECT so.order_id, s.service_name, g.first_name || ' ' || g.last_name AS guest_name, so.order_timestamp, so.delivery_timestamp, st.first_name || ' ' || st.last_name AS delivered_by\nFROM hospitality_technology.service_orders so\nJOIN hospitality_technology.services s ON so.service_id = s.service_id\nJOIN hospitality_technology.guests g ON so.guest_id = g.guest_id\nJOIN hospitality_technology.staff st ON so.staff_id_delivered = st.staff_id\nWHERE so.order_timestamp >= current_date - INTERVAL '7 days'\n  AND so.status = 'Delivered'\nORDER BY so.delivery_timestamp ASC\nLIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 )\nCREATE TABLE hospitality_technology.guests ( guest_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, address_line1.text, city.text, state_province.text, postal_code.text, country_code.text, preferences.text, loyalty_member_id.text, communication_consent.boolean, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.reservations ( reservation_id.text, property_id.text, guest_id.text, room_id.text, room_type_id.text, check_in_date.date, check_out_date.date, actual_check_in_ts.timestamp, actual_check_out_ts.timestamp, num_adults.integer, num_children.integer, status.text, booking_source.text, rate_plan_id.text, total_amount.numeric, amount_paid.numeric, special_requests.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id.text, property_id.text, first_name.text, last_name.text, position.text, work_email.text, work_phone.text, hire_date.date, termination_date.date, is_active.boolean, access_level.integer, manager_id.text, created_at.timestamp )\nCREATE TABLE hospitality_technology.services ( service_id.text, 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.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 ( 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": "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": "Provide a count of appointments grouped by the booking method."}, {"role": "assistant", "content": "SELECT booking_method, COUNT(*) AS appointment_count FROM government_services.appointments GROUP BY booking_method;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.documents (\n    document_id character varying(64) NOT NULL, -- unique identifier for the document instance\n    application_id character varying(64), -- FK to applications table (optional, could be linked to citizen directly)\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    document_type character varying(100) NOT NULL, -- e.g., Passport Scan, Proof of Address, Birth Certificate\n    file_reference text NOT NULL, -- reference to the stored file (e.g., S3 URL, internal path)\n    upload_timestamp timestamp NOT NULL,\n    expiry_date date,\n    verification_status character varying(30) DEFAULT 'Pending', -- e.g., Pending, Verified, Rejected\n    verified_by_employee_id character varying(64), -- FK to employees table\n    verification_timestamp timestamp,\n    PRIMARY KEY (document_id)\n)\nCREATE TABLE government_services.employees (\n    employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(150) NOT NULL,\n    department character varying(100),\n    work_email character varying(128) NOT NULL UNIQUE,\n    work_phone character varying(32),\n    hire_date date NOT NULL,\n    termination_date date, -- null if currently employed\n    access_level character varying(50), -- Role or permission level\n    manager_employee_id character varying(64), -- FK to self for reporting structure\n    PRIMARY KEY (employee_id)\n)\nCREATE TABLE government_services.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    employee_id character varying(64), -- FK to employees table (optional, if assigned)\n    location_id character varying(64), -- FK to service_locations table (if physical)\n    service_id character varying(64), -- FK to services table (optional, if related to specific service)\n    scheduled_start_time timestamp NOT NULL,\n    scheduled_end_time timestamp,\n    purpose text NOT NULL, -- reason for the appointment\n    status character varying(30) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-Show\n    booking_method character varying(50), -- e.g., Online, Phone, In-Person\n    created_at timestamp NOT NULL, -- when the appointment was booked\n    notes text,\n    PRIMARY KEY (appointment_id)\n)\nCREATE TABLE government_services.notifications (\n    notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    application_id character varying(64), -- FK to applications table (optional)\n    message_subject character varying(255),\n    message_body text NOT NULL,\n    channel character varying(30) NOT NULL, -- e.g., Email, SMS, Portal Message, Mail\n    sent_at timestamp NOT NULL,\n    status character varying(30) NOT NULL, -- e.g., Queued, Sent, Delivered, Failed, Read\n    related_entity_type character varying(50), -- e.g., Application, Appointment, Document Request\n    related_entity_id character varying(64), -- ID of the related entity\n    PRIMARY KEY (notification_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List the top 5 tokens by net_flow, showing token_symbol, net_flow, pnl, and price."}, {"role": "assistant", "content": "SELECT token_symbol,\n       net_flow,\n       pnl,\n       price\nFROM smart_money_token_performance\nORDER BY net_flow DESC\nLIMIT 5;"}, {"role": "user", "content": "Now join this result back to the full table to include the chain for each of these tokens."}, {"role": "assistant", "content": "WITH top5 AS (\n  SELECT token_symbol\n  FROM smart_money_token_performance\n  ORDER BY net_flow DESC\n  LIMIT 5\n)\nSELECT t.token_symbol,\n       t.chain,\n       t.net_flow,\n       t.pnl,\n       t.price\nFROM smart_money_token_performance t\nJOIN top5 ON t.token_symbol = top5.token_symbol;"}, {"role": "user", "content": "Filter these joined results to only include tokens with realized_ratio greater than 0.1."}, {"role": "assistant", "content": "WITH top5 AS (\n  SELECT token_symbol\n  FROM smart_money_token_performance\n  ORDER BY net_flow DESC\n  LIMIT 5\n)\nSELECT t.token_symbol,\n       t.chain,\n       t.net_flow,\n       t.pnl,\n       t.price,\n       t.realized_ratio\nFROM smart_money_token_performance t\nJOIN top5 ON t.token_symbol = top5.token_symbol\nWHERE t.realized_ratio > 0.1;"}, {"role": "user", "content": "Sort the final output by realized_ratio in descending order."}, {"role": "assistant", "content": "WITH top5 AS (\n  SELECT token_symbol\n  FROM smart_money_token_performance\n  ORDER BY net_flow DESC\n  LIMIT 5\n)\nSELECT t.token_symbol,\n       t.chain,\n       t.net_flow,\n       t.pnl,\n       t.price,\n       t.realized_ratio\nFROM smart_money_token_performance t\nJOIN top5 ON t.token_symbol = top5.token_symbol\nWHERE t.realized_ratio > 0.1\nORDER BY t.realized_ratio 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 smart_money_token_performance ( token_address.text, token_symbol.text, pnl.numeric, net_flow.numeric, avg_cost.numeric, price.numeric, realized_ratio.numeric, roi.numeric, chain.text )\n"}
{"conversations": [{"role": "user", "content": "I want a summary of each asset showing the total number of trades executed and the average trade price, including asset name and symbol."}, {"role": "assistant", "content": "SELECT a.asset_id,\n       a.name,\n       a.symbol,\n       COUNT(t.trade_id) AS trades_count,\n       AVG(t.price) AS avg_price\nFROM trading_platform.assets a\nLEFT JOIN trading_platform.trades t ON a.asset_id = t.asset_id\nGROUP BY a.asset_id, a.name, a.symbol;"}, {"role": "user", "content": "Actually, exclude trades before '2024-05-01'."}, {"role": "assistant", "content": "SELECT a.asset_id,\n       a.name,\n       a.symbol,\n       COUNT(t.trade_id) AS trades_count,\n       AVG(t.price) AS avg_price\nFROM trading_platform.assets a\nLEFT JOIN trading_platform.trades t ON a.asset_id = t.asset_id\n  AND t.traded_at >= '2024-05-01'\nGROUP BY a.asset_id, a.name, a.symbol;"}], "system": "You are an SQL statement expert. Given the table structure 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 text, order_id text, buyer_id text, seller_id text, asset_id text, quantity numeric, price numeric, traded_at timestamp )\nCREATE TABLE trading_platform.assets ( asset_id text, 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.peers ( peer_id text, ip_address text, port integer, last_seen timestamp )\nCREATE TABLE trading_platform.metadata ( metadata_id text, asset_id text, key text, value text )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id text, user_id text, status text, reviewed_at timestamp )\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": "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": "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": "Show me wallet addresses that hold more than 1000 of any ERC20 token, along with the token symbol and amount, sorted by amount in descending order."}, {"role": "assistant", "content": "SELECT b.wallet_address, t.symbol, b.amount FROM erc20_balances b JOIN sui_coins_metadata t ON b.contract_address = t.coin_type WHERE CAST(b.amount AS decimal) > 1000 ORDER BY CAST(b.amount AS decimal) DESC;"}, {"role": "user", "content": "Can you also include the current price of each token from the token_prices_latest table?"}, {"role": "assistant", "content": "SELECT b.wallet_address, t.symbol, b.amount, p.price FROM erc20_balances b JOIN sui_coins_metadata t ON b.contract_address = t.coin_type JOIN token_prices_latest p ON b.contract_address = p.address WHERE CAST(b.amount AS decimal) > 1000 ORDER BY CAST(b.amount AS decimal) DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.text )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk varchar )\nCREATE TABLE sui_coins_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\nCREATE TABLE nft_metadata (\n    blockchain varchar NOT NULL, -- blockchain fields for the functionType  in contract\n    contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n    token_id varchar NOT NULL, -- The number of the token\n    contract_name varchar NOT NULL, -- contract_name fields for the functionType  in contract\n    erc_type varchar NOT NULL, -- The type of token\n    amount bigint NOT NULL, -- amount fields for the functionType  in contract\n    minter varchar NOT NULL, -- minter fields for the functionType  in contract\n    owner varchar NOT NULL, -- owner fields for the functionType  in contract\n    mint_block_number bigint NOT NULL, -- mint_block_number fields for the functionType  in contract\n    mint_time bigint NOT NULL, -- mint_time fields for the functionType  in contract\n    mint_transaction_hash varchar NOT NULL, -- mint_transaction_hash fields for the functionType  in contract\n    mint_price varchar NOT NULL, -- mint_price fields for the functionType  in contract\n    token_uri varchar NOT NULL, -- token_uri fields for the functionType  in contract\n    metadata varchar NOT NULL, -- metadata fields for the functionType  in contract\n    name varchar NOT NULL, -- name fields for the functionType  in contract\n    image_uri varchar NOT NULL, -- image_uri fields for the functionType  in contract\n    traits varchar NOT NULL, -- traits fields for the functionType  in contract\n    updated_at bigint NOT NULL, -- updated_at fields for the functionType  in contract\n    status varchar NOT NULL, -- status fields for the functionType  in contract\n    rarity_score real NOT NULL, -- rarity_score fields for the functionType  in contract\n    rarity_rank integer NOT NULL, -- rarity_rank fields for the functionType  in contract\n    unique_attribute_count integer NOT NULL, -- unique_attribute_count fields for the functionType  in contract\n    pk integer NOT NULL  -- Partition key for the table(floor(mint_time / 1000 / 86400 / 30))\n)\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone (\n    address varchar NOT NULL, -- address fields for the functionType  in contract\n    table_id varchar NOT NULL, -- table_id fields for the functionType  in contract\n    key_bytes varchar NOT NULL, -- key_bytes fields for the functionType  in contract\n    key0 varchar NOT NULL, -- key0 fields for the functionType  in contract\n    key1 varchar NOT NULL, -- key1 fields for the functionType  in contract\n    static_data varchar NOT NULL, -- static_data fields for the functionType  in contract\n    encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType  in contract\n    dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType  in contract\n    is_deleted boolean NOT NULL, -- is_deleted fields for the functionType  in contract\n    block_number bigint NOT NULL, -- Block number uniquely identifying the block\n    log_index bigint NOT NULL  -- Index of the log within the transaction\n)\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_balances_avalanche (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"}
{"conversations": [{"role": "user", "content": "Which pairs of routes have the same distance in kilometers but different estimated durations? Show their route numbers, distances and both estimated durations."}, {"role": "assistant", "content": "SELECT r1.route_number AS route_number_1, r2.route_number AS route_number_2, r1.distance_km, r1.estimated_duration_minutes AS estimated_duration_1, r2.estimated_duration_minutes AS estimated_duration_2\nFROM transportation.routes r1\nJOIN transportation.routes r2\n    ON r1.distance_km = r2.distance_km\n    AND r1.estimated_duration_minutes <> r2.estimated_duration_minutes\n    AND r1.route_id < r2.route_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": "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": "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": "List the full name of each lawyer along with the location and status of their appointments."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T2.location, T2.status FROM legal_services.lawyers AS T1 JOIN legal_services.appointments AS T2 ON T1.lawyer_id = T2.lawyer_id"}, {"role": "user", "content": "Please only show appointments with a status of 'completed' or 'cancelled', and sort by lawyer's last name."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T2.location, T2.status FROM legal_services.lawyers AS T1 JOIN legal_services.appointments AS T2 ON T1.lawyer_id = T2.lawyer_id WHERE T2.status IN ('completed', 'cancelled') ORDER BY T1.last_name"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers ( lawyer_id text PRIMARY KEY, first_name text, last_name text, bar_number text UNIQUE, firm_id text, email text UNIQUE, phone text, specialization text, hire_date timestamp, is_partner bool )\nCREATE TABLE legal_services.time_entries (\n    entry_id character varying(64) NOT NULL,  -- unique identifier for the time entry\n    case_id character varying(64) NOT NULL, -- FK to cases table\n    lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (who performed the work)\n    date_worked date NOT NULL, -- date the work was performed\n    hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), -- duration of work in hours (e.g., 1.5 for 1h 30m)\n    billing_rate numeric(10, 2) NOT NULL, -- hourly rate applied for this entry\n    description text NOT NULL, -- detailed description of the work performed\n    is_billable boolean DEFAULT true, -- whether this time entry is billable to the client\n    is_billed boolean DEFAULT false, -- whether this entry has been included in an invoice\n    invoice_id character varying(64), -- FK to invoices table (once billed)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the entry was recorded\n    PRIMARY KEY (entry_id)\n)\nCREATE TABLE legal_services.appointments ( appointment_id text PRIMARY KEY, client_id text, lawyer_id text, case_id text, start_time timestamp, end_time timestamp, location text, subject text, notes text, status text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "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": "For each manager, count how many agents they manage. Show manager_id and agent_count."}, {"role": "assistant", "content": "SELECT manager_id,\n       COUNT(*) AS agent_count\nFROM insurance.agents\nGROUP BY manager_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.agents ( agent_id.text, first_name.text, last_name.text, agency_name.text, license_number.text, license_state.text, contact_email.text, contact_phone.text, hire_date.date, termination_date.date, status.text, commission_rate.numeric, manager_id.text )\n"}
{"conversations": [{"role": "user", "content": "For each address, show the total amount contained in UTXOs that have been spent."}, {"role": "assistant", "content": "SELECT address, SUM(amount) FROM utxos WHERE spent = TRUE GROUP BY address;"}, {"role": "user", "content": "Only include addresses where this total spent amount is greater than 500 and order the results by the total amount descending."}, {"role": "assistant", "content": "SELECT address, SUM(amount) FROM utxos WHERE spent = TRUE GROUP BY address HAVING SUM(amount) > 500 ORDER BY SUM(amount) DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.utxos (\n    utxo_id character varying(64) NOT NULL,  -- unique identifier for the UTXO\n    transaction_id character varying(64) NOT NULL, -- identifier of the transaction that created the UTXO\n    output_index integer NOT NULL, -- index of the output in the transaction\n    address character varying(128) NOT NULL, -- address that can spend the UTXO\n    amount numeric(38,14) NOT NULL, -- amount of the asset in the UTXO\n    spent boolean NOT NULL, -- whether the UTXO has been spent\n    PRIMARY KEY (utxo_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all patients born in the 1980s, including their full names and genders."}, {"role": "assistant", "content": "SELECT CONCAT(first_name, ' ', last_name) AS full_name, gender FROM healthcare.patients WHERE date_of_birth BETWEEN '1980-01-01' AND '1989-12-31';"}, {"role": "user", "content": "Now filter it to only show female patients who have a phone number listed."}, {"role": "assistant", "content": "SELECT CONCAT(first_name, ' ', last_name) AS full_name, gender FROM healthcare.patients WHERE date_of_birth BETWEEN '1980-01-01' AND '1989-12-31' AND gender = 'Female' AND phone_number IS NOT NULL;"}, {"role": "user", "content": "Can you also include their email addresses in the results?"}, {"role": "assistant", "content": "SELECT CONCAT(first_name, ' ', last_name) AS full_name, gender, email FROM healthcare.patients WHERE date_of_birth BETWEEN '1980-01-01' AND '1989-12-31' AND gender = 'Female' AND phone_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.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "How many unique patient records are there for each gender?"}, {"role": "assistant", "content": "SELECT gender, COUNT(DISTINCT patient_id) AS patient_count FROM healthcare.patients GROUP BY gender;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id.text, first_name.text, last_name.text, date_of_birth.date, gender.text, address.text, phone_number.text, email.text, emergency_contact_name.text, emergency_contact_phone.text, created_at.timestamp, updated_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me each product_type along with the count of products for that type, but only include types where the average base_premium exceeds 500. Order the results by the product count in descending order."}, {"role": "assistant", "content": "SELECT product_type,\n       COUNT(*) AS product_count\nFROM insurance.insurance_products\nGROUP BY product_type\nHAVING AVG(base_premium) > 500\nORDER BY product_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.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 )\n"}
{"conversations": [{"role": "user", "content": "How many reviews does each staff member respond to, along with their full name and the average response time in hours?"}, {"role": "assistant", "content": "SELECT st.staff_id,\n       st.first_name || ' ' || st.last_name AS staff_full_name,\n       COUNT(*) AS response_count,\n       AVG(EXTRACT(EPOCH FROM (r.response_date - r.review_date)) / 3600) AS avg_response_time_hours\nFROM hospitality_technology.reviews r\nJOIN hospitality_technology.staff st\n  ON r.response_staff_id = st.staff_id\nWHERE r.response_date IS NOT NULL\nGROUP BY st.staff_id, st.first_name, st.last_name;"}, {"role": "user", "content": "Filter to only include staff who responded to at least 5 reviews."}, {"role": "assistant", "content": "SELECT sub.staff_id,\n       sub.staff_full_name,\n       sub.response_count,\n       sub.avg_response_time_hours\nFROM (\n  SELECT st.staff_id,\n         st.first_name || ' ' || st.last_name AS staff_full_name,\n         COUNT(*) AS response_count,\n         AVG(EXTRACT(EPOCH FROM (r.response_date - r.review_date)) / 3600) AS avg_response_time_hours\n  FROM hospitality_technology.reviews r\n  JOIN hospitality_technology.staff st\n    ON r.response_staff_id = st.staff_id\n  WHERE r.response_date IS NOT NULL\n  GROUP BY st.staff_id, st.first_name, st.last_name\n) sub\nWHERE sub.response_count >= 5;"}, {"role": "user", "content": "Also order the result by average response time ascending."}, {"role": "assistant", "content": "SELECT sub.staff_id,\n       sub.staff_full_name,\n       sub.response_count,\n       sub.avg_response_time_hours\nFROM (\n  SELECT st.staff_id,\n         st.first_name || ' ' || st.last_name AS staff_full_name,\n         COUNT(*) AS response_count,\n         AVG(EXTRACT(EPOCH FROM (r.response_date - r.review_date)) / 3600) AS avg_response_time_hours\n  FROM hospitality_technology.reviews r\n  JOIN hospitality_technology.staff st\n    ON r.response_staff_id = st.staff_id\n  WHERE r.response_date IS NOT NULL\n  GROUP BY st.staff_id, st.first_name, st.last_name\n) sub\nWHERE sub.response_count >= 5\nORDER BY sub.avg_response_time_hours ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text PRIMARY KEY, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.rooms (\n    room_id character varying(64) NOT NULL,  -- unique identifier for the room\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    room_number character varying(10) NOT NULL, -- room number identifier (e.g., '101', 'Suite 2B')\n    room_type_id character varying(64) NOT NULL, -- FK to room_types table\n    floor integer, -- floor number the room is on\n    status character varying(50) NOT NULL, -- e.g., Available, Occupied, Cleaning, OutOfOrder, Maintenance\n    is_smoking boolean NOT NULL DEFAULT false, -- smoking allowed flag\n    features text, -- description of features (e.g., Balcony, Sea View, Jacuzzi)\n    current_condition text, -- notes on room condition\n    last_cleaned_at timestamp with time zone, -- timestamp of last cleaning\n    PRIMARY KEY (room_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.room_types ( room_type_id text, property_id text, type_name text, description text, base_rate numeric, max_occupancy integer, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.guests ( guest_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id text, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level integer, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.services (\n    service_id character varying(64) NOT NULL, -- unique identifier for a chargeable service\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    service_name character varying(150) NOT NULL, -- e.g., Room Service - Burger, Spa - Massage 60min, Laundry - Shirt\n    description text,\n    category character varying(100), -- e.g., Food & Beverage, Wellness, Business Center, Activities\n    price numeric(10, 2) NOT NULL, -- price per unit/instance\n    unit character varying(30), -- e.g., Per Item, Per Hour, Per Day\n    is_available boolean NOT NULL DEFAULT true, -- is the service currently offered?\n    department character varying(100), -- department responsible (e.g., F&B, Spa, Housekeeping)\n    PRIMARY KEY (service_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\nCREATE TABLE hospitality_technology.payments (\n    payment_id character varying(64) NOT NULL,  -- unique identifier for the payment transaction\n    reservation_id character varying(64), -- FK to reservations (if payment is for a stay)\n    guest_id character varying(64) NOT NULL, -- FK to guests (who paid)\n    bill_id character varying(64), -- FK to bills/invoices this payment applies to\n    amount numeric(12,2) NOT NULL, -- amount of the payment\n    currency_code character varying(3) NOT NULL, -- ISO currency code (e.g., USD, EUR)\n    payment_method character varying(50) NOT NULL, -- e.g., CreditCard, Cash, BankTransfer, Points, Voucher\n    card_type character varying(50), -- e.g., Visa, MasterCard, Amex (if CC)\n    card_last_four character varying(4), -- last 4 digits of CC (if CC)\n    transaction_ref character varying(128), -- reference ID from payment gateway or processor\n    payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the payment occurred\n    status character varying(50) NOT NULL, -- e.g., Pending, Succeeded, Failed, Refunded, Disputed\n    staff_id_processed character varying(64), -- FK to staff (who processed the payment)\n    notes text, -- notes about the payment\n    PRIMARY KEY (payment_id),\n    FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n    FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n    FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "Show 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": "Which customers have policies that expired in the last month? Please show the customer ID, policy number, and expiration date."}, {"role": "assistant", "content": "SELECT c.customer_id, p.policy_number, p.end_date\nFROM insurance.customers c\nJOIN insurance.policies p ON c.customer_id = p.customer_id\nWHERE p.end_date >= (CURRENT_DATE - INTERVAL '1 month') AND p.end_date < CURRENT_DATE;"}, {"role": "user", "content": "Add the customer's email to the results."}, {"role": "assistant", "content": "SELECT c.customer_id, c.email, p.policy_number, p.end_date\nFROM insurance.customers c\nJOIN insurance.policies p ON c.customer_id = p.customer_id\nWHERE p.end_date >= (CURRENT_DATE - INTERVAL '1 month') AND p.end_date < CURRENT_DATE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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.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 )\n"}
{"conversations": [{"role": "user", "content": "Find all customers who have made a premium payment and list their first name, last name, email, and the total amount they have paid across all their payments."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T1.email, SUM(T2.amount_paid) FROM insurance.customers AS T1 JOIN insurance.premium_payments AS T2 ON T1.customer_id = T2.customer_id GROUP BY T1.customer_id, T1.first_name, T1.last_name, T1.email;"}], "system": "You are an SQL statement expert. Given the table structure 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.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 )\n"}
{"conversations": [{"role": "user", "content": "For each passenger, show their passenger_id, first_name, last_name, the date and time of their earliest booking, and the date and time of their latest booking."}, {"role": "assistant", "content": "SELECT p.passenger_id,\n       p.first_name,\n       p.last_name,\n       MIN(b.booking_time) AS earliest_booking_time,\n       MAX(b.booking_time) AS latest_booking_time\nFROM transportation.passengers p\nLEFT JOIN transportation.bookings b\n  ON p.passenger_id = b.passenger_id\nGROUP BY p.passenger_id,\n         p.first_name,\n         p.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 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.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.passengers (\n    passenger_id character varying(64) NOT NULL,  -- unique identifier for the passenger\n    first_name character varying(128) NOT NULL, -- passenger's first name\n    last_name character varying(128) NOT NULL, -- passenger's last name\n    email character varying(128) UNIQUE, -- email address\n    phone_number character varying(32) UNIQUE, -- phone number\n    date_of_birth date, -- passenger's date of birth\n    loyalty_program_id character varying(64), -- identifier for loyalty program membership\n    created_at timestamp with time zone NOT NULL, -- time when the passenger record was created\n    PRIMARY KEY (passenger_id)\n)\nCREATE TABLE transportation.bookings ( booking_id 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": "Show me the top 3 tokens by USD value inflow where smart money was buying (type = 1), along with their chain information."}, {"role": "assistant", "content": "SELECT token_symbol, chain, usd_value FROM smart_money_token_inflow WHERE type = 1 ORDER BY usd_value DESC LIMIT 3;"}, {"role": "user", "content": "Can you filter these results to only include tokens from the Ethereum chain?"}, {"role": "assistant", "content": "SELECT token_symbol, chain, usd_value FROM smart_money_token_inflow WHERE type = 1 AND chain = 'Ethereum' ORDER BY usd_value DESC LIMIT 3;"}, {"role": "user", "content": "Now include the average price for these tokens as well."}, {"role": "assistant", "content": "SELECT token_symbol, chain, usd_value, avg_price FROM smart_money_token_inflow WHERE type = 1 AND chain = 'Ethereum' ORDER BY usd_value DESC LIMIT 3;"}, {"role": "user", "content": "Finally, order these results by average price instead of USD value."}, {"role": "assistant", "content": "SELECT token_symbol, chain, usd_value, avg_price FROM smart_money_token_inflow WHERE type = 1 AND chain = 'Ethereum' ORDER BY avg_price DESC LIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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) )\n  \"CREATE TABLE smart_money_token_inflow (\",\n    \"token_address character varying(100) NOT NULL, -- the token's address\",\n    \"token_symbol character varying(100), -- the tokens's symbol\",\n    \"token_amount numeric(38,2), -- the absolute value of the amount if user bought minus  the amount user sold of this token\",\n    \"usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token\",\n    \"avg_price numeric(38,6), -- the average cost price of user spent on this token\",\n    \"type int, -- the direction of the trade on this token. 1 means buying, 2 means selling\",\n    \"address_amount integer, -- the amount of the user bought this token\",\n    \"narrative character varying(100), -- the category or narrative of the token\",\n    \"chain character varying(100), -- the chain that the token resides\",\n    \",PRIMARY KEY (token_address, chain)\",\n\n"}
{"conversations": [{"role": "user", "content": "List all claims, including the claim ID, incident date, estimated loss, and the name of the insurance product associated with the policy under which the claim was made."}, {"role": "assistant", "content": "SELECT\n  c.claim_id,\n  c.incident_date,\n  c.estimated_loss,\n  ip.product_name\nFROM insurance.claims AS c\nJOIN insurance.policies AS p\n  ON c.policy_id = p.policy_id\nJOIN insurance.insurance_products AS ip\n  ON p.product_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.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": "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": "Show me all home loans (loan_id, principal_amount, interest_rate) where the current principal balance is more than 75% of the original principal amount, along with the account_id and employee details (first_name, last_name) of the employee who processed the loan application."}, {"role": "assistant", "content": "SELECT l.loan_id, l.principal_amount, l.interest_rate, l.account_id, e.first_name, e.last_name FROM financial_services.loans l JOIN financial_services.employees e ON l.account_id = e.employee_id WHERE l.loan_type = 'Home' AND l.current_principal_balance > (l.principal_amount * 0.75)"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.transactions ( transaction_id.text, account_id.text, related_account_id.text, transaction_type.text, amount.numeric, currency.text, transaction_date.timestamp, effective_date.date, description.text, status.text, reference_number.text )\nCREATE TABLE financial_services.securities ( security_id.text, ticker_symbol.text, isin_code.text, cusip_code.text, security_name.text, security_type.text, exchange.text, currency.text, issuer_name.text, sector.text, last_updated.timestamp )\nCREATE TABLE financial_services.market_data ( data_point_id.bigint, security_id.text, data_timestamp.timestamp, open_price.numeric, high_price.numeric, low_price.numeric, close_price.numeric, adjusted_close_price.numeric, volume.bigint, source.text )\nCREATE TABLE financial_services.employees ( employee_id.text, first_name.text, last_name.text, job_title.text, department.text, branch_id.text, email.text, phone_extension.text, hire_date.date, termination_date.date, manager_id.text, status.text )\nCREATE TABLE financial_services.loans ( loan_id.text, account_id.text, loan_type.text, principal_amount.numeric, current_principal_balance.numeric, interest_rate.numeric, term_months.integer, origination_date.date, maturity_date.date, monthly_payment.numeric, collateral_description.text, status.text )\n"}
{"conversations": [{"role": "user", "content": "List all pairs of vehicles in the same depot with different status. Include both vehicle IDs with their statuses and the depot_id."}, {"role": "assistant", "content": "SELECT v1.vehicle_id   AS vehicle1_id,\n       v1.status       AS status1,\n       v2.vehicle_id   AS vehicle2_id,\n       v2.status       AS status2,\n       v1.depot_id\nFROM transportation.vehicles v1\nJOIN transportation.vehicles v2\n  ON v1.depot_id = v2.depot_id\n AND v1.vehicle_id < v2.vehicle_id\n AND v1.status <> v2.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 transportation.vehicles ( vehicle_id.text, license_plate.text, vin.text, make.text, model.text, year.integer, type.text, capacity.integer, fuel_type.text, status.text, depot_id.text, acquisition_date.date )\n"}
{"conversations": [{"role": "user", "content": "For each user, find the previous user by registration time. List current user_id and username, previous user_id and username, and the time difference in minutes between their registrations."}, {"role": "assistant", "content": "SELECT u.user_id AS current_user_id,\n       u.username AS current_username,\n       p.user_id AS previous_user_id,\n       p.username AS previous_username,\n       EXTRACT(EPOCH FROM (u.created_at - p.created_at)) / 60 AS diff_minutes\nFROM web3.users u\nJOIN web3.users p\n  ON p.created_at = (\n    SELECT MAX(created_at)\n    FROM web3.users\n    WHERE created_at < u.created_at\n  )\nORDER BY u.created_at;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.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) )\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": "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": "Show the name and symbol for all assets in the system."}, {"role": "assistant", "content": "SELECT name, symbol FROM assets;"}, {"role": "user", "content": "Now, include any associated metadata key and value for each asset. If an asset has no metadata, it should still be listed."}, {"role": "assistant", "content": "SELECT T1.name, T1.symbol, T2.key, T2.value FROM assets AS T1 LEFT JOIN metadata AS T2 ON T1.asset_id = T2.asset_id;"}, {"role": "user", "content": "Filter the results to only show entries where the metadata key contains the word 'description' and the asset type is 'cryptocurrency'."}, {"role": "assistant", "content": "SELECT T1.name, T1.symbol, T2.key, T2.value FROM assets AS T1 LEFT JOIN metadata AS T2 ON T1.asset_id = T2.asset_id WHERE T2.key LIKE '%description%' AND T1.type = 'cryptocurrency';"}, {"role": "user", "content": "Sort the final list by asset name alphabetically."}, {"role": "assistant", "content": "SELECT T1.name, T1.symbol, T2.key, T2.value FROM assets AS T1 LEFT JOIN metadata AS T2 ON T1.asset_id = T2.asset_id WHERE T2.key LIKE '%description%' AND T1.type = 'cryptocurrency' ORDER BY T1.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.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, created_at timestamp )\nCREATE TABLE trading_platform.assets (\n    asset_id character varying(64) NOT NULL,  -- unique identifier for the asset\n    name character varying(128) NOT NULL, -- name of the asset\n    symbol character varying(32) NOT NULL, -- symbol of the asset\n    type character varying(32) NOT NULL, -- type of the asset (e.g., cryptocurrency, stock)\n    PRIMARY KEY (asset_id)\n)\nCREATE TABLE trading_platform.dapps ( 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": "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": "Show pairs of time entries for the same lawyer on the same date with different billing rates, including both entry IDs, the lawyer ID, the work date, and both billing rates."}, {"role": "assistant", "content": "SELECT a.entry_id AS entry1_id, b.entry_id AS entry2_id, a.lawyer_id, a.date_worked, a.billing_rate AS rate1, b.billing_rate AS rate2\nFROM legal_services.time_entries a\nJOIN legal_services.time_entries b\n  ON a.lawyer_id = b.lawyer_id\n  AND a.date_worked = b.date_worked\n  AND a.entry_id < b.entry_id\n  AND a.billing_rate <> b.billing_rate;"}, {"role": "user", "content": "Actually, I only want to include entries where both are billable."}, {"role": "assistant", "content": "SELECT a.entry_id AS entry1_id, b.entry_id AS entry2_id, a.lawyer_id, a.date_worked, a.billing_rate AS rate1, b.billing_rate AS rate2\nFROM legal_services.time_entries a\nJOIN legal_services.time_entries b\n  ON a.lawyer_id = b.lawyer_id\n  AND a.date_worked = b.date_worked\n  AND a.entry_id < b.entry_id\n  AND a.billing_rate <> b.billing_rate\nWHERE a.is_billable = true\n  AND b.is_billable = true;"}, {"role": "user", "content": "Also, sort the results by lawyer_id, then by date_worked, and then by the absolute difference in billing rates descending."}, {"role": "assistant", "content": "SELECT a.entry_id AS entry1_id, b.entry_id AS entry2_id, a.lawyer_id, a.date_worked, a.billing_rate AS rate1, b.billing_rate AS rate2\nFROM legal_services.time_entries a\nJOIN legal_services.time_entries b\n  ON a.lawyer_id = b.lawyer_id\n  AND a.date_worked = b.date_worked\n  AND a.entry_id < b.entry_id\n  AND a.billing_rate <> b.billing_rate\nWHERE a.is_billable = true\n  AND b.is_billable = true\nORDER BY a.lawyer_id, a.date_worked, ABS(a.billing_rate - b.billing_rate) 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 ( entry_id.text, case_id.text, lawyer_id.text, date_worked.date, hours_spent.numeric, billing_rate.numeric, description.text, is_billable.boolean, is_billed.boolean, invoice_id.text, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "For all chains, which token held by centralized exchanges (CEX) has the highest ROI according to smart money token performance? Show token symbol, chain, exchange, total USD value held on CEX, and the smart money ROI."}, {"role": "assistant", "content": "SELECT c.token_symbol, c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, s.roi\nFROM cex_token_balance c\nJOIN smart_money_token_performance s ON c.token_symbol = s.token_symbol AND c.chain = s.chain\nGROUP BY c.token_symbol, c.chain, c.exchange, s.roi\nORDER BY s.roi DESC\nLIMIT 1;"}, {"role": "user", "content": "Instead of just the top one, show the top 3 tokens by ROI, and only include cases where the total USD value held on CEX is greater than $2,000,000."}, {"role": "assistant", "content": "SELECT c.token_symbol, c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, s.roi\nFROM cex_token_balance c\nJOIN smart_money_token_performance s ON c.token_symbol = s.token_symbol AND c.chain = s.chain\nGROUP BY c.token_symbol, c.chain, c.exchange, s.roi\nHAVING SUM(c.usd_value) > 2000000\nORDER BY s.roi DESC\nLIMIT 3;"}, {"role": "user", "content": "Add the last recorded price for each token, and sort by total_usd_value in descending order."}, {"role": "assistant", "content": "SELECT c.token_symbol, c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, s.roi, MAX(c.price) AS last_price\nFROM cex_token_balance c\nJOIN smart_money_token_performance s ON c.token_symbol = s.token_symbol AND c.chain = s.chain\nGROUP BY c.token_symbol, c.chain, c.exchange, s.roi\nHAVING SUM(c.usd_value) > 2000000\nORDER BY total_usd_value DESC\nLIMIT 3;"}, {"role": "user", "content": "I got duplicate tokens across exchanges. Can you show only the top exchange (with the greatest USD value) per token and chain combination?"}, {"role": "assistant", "content": "WITH cex_totals AS (\n  SELECT c.token_symbol, c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, s.roi, MAX(c.price) AS last_price,\n         ROW_NUMBER() OVER (PARTITION BY c.token_symbol, c.chain ORDER BY SUM(c.usd_value) DESC) as rn\n  FROM cex_token_balance c\n  JOIN smart_money_token_performance s ON c.token_symbol = s.token_symbol AND c.chain = s.chain\n  GROUP BY c.token_symbol, c.chain, c.exchange, s.roi\n  HAVING SUM(c.usd_value) > 2000000\n)\nSELECT token_symbol, chain, exchange, total_usd_value, roi, last_price\nFROM cex_totals\nWHERE rn = 1\nORDER BY total_usd_value 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 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 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": "Show me all active managers along with their property IDs and the number of staff members they supervise, ordered by the number of supervised staff in descending order."}, {"role": "assistant", "content": "SELECT s.staff_id, s.property_id, s.first_name, s.last_name, COUNT(s2.staff_id) AS supervised_staff_count FROM hospitality_technology.staff s LEFT JOIN hospitality_technology.staff s2 ON s.staff_id = s2.manager_id WHERE s.position = 'Manager' AND s.is_active = true GROUP BY s.staff_id, s.property_id, s.first_name, s.last_name ORDER BY supervised_staff_count DESC;"}, {"role": "user", "content": "Now, include only managers who supervise at least 3 staff members and show their email addresses as well."}, {"role": "assistant", "content": "SELECT s.staff_id, s.property_id, s.first_name, s.last_name, s.work_email, COUNT(s2.staff_id) AS supervised_staff_count FROM hospitality_technology.staff s LEFT JOIN hospitality_technology.staff s2 ON s.staff_id = s2.manager_id WHERE s.position = 'Manager' AND s.is_active = true GROUP BY s.staff_id, s.property_id, s.first_name, s.last_name, s.work_email HAVING COUNT(s2.staff_id) >= 3 ORDER BY supervised_staff_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.staff (\n    staff_id character varying(64) NOT NULL,  -- unique identifier for the staff member\n    property_id character varying(64) NOT NULL, -- FK to properties table (primary property)\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    position character varying(100) NOT NULL, -- e.g., Front Desk Agent, Housekeeper, Manager, Concierge\n    work_email character varying(255) UNIQUE, -- staff member's work email\n    work_phone character varying(30),\n    hire_date date NOT NULL,\n    termination_date date, -- date employment ended (if applicable)\n    is_active boolean NOT NULL DEFAULT true, -- currently employed flag\n    access_level integer NOT NULL, -- permission level within systems (e.g., 1=basic, 5=admin)\n    manager_id character varying(64), -- FK to staff table (self-referencing for supervisor)\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (staff_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id)\n)\n"}
{"conversations": [{"role": "user", "content": "I want to know, for each conversation participant, how many unread messages they have. Return participant_id, conversation_id, and unread_count."}, {"role": "assistant", "content": "SELECT cp.participant_id,\n       cp.conversation_id,\n       COUNT(m.message_id) AS unread_count\nFROM social_media.conversation_participants cp\nJOIN social_media.messages m\n  ON m.conversation_id = cp.conversation_id\nWHERE m.sent_at > COALESCE(cp.last_read_at, '1970-01-01'::timestamp)\nGROUP BY cp.participant_id, cp.conversation_id;"}, {"role": "user", "content": "Can you filter the results to only include participants who joined the conversation before the earliest unread message was sent?"}, {"role": "assistant", "content": "SELECT cp.participant_id,\n       cp.conversation_id,\n       COUNT(m.message_id) AS unread_count\nFROM social_media.conversation_participants cp\nJOIN social_media.messages m\n  ON m.conversation_id = cp.conversation_id\nWHERE m.sent_at > COALESCE(cp.last_read_at, '1970-01-01'::timestamp)\nGROUP BY cp.participant_id, cp.conversation_id\nHAVING cp.joined_at < MIN(m.sent_at);"}, {"role": "user", "content": "Also, include the timestamp of the most recent unread message for each participant as last_unread_at."}, {"role": "assistant", "content": "SELECT cp.participant_id,\n       cp.conversation_id,\n       COUNT(m.message_id)   AS unread_count,\n       MAX(m.sent_at)        AS last_unread_at\nFROM social_media.conversation_participants cp\nJOIN social_media.messages m\n  ON m.conversation_id = cp.conversation_id\nWHERE m.sent_at > COALESCE(cp.last_read_at, '1970-01-01'::timestamp)\nGROUP BY cp.participant_id, cp.conversation_id\nHAVING cp.joined_at < MIN(m.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 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.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.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.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 post IDs and their corresponding hashtag names for posts that include media."}, {"role": "assistant", "content": "SELECT ph.post_id, h.tag_name\nFROM social_media.post_hashtags ph\nJOIN social_media.hashtags h ON ph.hashtag_id = h.hashtag_id\nJOIN social_media.posts p ON ph.post_id = p.post_id\nWHERE p.media_url IS NOT NULL AND p.media_url != '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.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 )\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 ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.post_hashtags (\n    post_hashtag_id character varying(64) NOT NULL, -- unique identifier for the post-hashtag link\n    post_id character varying(64) NOT NULL, -- identifier of the post (FK to posts.post_id)\n    hashtag_id character varying(64) NOT NULL, -- identifier of the hashtag (FK to hashtags.hashtag_id)\n    PRIMARY KEY (post_hashtag_id),\n    CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) -- prevent duplicate tags on a post\n)\nCREATE TABLE social_media.messages (\n    message_id character varying(64) NOT NULL, -- unique identifier for the message\n    conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n    sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n    content text, -- textual content of the message\n    media_url text, -- URL to attached media (image/video)\n    media_type character varying(20), -- type of media ('image', 'video', null)\n    sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n    read_at timestamp, -- timestamp when message was read by recipient(s)\n    PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversations ( conversation_id text PRIMARY KEY, created_at timestamp, last_message_at timestamp, is_group_chat bool, group_name text )\nCREATE TABLE social_media.conversation_participants (\n    participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n    conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n    user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n    joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n    last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n    PRIMARY KEY (participant_id),\n    CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications (\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 ( setting_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL UNIQUE, theme character varying(20) DEFAULT 'light', email_notifications_enabled boolean DEFAULT true, push_notifications_enabled boolean DEFAULT true, private_profile boolean DEFAULT false, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (setting_id) )\n"}
{"conversations": [{"role": "user", "content": "Show the IDs and registration dates of all verified citizens who could be eligible for at least one active service. Display the citizen ID and registration date."}, {"role": "assistant", "content": "SELECT DISTINCT c.citizen_id, c.registration_date\nFROM government_services.citizens c\nJOIN government_services.services s ON s.is_active = true\nWHERE c.is_verified = true;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id 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": "Show me the user ID, wallet ID, address ID, and the transaction ID for transactions where the sender address is linked to an address associated with a wallet."}, {"role": "assistant", "content": "SELECT DISTINCT w.user_id, w.wallet_id, w.address_id, t.transaction_id FROM blockchain.wallets w JOIN blockchain.transactions t ON w.address_id = t.sender_address;"}, {"role": "user", "content": "Filter this list to only include transactions with an amount greater than 1000."}, {"role": "assistant", "content": "SELECT DISTINCT w.user_id, w.wallet_id, w.address_id, t.transaction_id FROM blockchain.wallets w JOIN blockchain.transactions t ON w.address_id = t.sender_address WHERE t.amount > 1000;"}, {"role": "user", "content": "Actually, I also want to see the amount and the transaction timestamp, and filter for transactions that occurred in 2023."}, {"role": "assistant", "content": "SELECT DISTINCT w.user_id, w.wallet_id, w.address_id, t.transaction_id, t.amount, t.timestamp FROM blockchain.wallets w JOIN blockchain.transactions t ON w.address_id = t.sender_address WHERE t.amount > 1000 AND t.timestamp >= '2023-01-01' AND t.timestamp < '2024-01-01';"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE blockchain.blocks ( block_id text PRIMARY KEY, previous_block_id text, timestamp timestamp, nonce int, merkle_root text, difficulty int )\nCREATE TABLE blockchain.transactions ( transaction_id text PRIMARY KEY, block_id text, sender_address text, receiver_address text, amount numeric, timestamp timestamp, signature text )\nCREATE TABLE blockchain.nodes ( node_id text PRIMARY KEY, ip_address text, port int, last_seen timestamp )\nCREATE TABLE blockchain.wallets ( wallet_id text PRIMARY KEY, user_id text, address_id text, private_key text )\nCREATE TABLE blockchain.smart_contracts ( contract_id text PRIMARY KEY, creator_address text, code text, timestamp timestamp )\n"}
{"conversations": [{"role": "user", "content": "Count how many appointments have been canceled at each location. Return the location and cancelled_count."}, {"role": "assistant", "content": "SELECT location, COUNT(*) AS cancelled_count\nFROM legal_services.appointments\nWHERE status = 'Canceled'\nGROUP BY location;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text PRIMARY KEY, first_name text, last_name text, company_name text, email text UNIQUE, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.lawyers (\n    lawyer_id character varying(64) NOT NULL,  -- unique identifier for the lawyer\n    first_name character varying(100) NOT NULL, -- lawyer's first name\n    last_name character varying(100) NOT NULL, -- lawyer's last name\n    bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n    firm_id character varying(64), -- FK to law_firms table\n    email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n    phone character varying(32), -- lawyer's contact phone number\n    specialization text, -- areas of legal expertise\n    hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n    is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n    PRIMARY KEY (lawyer_id)\n)\nCREATE TABLE legal_services.time_entries (\n    entry_id character varying(64) NOT NULL,  -- unique identifier for the time entry\n    case_id character varying(64) NOT NULL, -- FK to cases table\n    lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (who performed the work)\n    date_worked date NOT NULL, -- date the work was performed\n    hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), -- duration of work in hours (e.g., 1.5 for 1h 30m)\n    billing_rate numeric(10, 2) NOT NULL, -- hourly rate applied for this entry\n    description text NOT NULL, -- detailed description of the work performed\n    is_billable boolean DEFAULT true, -- whether this time entry is billable to the client\n    is_billed boolean DEFAULT false, -- whether this entry has been included in an invoice\n    invoice_id character varying(64), -- FK to invoices table (once billed)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the entry was recorded\n    PRIMARY KEY (entry_id)\n)\nCREATE TABLE legal_services.invoices ( 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 (\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": "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": "Can you help me fetch the inventory details for components associated with a specific aircraft build, including the batch number, quantity, and warehouse location?"}, {"role": "assistant", "content": "MATCH (ab:AircraftBuild {build_id: 'specific_build_id'})-[:IS_MODEL]->(am:AircraftModel),\n(ib:InventoryBatch)-[:IS_INSTANCE_OF]->(c:Component)\nRETURN ib.inventory_record_id, ib.batch_number, ib.quantity, ib.location_warehouse"}, {"role": "user", "content": "Can you modify this to show only inventory batches received after a specific date, say June 1, 2023?"}, {"role": "assistant", "content": "MATCH (ab:AircraftBuild {build_id: 'specific_build_id'})-[:IS_MODEL]->(am:AircraftModel),\n(ib:InventoryBatch)-[:IS_INSTANCE_OF]->(c:Component)\nWHERE ib.received_date > datetime('2023-06-01')\nRETURN ib.inventory_record_id, ib.batch_number, ib.quantity, ib.location_warehouse"}, {"role": "user", "content": "What if I also want to exclude batches with quantities less than 10?"}, {"role": "assistant", "content": "MATCH (ab:AircraftBuild {build_id: 'specific_build_id'})-[:IS_MODEL]->(am:AircraftModel),\n(ib:InventoryBatch)-[:IS_INSTANCE_OF]->(c:Component)\nWHERE ib.received_date > datetime('2023-06-01') AND ib.quantity >= 10\nRETURN ib.inventory_record_id, ib.batch_number, ib.quantity, ib.location_warehouse"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nNode Label ':AircraftModel'. Properties: { model_id: String (Constraint: UNIQUE), model_name: String, manufacturer: String, passenger_capacity: Integer, max_range_km: Integer, engine_type: String, wingspan_m: Float, status: String, first_flight_date: Date }. Index on model_id.\nNode Label ':Material'. Properties: { material_id: String (Constraint: UNIQUE), material_name: String, specification: String, description: String, density_kg_m3: Float, tensile_strength_mpa: Integer }. Index on material_id.\nNode Label ':AssemblyLine'. Properties: { line_id: String (Constraint: UNIQUE), line_name: String, location_building: String, location_area: String, capacity_units_per_month: Integer, status: String }. Relationship: (:AssemblyLine)-[:BUILDS_MODEL]->(:AircraftModel {model_id}). Index on line_id.\nNode Label ':AssemblyStep'. Properties: { step_id: String (Constraint: UNIQUE), step_number: Integer, step_name: String, description: String, standard_duration_hours: Float, required_skill_level: String, workstation: String }. Relationship: (:AssemblyLine {line_id})-[:HAS_STEP {sequence: <step_number>}]->(:AssemblyStep). Index on step_id.\nNode Label ':AircraftBuild'. Properties: { build_id: String (Constraint: UNIQUE), serial_number: String (Constraint: UNIQUE), build_start_date: Datetime, estimated_completion_date: Date, actual_completion_date: Datetime, current_status: String, customer_order_id: String }. Relationships: (:AircraftBuild)-[:IS_MODEL]->(:AircraftModel {model_id}), (:AircraftBuild)-[:ASSEMBLED_ON]->(:AssemblyLine {line_id}). Index on build_id, serial_number, current_status.\nNode Label ':Employee'. Properties: { employee_id: String (Constraint: UNIQUE), first_name: String, last_name: String, job_title: String, skill_certifications: String[], hire_date: Date, employment_status: String }. Relationships: (:Employee)-[:ASSIGNED_TO]->(:AssemblyLine {line_id}), (:Employee)-[:REPORTS_TO]->(:Employee {employee_id as supervisor_id}). Index on employee_id.\nNode Label ':InventoryBatch'. Properties: { inventory_record_id: String (Constraint: UNIQUE), quantity: Integer, location_warehouse: String, location_bin: String, received_date: Datetime, expiry_date: Date, batch_number: String, last_updated: Datetime }. Relationship: (:InventoryBatch)-[:IS_INSTANCE_OF]->(:Component {component_id}). Index on inventory_record_id, component_id.\n"}
{"conversations": [{"role": "user", "content": "For each patient, find the next appointment after each one. Return patient_id, appointment_id, next_appointment_id, and the waiting time in minutes between them."}, {"role": "assistant", "content": "SELECT A.patient_id,\n       A.appointment_id AS current_id,\n       B.appointment_id AS next_id,\n       EXTRACT(EPOCH FROM (B.appointment_time - A.appointment_time)) / 60 AS wait_minutes\nFROM healthcare.appointments A\nJOIN healthcare.appointments B\n  ON A.patient_id = B.patient_id\n AND B.appointment_time = (\n       SELECT MIN(appointment_time)\n       FROM healthcare.appointments\n       WHERE patient_id = A.patient_id\n         AND appointment_time > A.appointment_time\n   );"}, {"role": "user", "content": "Now include only the pairs where the waiting time is less than 30 minutes."}, {"role": "assistant", "content": "SELECT A.patient_id,\n       A.appointment_id AS current_id,\n       B.appointment_id AS next_id,\n       EXTRACT(EPOCH FROM (B.appointment_time - A.appointment_time)) / 60 AS wait_minutes\nFROM healthcare.appointments A\nJOIN healthcare.appointments B\n  ON A.patient_id = B.patient_id\n AND B.appointment_time = (\n       SELECT MIN(appointment_time)\n       FROM healthcare.appointments\n       WHERE patient_id = A.patient_id\n         AND appointment_time > A.appointment_time\n   )\nWHERE EXTRACT(EPOCH FROM (B.appointment_time - A.appointment_time)) / 60 < 30;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.appointments ( appointment_id text PRIMARY KEY, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes int, reason text, status text, location_id text, notes text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 projects by valuation that completed fundraising rounds in the last 6 months, along with their narrative information if available."}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.rounds_name, pfr.valuation, pfr.investment_date, ni.narrative, ni.trend_rank\nFROM project_fundraising_record pfr\nLEFT JOIN narrative_info ni ON pfr.project_name = ni.narrative\nWHERE pfr.investment_date >= date_sub(now(), interval 6 month)\nORDER BY pfr.valuation DESC\nLIMIT 5;"}, {"role": "user", "content": "Can you filter these results to only include projects with valuation over $50 million and add their 24-hour trading volume from the narrative?"}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.rounds_name, pfr.valuation, ni.volume_24h\nFROM project_fundraising_record pfr\nLEFT JOIN narrative_info ni ON pfr.project_name = ni.narrative\nWHERE pfr.investment_date >= date_sub(now(), interval 6 month)\nAND pfr.valuation > 50000000\nORDER BY pfr.valuation 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 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 )\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 smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\n"}
{"conversations": [{"role": "user", "content": "Which service locations are not accessible and belong to agencies with a jurisdiction level of 'Local'? Show the location name and city."}, {"role": "assistant", "content": "SELECT sl.location_name, sl.city\nFROM government_services.service_locations sl\nINNER JOIN government_services.agencies a ON sl.agency_id = a.agency_id\nWHERE sl.is_accessible = FALSE\n  AND a.jurisdiction_level = 'Local';"}], "system": "You are an SQL statement expert. Given the table structure 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, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.documents ( document_id text, 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 pairs of properties located in the same city, showing each pair's property IDs and names along with the city."}, {"role": "assistant", "content": "SELECT p1.property_id AS property_id_1,\n       p1.property_name AS property_name_1,\n       p2.property_id AS property_id_2,\n       p2.property_name AS property_name_2,\n       p1.city\nFROM hospitality_technology.properties p1\nJOIN hospitality_technology.properties p2\n  ON p1.city = p2.city\n AND p1.property_id < p2.property_id;"}, {"role": "user", "content": "Only include pairs in cities that have more than two properties."}, {"role": "assistant", "content": "SELECT p1.property_id AS property_id_1,\n       p1.property_name AS property_name_1,\n       p2.property_id AS property_id_2,\n       p2.property_name AS property_name_2,\n       p1.city\nFROM hospitality_technology.properties p1\nJOIN hospitality_technology.properties p2\n  ON p1.city = p2.city\n AND p1.property_id < p2.property_id\nWHERE p1.city IN (\n  SELECT city\n  FROM hospitality_technology.properties\n  GROUP BY city\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.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) )\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": "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": "List all ERC20 tokens where the total supply is between 1 million and 10 million, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT ti.tick as name, ti.tick as symbol, tb.tick as contract_address FROM token_info ti JOIN token_balances tb ON ti.tick = tb.tick WHERE CAST(tb.total_supply AS decimal) BETWEEN 1000000 AND 10000000;"}, {"role": "user", "content": "I think there's an error in your query - it should be tb.total_supply not ti.total_supply. Also, can you add the current price of each token from the token_prices_latest table?"}, {"role": "assistant", "content": "SELECT ti.tick as name, ti.tick as symbol, tb.tick as contract_address, tpl.price FROM token_info ti JOIN token_balances tb ON ti.tick = tb.tick LEFT JOIN token_prices_latest tpl ON ti.tick = tpl.tick WHERE CAST(tb.total_supply AS decimal) BETWEEN 1000000 AND 10000000;"}, {"role": "user", "content": "Now sort these results by price in descending order and limit to the top 10."}, {"role": "assistant", "content": "SELECT ti.tick as name, ti.tick as symbol, tb.tick as contract_address, tpl.price FROM token_info ti JOIN token_balances tb ON ti.tick = tb.tick LEFT JOIN token_prices_latest tpl ON ti.tick = tpl.tick WHERE CAST(tb.total_supply AS decimal) BETWEEN 1000000 AND 10000000 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 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 nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_coins_metadata ( object_id.text, coin_type.text, status.text, decimals.bigint, description.text, icon_url.text, symbol.text, name.text )\nCREATE TABLE nft_metadata ( blockchain.text, contract_address.text, token_id.text, contract_name.text, erc_type.text, amount.bigint, minter.text, owner.text, mint_block_number.bigint, mint_time.bigint, mint_transaction_hash.text, mint_price.text, token_uri.text, metadata.text, name.text, image_uri.text, traits.text, updated_at.bigint, status.text, rarity_score.real, rarity_rank.integer, unique_attribute_count.integer, pk.integer )\nCREATE TABLE nft_collections ( blockchain.text, contract_address.text, name.text, symbol.text, deploy_block_number.bigint, deploy_block_time.bigint, erc_type.text, owner.text, traits.text, description.text, slug.text, media_info.text, image_url.text, banner_image_url.text, updated_at.bigint, banner.text, token_count.bigint, floor_price.text, floor_price_symbol.text, floor_price_contract.text, pk.integer )\nCREATE TABLE 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_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 users registered each month for 2024."}, {"role": "assistant", "content": "SELECT\n  date_trunc('month', created_at) AS month,\n  COUNT(*) AS user_count\nFROM trading_platform.users\nWHERE created_at >= '2024-01-01'\n  AND created_at < '2025-01-01'\nGROUP BY month\nORDER BY month;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all payments made by credit card, including the payment ID, guest ID, amount, status, and card last four digits. Order by payment amount descending."}, {"role": "assistant", "content": "SELECT payment_id, guest_id, amount, status, card_last_four\nFROM hospitality_technology.payments\nWHERE payment_method = 'CreditCard'\nORDER BY amount DESC;"}, {"role": "user", "content": "Can you limit the results to only the top 10 highest payments?"}, {"role": "assistant", "content": "SELECT payment_id, guest_id, amount, status, card_last_four\nFROM hospitality_technology.payments\nWHERE payment_method = 'CreditCard'\nORDER BY amount DESC\nLIMIT 10;"}, {"role": "user", "content": "Also, only show results where the status is 'Succeeded'."}, {"role": "assistant", "content": "SELECT payment_id, guest_id, amount, status, card_last_four\nFROM hospitality_technology.payments\nWHERE payment_method = 'CreditCard' AND status = 'Succeeded'\nORDER BY amount 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 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 )\n"}
{"conversations": [{"role": "user", "content": "List all unspent UTXOs, including their utxo_id, address, amount, and transaction_id."}, {"role": "assistant", "content": "SELECT utxo_id, address, amount, transaction_id \nFROM trading_platform.utxos \nWHERE spent = false;"}], "system": "You are an SQL statement expert. Given the table structure 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.trades ( trade_id text, 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, transaction_id text, output_index integer, address text, amount numeric, spent boolean )\nCREATE TABLE trading_platform.metadata ( metadata_id text, asset_id text, key text, value text )\nCREATE TABLE trading_platform.notifications ( notification_id text, user_id text, message text, sent_at timestamp, read_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List the product ID, name, and creation date for all insurance products created in 2024."}, {"role": "assistant", "content": "SELECT product_id, product_name, created_at\nFROM insurance.insurance_products\nWHERE created_at >= '2024-01-01' AND created_at < '2025-01-01';"}, {"role": "user", "content": "Actually, can you also include the product type and base premium in the results?"}, {"role": "assistant", "content": "SELECT product_id, product_name, product_type, base_premium, created_at\nFROM insurance.insurance_products\nWHERE created_at >= '2024-01-01' AND created_at < '2025-01-01';"}, {"role": "user", "content": "I only want to see those products with a base premium below 1000."}, {"role": "assistant", "content": "SELECT product_id, product_name, product_type, base_premium, created_at\nFROM insurance.insurance_products\nWHERE created_at >= '2024-01-01' AND created_at < '2025-01-01'\n  AND base_premium < 1000;"}, {"role": "user", "content": "Also, sort the result by product name in ascending order."}, {"role": "assistant", "content": "SELECT product_id, product_name, product_type, base_premium, created_at\nFROM insurance.insurance_products\nWHERE created_at >= '2024-01-01' AND created_at < '2025-01-01'\n  AND base_premium < 1000\nORDER BY product_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 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)\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 doctor, count how many diagnoses they have recorded in total. Display doctor ID and the total count."}, {"role": "assistant", "content": "SELECT doctor_id, COUNT(*) AS total_diagnoses FROM healthcare.diagnoses GROUP BY doctor_id;"}, {"role": "user", "content": "Modify the query to also show the number of unique patients they have diagnosed, and filter the results to only include doctors who have diagnosed more than 10 distinct patients."}, {"role": "assistant", "content": "SELECT doctor_id, COUNT(*) AS total_diagnoses, COUNT(DISTINCT patient_id) AS unique_patients FROM healthcare.diagnoses GROUP BY doctor_id HAVING COUNT(DISTINCT 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.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": "List all clients along with their case_number and case_type for cases that are currently 'Open'."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, c.email, cs.case_number, cs.case_type\nFROM legal_services.clients AS c\nJOIN legal_services.cases AS cs\n  ON c.client_id = cs.client_id\nWHERE cs.status = 'Open';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, company_name character varying(200), email character varying(128) UNIQUE NOT NULL, phone character varying(32), address text, date_registered timestamp NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (client_id) )\nCREATE TABLE legal_services.lawyers ( lawyer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, bar_number character varying(64) UNIQUE NOT NULL, firm_id character varying(64), email character varying(128) UNIQUE NOT NULL, phone character varying(32), specialization text, hire_date timestamp NOT NULL, is_partner boolean DEFAULT false, PRIMARY KEY (lawyer_id) )\nCREATE TABLE legal_services.law_firms ( firm_id character varying(64) NOT NULL, firm_name character varying(200) NOT NULL, address text NOT NULL, phone character varying(32), website character varying(255), founded_date date, managing_partner_id character varying(64), PRIMARY KEY (firm_id) )\nCREATE TABLE legal_services.cases ( case_id character varying(64) NOT NULL, case_number character varying(100) UNIQUE, case_name text NOT NULL, client_id character varying(64) NOT NULL, lead_lawyer_id character varying(64) NOT NULL, case_type character varying(100) NOT NULL, status character varying(50) NOT NULL, date_opened timestamp NOT NULL, date_closed timestamp, description text, court_jurisdiction character varying(128), PRIMARY KEY (case_id) )\nCREATE TABLE legal_services.documents ( document_id character varying(64) NOT NULL, case_id character varying(64) NOT NULL, document_name character varying(255) NOT NULL, document_type character varying(100), storage_path text NOT NULL, uploaded_by_lawyer_id character varying(64), upload_timestamp timestamp NOT NULL, version integer DEFAULT 1, description text, PRIMARY KEY (document_id) )\nCREATE TABLE legal_services.time_entries ( entry_id character varying(64) NOT NULL, case_id character varying(64) NOT NULL, lawyer_id character varying(64) NOT NULL, date_worked date NOT NULL, hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), billing_rate numeric(10, 2) NOT NULL, description text NOT NULL, is_billable boolean DEFAULT true, is_billed boolean DEFAULT false, invoice_id character varying(64), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (entry_id) )\nCREATE TABLE legal_services.appointments ( appointment_id character varying(64) NOT NULL, client_id character varying(64) NOT NULL, lawyer_id character varying(64) NOT NULL, case_id character varying(64), start_time timestamp NOT NULL, end_time timestamp NOT NULL, location text, subject character varying(255), notes text, status character varying(50) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (appointment_id) )\n"}
{"conversations": [{"role": "user", "content": "Show the route number and description for routes that have bookings associated with them."}, {"role": "assistant", "content": "SELECT DISTINCT T1.route_number, T1.description FROM transportation.routes AS T1 JOIN transportation.bookings AS T2 ON T1.route_id = T2.trip_id;"}, {"role": "user", "content": "For these routes, what is the average fare of the associated bookings?"}, {"role": "assistant", "content": "SELECT T1.route_number, AVG(T2.fare) FROM transportation.routes AS T1 JOIN transportation.bookings AS T2 ON T1.route_id = T2.trip_id GROUP BY T1.route_number;"}, {"role": "user", "content": "Also, only include routes where the average fare is greater than 75."}, {"role": "assistant", "content": "SELECT T1.route_number, AVG(T2.fare) FROM transportation.routes AS T1 JOIN transportation.bookings AS T2 ON T1.route_id = T2.trip_id GROUP BY T1.route_number HAVING AVG(T2.fare) > 75;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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, 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.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 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": "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": "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": "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": "Could you provide the total number of game sessions and the number of distinct players for each game genre? Display the genre, session count, and player count."}, {"role": "assistant", "content": "SELECT g.genre, COUNT(gs.session_id) AS session_count, COUNT(DISTINCT gs.player_id) AS player_count FROM gaming_technology.game_sessions AS gs JOIN gaming_technology.games AS g ON gs.game_id = g.game_id WHERE g.genre IS NOT NULL GROUP BY g.genre ORDER BY g.genre;"}, {"role": "user", "content": "Thanks. Can you modify the query to only include games that were released after the year 2020?"}, {"role": "assistant", "content": "SELECT g.genre, COUNT(gs.session_id) AS session_count, COUNT(DISTINCT gs.player_id) AS player_count FROM gaming_technology.game_sessions AS gs JOIN gaming_technology.games AS g ON gs.game_id = g.game_id WHERE g.genre IS NOT NULL AND g.release_date >= '2021-01-01' GROUP BY g.genre ORDER BY g.genre;"}], "system": "You are an SQL statement expert. Given the table structure 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)\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": "List properties and the average base rate of their room types."}, {"role": "assistant", "content": "SELECT T1.property_name ,  AVG(T2.base_rate) FROM hospitality_technology.properties AS T1 JOIN hospitality_technology.room_types AS T2 ON T1.property_id  =  T2.property_id GROUP BY T1.property_name"}, {"role": "user", "content": "Filter to only show properties where the average base rate is above 250."}, {"role": "assistant", "content": "SELECT T1.property_name ,  AVG(T2.base_rate) FROM hospitality_technology.properties AS T1 JOIN hospitality_technology.room_types AS T2 ON T1.property_id  =  T2.property_id GROUP BY T1.property_name HAVING AVG(T2.base_rate)  >  250"}, {"role": "user", "content": "Also, only include properties in 'New York' or 'Florida' and order by average base rate descending."}, {"role": "assistant", "content": "SELECT T1.property_name ,  AVG(T2.base_rate) AS avg_base_rate FROM hospitality_technology.properties AS T1 JOIN hospitality_technology.room_types AS T2 ON T1.property_id  =  T2.property_id WHERE T1.state IN ('New York', 'Florida') GROUP BY T1.property_name HAVING AVG(T2.base_rate)  >  250 ORDER BY avg_base_rate 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 (\n    room_type_id character varying(64) NOT NULL, -- unique identifier for the room type\n    property_id character varying(64) NOT NULL, -- FK to properties table (type might be property-specific)\n    type_name character varying(100) NOT NULL, -- e.g., Standard King, Deluxe Queen, Executive Suite\n    description text, -- description of the room type\n    base_rate numeric(10, 2) NOT NULL, -- standard price per night\n    max_occupancy integer NOT NULL, -- maximum number of guests\n    bed_type character varying(50), -- e.g., King, Queen, 2 Doubles, Twin\n    area_sqft numeric(8,2), -- size of the room in square feet\n    amenities text, -- comma-separated list or JSON of amenities\n    PRIMARY KEY (room_type_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show me the make and model of vehicles along with the route number and distance for all routes that are serviced by vehicles with a fuel_type of 'Electric'."}, {"role": "assistant", "content": "SELECT v.make, v.model, r.route_number, r.distance_km\nFROM transportation.vehicles v\nJOIN transportation.routes r ON v.vehicle_id = r.route_id\nWHERE v.fuel_type = 'Electric';"}, {"role": "user", "content": "Oops, I want to include the estimated duration for each route as well, and only show routes where the estimated duration is less than 90 minutes."}, {"role": "assistant", "content": "SELECT v.make, v.model, r.route_number, r.distance_km, r.estimated_duration_minutes\nFROM transportation.vehicles v\nJOIN transportation.routes r ON v.vehicle_id = r.route_id\nWHERE v.fuel_type = 'Electric' AND r.estimated_duration_minutes < 90;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text, license_plate text, vin text, make text, model text, year integer, type text, capacity integer, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers (\n    driver_id character varying(64) NOT NULL,  -- unique identifier for the driver\n    employee_id character varying(64) NOT NULL UNIQUE, -- employee reference number\n    first_name character varying(128) NOT NULL, -- driver's first name\n    last_name character varying(128) NOT NULL, -- driver's last name\n    license_number character varying(64) NOT NULL UNIQUE, -- driving license number\n    license_expiry_date date NOT NULL, -- expiry date of the license\n    contact_number character varying(32), -- phone number\n    email character varying(128) UNIQUE, -- email address\n    hire_date date NOT NULL, -- date the driver was hired\n    status character varying(32) NOT NULL, -- e.g., Active, On Leave, Terminated\n    PRIMARY KEY (driver_id)\n)\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.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id text, vehicle_id text, trip_id text, log_timestamp timestamp, fuel_type text, quantity numeric, unit text, cost_per_unit numeric, total_cost numeric, odometer_reading integer, location_id text )\n"}
{"conversations": [{"role": "user", "content": "Show me all wallet addresses and their private keys for users who have more than 3 wallets."}, {"role": "assistant", "content": "SELECT w.address_id, w.private_key FROM blockchain.wallets w WHERE w.user_id IN (SELECT user_id FROM blockchain.wallets GROUP BY user_id HAVING COUNT(*) > 3);"}, {"role": "user", "content": "Now, filter these results to only show wallets where the private_key starts with '0x1'."}, {"role": "assistant", "content": "SELECT w.address_id, w.private_key FROM blockchain.wallets w WHERE w.user_id IN (SELECT user_id FROM blockchain.wallets GROUP BY user_id HAVING COUNT(*) > 3) AND w.private_key LIKE '0x1%';"}], "system": "You are an SQL statement expert. Given the table structure 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 (\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_id character varying(128) NOT NULL, -- identifier of the address associated with the wallet\n    private_key text NOT NULL, -- private key of the wallet\n    PRIMARY KEY (wallet_id)\n)\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": "List all agencies that do not have a website URL specified. Return their agency_id, agency_name, and main_phone_number."}, {"role": "assistant", "content": "SELECT agency_id, agency_name, main_phone_number FROM government_services.agencies WHERE website_url IS NULL OR website_url = '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\n"}
{"conversations": [{"role": "user", "content": "List 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": "Find all pairs of transactions that occurred in the same block and were sent to the same address. Show both transaction IDs, the shared recipient address, and the block number."}, {"role": "assistant", "content": "SELECT t1.transaction_id AS tx1,\n       t2.transaction_id AS tx2,\n       t1.to_address,\n       t1.block_number\nFROM transactions t1\nJOIN transactions t2\n  ON t1.to_address = t2.to_address\n AND t1.block_number = t2.block_number\n AND t1.transaction_id < t2.transaction_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.transactions ( transaction_id text, from_address text, to_address text, value numeric, gas_used integer, gas_price numeric, block_number integer, timestamp timestamp, input_data text, status text, nonce integer )\n"}
{"conversations": [{"role": "user", "content": "Show 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": "Find any two claims made by the same customer on the same day. Return customer_id, the two claim IDs, and the incident date."}, {"role": "assistant", "content": "SELECT c1.customer_id,\n       c1.claim_id AS claim1_id,\n       c2.claim_id AS claim2_id,\n       DATE(c1.incident_date) AS incident_date\nFROM insurance.claims c1\nJOIN insurance.claims c2\n  ON c1.customer_id = c2.customer_id\n AND DATE(c1.incident_date) = DATE(c2.incident_date)\n AND c1.claim_id < c2.claim_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims ( claim_id text, policy_id text, customer_id text, incident_date timestamp, reported_date timestamp, description text, estimated_loss numeric, status text, settlement_amount numeric, settlement_date date, claim_handler_id text, police_report_number text )\n"}
{"conversations": [{"role": "user", "content": "Retrieve the product_id, product_name, base_premium, and created_at for all active insurance products with a base_premium greater than 1000, ordered by base_premium descending."}, {"role": "assistant", "content": "SELECT\n  product_id,\n  product_name,\n  base_premium,\n  created_at\nFROM insurance.insurance_products\nWHERE is_active = true\n  AND base_premium > 1000\nORDER BY base_premium DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.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)\n"}
{"conversations": [{"role": "user", "content": "Show me all patients who have a primary insurance plan from 'Blue Cross', along with their insurance policy numbers and the plan types."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name, p.last_name, pi.policy_number, ip.plan_type FROM healthcare.patients p JOIN healthcare.patient_insurance pi ON p.patient_id = pi.patient_id JOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id WHERE ip.insurance_provider = 'Blue Cross' AND pi.is_primary = 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 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.medical_records ( record_id text PRIMARY KEY, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.insurance_plans (\n    plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n    plan_name character varying(200) NOT NULL, -- name of the insurance plan\n    insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n    plan_type character varying(50), -- e.g., PPO, HMO, EPO\n    contact_phone character varying(20), -- provider contact number\n    website character varying(255), -- provider website\n    PRIMARY KEY (plan_id)\n)\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n"}
{"conversations": [{"role": "user", "content": "List each lawyer's full name with the full name of the partner at the same firm."}, {"role": "assistant", "content": "SELECT l.lawyer_id,\n       CONCAT(l.first_name, ' ', l.last_name) AS lawyer_name,\n       CONCAT(p.first_name, ' ', p.last_name) AS partner_name\nFROM legal_services.lawyers l\nJOIN legal_services.lawyers p\n  ON l.firm_id = p.firm_id\n AND p.is_partner = true;"}, {"role": "user", "content": "Actually, I only want those lawyers whose specialization includes 'Corporate Law'. Could you update the query?"}, {"role": "assistant", "content": "SELECT l.lawyer_id,\n       CONCAT(l.first_name, ' ', l.last_name) AS lawyer_name,\n       CONCAT(p.first_name, ' ', p.last_name) AS partner_name\nFROM legal_services.lawyers l\nJOIN legal_services.lawyers p\n  ON l.firm_id = p.firm_id\n AND p.is_partner = true\nWHERE l.specialization ILIKE '%Corporate Law%';"}, {"role": "user", "content": "Also only show those who were hired after 2020-01-01."}, {"role": "assistant", "content": "SELECT l.lawyer_id,\n       CONCAT(l.first_name, ' ', l.last_name) AS lawyer_name,\n       CONCAT(p.first_name, ' ', p.last_name) AS partner_name\nFROM legal_services.lawyers l\nJOIN legal_services.lawyers p\n  ON l.firm_id = p.firm_id\n AND p.is_partner = true\nWHERE l.specialization ILIKE '%Corporate Law%'\n  AND l.hire_date > '2020-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers (\n    lawyer_id character varying(64) NOT NULL,  -- unique identifier for the lawyer\n    first_name character varying(100) NOT NULL, -- lawyer's first name\n    last_name character varying(100) NOT NULL, -- lawyer's last name\n    bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n    firm_id character varying(64), -- FK to law_firms table\n    email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n    phone character varying(32), -- lawyer's contact phone number\n    specialization text, -- areas of legal expertise\n    hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n    is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n    PRIMARY KEY (lawyer_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all ERC20 tokens where the price is between $1 and $10, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT t.name, t.symbol, t.address FROM token_prices_latest t WHERE t.price BETWEEN 1 AND 10;"}, {"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, tpl.address, tpl.price FROM token_prices_latest tpl JOIN sui_coins_metadata scm ON tpl.address = scm.coin_type 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, tpl.address, tpl.price FROM token_prices_latest tpl JOIN sui_coins_metadata scm ON tpl.address = scm.coin_type 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 ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text )\nCREATE TABLE erc20_balances_historical ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.integer )\nCREATE TABLE nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE 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 token_prices ( uuid.text, blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE token_prices_latest ( blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE erc20_approval ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text, pk.integer )\nCREATE TABLE token_balances ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.decimal, amount.decimal )\nCREATE TABLE token_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 ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.text, amount.text )\nCREATE TABLE token_info_bitcoin ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_avalanche ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.decimal, amount.decimal )\n"}
{"conversations": [{"role": "user", "content": "For each private conversation (is_group_chat = false), list the conversation_id and the usernames of its two participants."}, {"role": "assistant", "content": "SELECT c.conversation_id,\n       u1.username AS participant_one,\n       u2.username AS participant_two\nFROM social_media.conversations c\nJOIN social_media.conversation_participants cp1 ON c.conversation_id = cp1.conversation_id\nJOIN social_media.conversation_participants cp2 ON c.conversation_id = cp2.conversation_id AND cp2.user_id <> cp1.user_id\nJOIN social_media.users u1 ON cp1.user_id = u1.user_id\nJOIN social_media.users u2 ON cp2.user_id = u2.user_id\nWHERE c.is_group_chat = false\n  AND cp1.user_id < cp2.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 social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.comments ( comment_id text, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id text, tag_name text, created_at timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text, post_id text, hashtag_id text )\nCREATE TABLE social_media.messages ( message_id text, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id text, created_at timestamp, last_message_at timestamp, is_group_chat boolean, group_name text )\nCREATE TABLE social_media.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications ( notification_id text, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\nCREATE TABLE social_media.user_settings ( setting_id text, user_id text, theme text, email_notifications_enabled boolean, push_notifications_enabled boolean, private_profile boolean, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "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": "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": "Show each agency's name, jurisdiction level, and the count of its active services in the 'Healthcare' category."}, {"role": "assistant", "content": "SELECT a.agency_name, a.jurisdiction_level, COUNT(s.service_id) AS active_healthcare_services\nFROM government_services.agencies a\nJOIN government_services.services s ON a.agency_id = s.agency_id\nWHERE s.is_active = TRUE\n  AND s.category = 'Healthcare'\nGROUP BY a.agency_name, a.jurisdiction_level;"}], "system": "You are an SQL statement expert. Given the table structure 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, 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, 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.applications ( application_id.text, citizen_id.text, service_id.text, submitted_at.timestamp, status.text, last_updated_at.timestamp, assigned_employee_id.text, decision_date.date, notes.text, reference_number.text )\nCREATE TABLE government_services.payments ( payment_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, service_id character varying(64), amount numeric(12, 2) NOT NULL, currency character varying(3) NOT NULL DEFAULT 'USD', payment_method character varying(50), payment_provider_reference character varying(128), payment_timestamp timestamp NOT NULL, status character varying(30) NOT NULL, notes text, PRIMARY KEY (payment_id) )\nCREATE TABLE government_services.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": "I want to see, for each guest, the total number of payments they have made and the timestamp of their latest payment."}, {"role": "assistant", "content": "SELECT p.guest_id,\n       COUNT(p.payment_id) AS payment_count,\n       t.last_ts\nFROM hospitality_technology.payments p\nJOIN (\n    SELECT guest_id,\n           MAX(payment_timestamp) AS last_ts\n    FROM hospitality_technology.payments\n    GROUP BY guest_id\n) t ON p.guest_id = t.guest_id\nGROUP BY p.guest_id, t.last_ts;"}, {"role": "user", "content": "Only include guests whose latest payment status was 'Succeeded' and who have made at least 5 successful payments."}, {"role": "assistant", "content": "SELECT p.guest_id,\n       COUNT(p.payment_id) AS payment_count,\n       t.last_ts\nFROM hospitality_technology.payments p\nJOIN (\n    SELECT guest_id,\n           MAX(payment_timestamp) AS last_ts,\n           COUNT(*) AS cnt\n    FROM hospitality_technology.payments\n    WHERE status = 'Succeeded'\n    GROUP BY guest_id\n    HAVING COUNT(*) >= 5\n) t ON p.guest_id = t.guest_id\nGROUP BY p.guest_id, t.last_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 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) )\n"}
{"conversations": [{"role": "user", "content": "List all reservations that have a total_amount greater than the amount_paid. Include the reservation_id, guest_id, total_amount, and amount_paid."}, {"role": "assistant", "content": "SELECT reservation_id, guest_id, total_amount, amount_paid\nFROM hospitality_technology.reservations\nWHERE total_amount > amount_paid;"}, {"role": "user", "content": "Can you also show the check_in_date and check_out_date for each of those reservations?"}, {"role": "assistant", "content": "SELECT reservation_id, guest_id, total_amount, amount_paid, check_in_date, check_out_date\nFROM hospitality_technology.reservations\nWHERE total_amount > amount_paid;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.reservations ( reservation_id text PRIMARY KEY, property_id text, guest_id text, room_id text, room_type_id text, check_in_date date, check_out_date date, actual_check_in_ts timestamp, actual_check_out_ts timestamp, num_adults int, num_children int, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\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 )\n"}
{"conversations": [{"role": "user", "content": "How many users registered in each month?"}, {"role": "assistant", "content": "SELECT date_trunc('month', created_at) AS month,\n       COUNT(*) AS registrations\nFROM web3.users\nGROUP BY month\nORDER BY month;"}, {"role": "user", "content": "Actually, show only those months where registrations exceed 10."}, {"role": "assistant", "content": "SELECT date_trunc('month', created_at) AS month,\n       COUNT(*) AS registrations\nFROM web3.users\nGROUP BY month\nHAVING COUNT(*) > 10\nORDER BY month;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.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) )\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 all bookings with a status of 'confirmed' that were made in the last 7 days, including passenger_id and fare."}, {"role": "assistant", "content": "SELECT booking_id, passenger_id, fare FROM transportation.bookings WHERE status = 'confirmed' AND booking_time >= CURRENT_DATE - INTERVAL '7 days';"}, {"role": "user", "content": "Now include only bookings where the fare is greater than $50 and order them by booking_time in descending order."}, {"role": "assistant", "content": "SELECT booking_id, passenger_id, fare FROM transportation.bookings WHERE status = 'confirmed' AND booking_time >= CURRENT_DATE - INTERVAL '7 days' AND fare > 50 ORDER BY booking_time DESC;"}, {"role": "user", "content": "Can you also include the trip_id and filter to only show bookings for trip_id 'TRIP789'?"}, {"role": "assistant", "content": "SELECT booking_id, passenger_id, fare, trip_id FROM transportation.bookings WHERE status = 'confirmed' AND booking_time >= CURRENT_DATE - INTERVAL '7 days' AND fare > 50 AND trip_id = 'TRIP789' ORDER BY booking_time DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.bookings ( booking_id text PRIMARY KEY, passenger_id text, trip_id text, seat_number text, booking_time timestamp, status text, fare numeric, payment_transaction_id text, special_requests text )\n"}
{"conversations": [{"role": "user", "content": "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": "For each loyalty_program_id, how many unique passengers are enrolled and what is the average fare they have paid?"}, {"role": "assistant", "content": "SELECT\n  p.loyalty_program_id,\n  COUNT(DISTINCT p.passenger_id) AS passenger_count,\n  AVG(b.fare) AS avg_fare\nFROM transportation.passengers p\nJOIN transportation.bookings b\n  ON p.passenger_id = b.passenger_id\nGROUP BY p.loyalty_program_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 )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.passengers ( passenger_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, loyalty_program_id.text, created_at.timestamp )\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"}
{"conversations": [{"role": "user", "content": "List each booking with its previous booking time for the same passenger."}, {"role": "assistant", "content": "SELECT b.booking_id,\n       b.passenger_id,\n       b.booking_time,\n       LAG(b.booking_time) OVER (PARTITION BY b.passenger_id ORDER BY b.booking_time) AS previous_booking_time\nFROM transportation.bookings b;"}, {"role": "user", "content": "I only want records where the gap between bookings is more than 7 days."}, {"role": "assistant", "content": "SELECT booking_id,\n       passenger_id,\n       booking_time,\n       previous_booking_time\nFROM (\n  SELECT booking_id,\n         passenger_id,\n         booking_time,\n         LAG(booking_time) OVER (PARTITION BY passenger_id ORDER BY booking_time) AS previous_booking_time\n  FROM transportation.bookings\n) t\nWHERE previous_booking_time IS NOT NULL\n  AND booking_time - previous_booking_time > INTERVAL '7 days';"}, {"role": "user", "content": "Also include the total number of bookings for each passenger."}, {"role": "assistant", "content": "SELECT booking_id,\n       passenger_id,\n       booking_time,\n       previous_booking_time,\n       COUNT(*) OVER (PARTITION BY passenger_id) AS total_bookings\nFROM (\n  SELECT booking_id,\n         passenger_id,\n         booking_time,\n         LAG(booking_time) OVER (PARTITION BY passenger_id ORDER BY booking_time) AS previous_booking_time\n  FROM transportation.bookings\n) t\nWHERE previous_booking_time IS NOT NULL\n  AND booking_time - previous_booking_time > INTERVAL '7 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.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 each user, show their user_id, KYC status, and the total count of completed orders they've placed."}, {"role": "assistant", "content": "SELECT k.user_id, k.status, COUNT(o.order_id) AS completed_order_count\nFROM trading_platform.kyc_audit k\nJOIN trading_platform.orders o\n  ON k.user_id = o.user_id\n  AND o.status = 'completed'\nGROUP BY k.user_id, k.status;"}, {"role": "user", "content": "Only include users whose KYC status is 'approved'."}, {"role": "assistant", "content": "SELECT k.user_id, k.status, COUNT(o.order_id) AS completed_order_count\nFROM trading_platform.kyc_audit k\nJOIN trading_platform.orders o\n  ON k.user_id = o.user_id\n  AND o.status = 'completed'\nWHERE k.status = 'approved'\nGROUP BY k.user_id, k.status;"}, {"role": "user", "content": "Also calculate the total value of these completed orders as total_value."}, {"role": "assistant", "content": "SELECT k.user_id,\n       k.status,\n       COUNT(o.order_id) AS completed_order_count,\n       SUM(o.quantity * o.price) AS total_value\nFROM trading_platform.kyc_audit k\nJOIN trading_platform.orders o\n  ON k.user_id = o.user_id\n  AND o.status = 'completed'\nWHERE k.status = 'approved'\nGROUP BY k.user_id, k.status;"}, {"role": "user", "content": "Finally, order the results by total_value descending and limit to 5."}, {"role": "assistant", "content": "SELECT k.user_id,\n       k.status,\n       COUNT(o.order_id) AS completed_order_count,\n       SUM(o.quantity * o.price) AS total_value\nFROM trading_platform.kyc_audit k\nJOIN trading_platform.orders o\n  ON k.user_id = o.user_id\n  AND o.status = 'completed'\nWHERE k.status = 'approved'\nGROUP BY k.user_id, k.status\nORDER BY total_value 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.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.utxos ( utxo_id text PRIMARY KEY, transaction_id text, output_index int, address text, amount numeric, spent boolean )\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.logs ( log_id character varying(64) NOT NULL, user_id character varying(64), action character varying(128) NOT NULL, details text NOT NULL, logged_at timestamp NOT NULL, PRIMARY KEY (log_id) )\nCREATE TABLE trading_platform.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Find all ERC20 tokens with a total supply greater than 1 billion, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT name, symbol, contract_address FROM token_metas WHERE is_erc20 = 1 AND CAST(total_supply AS decimal) > 1000000000;"}, {"role": "user", "content": "Now join this with the token_prices_latest table to include the current price of each token."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND CAST(tm.total_supply AS decimal) > 1000000000;"}, {"role": "user", "content": "I think there's an error in your query - it should be 'tm.contract_address = tpl.address' not 'tm.contract_address = tpl.address'. Also, can you sort the results by price in descending order?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND CAST(tm.total_supply AS decimal) > 1000000000 ORDER BY tpl.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 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 erc20_balances (\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 varchar NOT NULL  -- The last string partition of the contract.\n)\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk text )\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_coins ( object_id.text, status.text, coin_type.text, balance.text, owner.text )\nCREATE TABLE nft_collections (\n    blockchain varchar NOT NULL, -- blockchain fields for the functionType  in contract\n    contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n    name varchar NOT NULL, -- name fields for the functionType  in contract\n    symbol varchar NOT NULL, -- symbol fields for the functionType  in contract\n    deploy_block_number bigint NOT NULL, -- deploy_block_number fields for the functionType  in contract\n    deploy_block_time bigint NOT NULL, -- deploy_block_time fields for the functionType  in contract\n    erc_type varchar NOT NULL, -- The type of token\n    owner varchar NOT NULL, -- owner fields for the functionType  in contract\n    traits varchar NOT NULL, -- traits fields for the functionType  in contract\n    description varchar NOT NULL, -- description fields for the functionType  in contract\n    slug varchar NOT NULL, -- slug fields for the functionType  in contract\n    media_info varchar NOT NULL, -- media_info fields for the functionType  in contract\n    image_url varchar NOT NULL, -- image_url fields for the functionType  in contract\n    banner_image_url varchar NOT NULL, -- banner_image_url fields for the functionType  in contract\n    updated_at bigint NOT NULL, -- updated_at fields for the functionType  in contract\n    banner varchar NOT NULL, -- banner fields for the functionType  in contract\n    token_count bigint NOT NULL, -- token_count fields for the functionType  in contract\n    floor_price varchar NOT NULL, -- floor_price fields for the functionType  in contract\n    floor_price_symbol varchar NOT NULL, -- floor_price_symbol fields for the functionType  in contract\n    floor_price_contract varchar NOT NULL, -- floor_price_contract fields for the functionType  in contract\n    pk integer NOT NULL  -- Partition key for the table(floor(deploy_block_time / 1000 / 86400 / 30))\n)\nCREATE TABLE token_prices (\n    uuid varchar(36) NOT NULL, -- uuid fields for the functionType  in contract\n    blockchain varchar(36) NOT NULL, -- blockchain fields for the functionType  in contract\n    address varchar(42) NOT NULL, -- address fields for the functionType  in contract\n    decimals bigint NOT NULL, -- decimals fields for the functionType  in contract\n    symbol varchar(36) NOT NULL, -- symbol fields for the functionType  in contract\n    price real NOT NULL, -- price fields for the functionType  in contract\n    timestamp timestamp(6) NOT NULL  -- timestamp fields for the functionType  in contract\n)\nCREATE TABLE 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 )\n"}
{"conversations": [{"role": "user", "content": "Show me all claims handled by agents who were hired in the last 3 years, along with the agent's full name and agency."}, {"role": "assistant", "content": "SELECT c.claim_id, c.policy_id, c.incident_date, c.status, CONCAT(a.first_name, ' ', a.last_name) AS agent_name, a.agency_name FROM insurance.claims c JOIN insurance.agents a ON c.claim_handler_id = a.agent_id WHERE a.hire_date >= CURRENT_DATE - INTERVAL '3 years';"}, {"role": "user", "content": "Now filter this to only show claims that were settled for more than $10,000."}, {"role": "assistant", "content": "SELECT c.claim_id, c.policy_id, c.incident_date, c.status, c.settlement_amount, CONCAT(a.first_name, ' ', a.last_name) AS agent_name, a.agency_name FROM insurance.claims c JOIN insurance.agents a ON c.claim_handler_id = a.agent_id WHERE a.hire_date >= CURRENT_DATE - INTERVAL '3 years' AND c.settlement_amount > 10000;"}, {"role": "user", "content": "I also want to see how long it took to settle these claims (difference between reported_date and settlement_date)."}, {"role": "assistant", "content": "SELECT c.claim_id, c.policy_id, c.incident_date, c.status, c.settlement_amount, (c.settlement_date - c.reported_date) AS days_to_settle, CONCAT(a.first_name, ' ', a.last_name) AS agent_name, a.agency_name FROM insurance.claims c JOIN insurance.agents a ON c.claim_handler_id = a.agent_id WHERE a.hire_date >= CURRENT_DATE - INTERVAL '3 years' AND c.settlement_amount > 10000;"}, {"role": "user", "content": "Now order the results by the longest settlement time first."}, {"role": "assistant", "content": "SELECT c.claim_id, c.policy_id, c.incident_date, c.status, c.settlement_amount, (c.settlement_date - c.reported_date) AS days_to_settle, CONCAT(a.first_name, ' ', a.last_name) AS agent_name, a.agency_name FROM insurance.claims c JOIN insurance.agents a ON c.claim_handler_id = a.agent_id WHERE a.hire_date >= CURRENT_DATE - INTERVAL '3 years' AND c.settlement_amount > 10000 ORDER BY days_to_settle DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims ( claim_id 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.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": "I need to find all bookings for a specific schedule with schedule_id 'sched_1122' and include the passenger and ticket details."}, {"role": "assistant", "content": "SMEMBERS schedule:sched_1122:bookings\nHGETALL booking:book_*\nHGETALL passenger:pass_*\nSMEMBERS booking:book_*:tickets\nHGETALL ticket:tkt_*"}, {"role": "user", "content": "Can you filter the tickets to show only those that are not checked in?"}, {"role": "assistant", "content": "SMEMBERS schedule:sched_1122:bookings\nHGETALL booking:book_*\nHGETALL passenger:pass_*\nSMEMBERS booking:book_*:tickets\nHGET ticket:tkt_* is_checked_in\nIF is_checked_in == 0 THEN\nHGETALL ticket:tkt_*\nENDIF"}, {"role": "user", "content": "Can you also include the car details for each ticket?"}, {"role": "assistant", "content": "SMEMBERS schedule:sched_1122:bookings\nHGETALL booking:book_*\nHGETALL passenger:pass_*\nSMEMBERS booking:book_*:tickets\nHGET ticket:tkt_* is_checked_in\nIF is_checked_in == 0 THEN\nHGETALL ticket:tkt_*\nHGET ticket:tkt_* car_id\nHGETALL car:car_*\nENDIF"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// Use Hashes for platform details. Key format: platform:<platform_id>\n// HSET platform:plat_123 platform_id \"plat_123\" station_id \"station_xyz\" platform_number \"1A\" track_number \"T1\" status \"Operational\" length_meters 250.50 accessible 1\n\n// To link platforms to stations (optional):\n// SADD station:station_xyz:platforms platform:plat_123 platform:plat_456\n// Use Hashes for train details. Key format: train:<train_id>\n// HSET train:train_789 train_id \"train_789\" train_number \"Acela 2151\" model \"Siemens Velaro\" ... status \"Active\" ...\n\n// To find train by train_number (optional index):\n// SET train_number:\"Acela 2151\" train:train_789\n// Use Hashes for car details. Key format: car:<car_id>\n// HSET car:car_abc car_id \"car_abc\" train_id \"train_789\" car_number \"C3\" car_type \"Passenger\" class \"Business\" capacity 60 features \"WiFi,Power Outlet\"\n\n// To link cars to trains (optional):\n// SADD train:train_789:cars car:car_abc car:car_def\n// Use Hashes for details. Key format: route_station:<route_station_id>\n// HSET route_station:rs_ne_1 route_station_id \"rs_ne_1\" route_id \"route_ne_corr\" station_id \"station_bos\" sequence_order 1 ...\n\n// To find stops for a route, use a Sorted Set (score by sequence_order):\n// ZADD route:route_ne_corr:stops 1 route_station:rs_ne_1\n// ZADD route:route_ne_corr:stops 2 route_station:rs_ne_2\n// Use Hashes for schedule details. Key format: schedule:<schedule_id>\n// HSET schedule:sched_1122 schedule_id \"sched_1122\" train_id \"train_789\" route_id \"route_ne_corr\" departure_datetime \"2024-05-10T08:00:00-04:00\" ... status \"Scheduled\"\n// Use Hashes for details. Key format: schedule_stop:<stop_id>\n// HSET schedule_stop:stop_sched1122_1 stop_id \"stop_sched1122_1\" schedule_id \"sched_1122\" station_id \"station_bos\" ...\n\n// To find stops for a schedule, use a Sorted Set (score by sequence_order):\n// ZADD schedule:sched_1122:stops 1 schedule_stop:stop_sched1122_1\n// ZADD schedule:sched_1122:stops 2 schedule_stop:stop_sched1122_2\n// Use Hashes for passenger details. Key format: passenger:<passenger_id>\n// HSET passenger:pass_pqr passenger_id \"pass_pqr\" first_name \"Alice\" last_name \"Smith\" email \"alice.smith@example.com\" ...\n\n// To find passenger by email (optional index):\n// SET passenger_email:\"alice.smith@example.com\" passenger:pass_pqr\n// Use Hashes for booking details. Key format: booking:<booking_id>\n// HSET booking:book_zyx booking_id \"book_zyx\" passenger_id \"pass_pqr\" schedule_id \"sched_1122\" ... status \"Confirmed\" ...\n\n// To link bookings to passengers/schedules (optional):\n// SADD passenger:pass_pqr:bookings booking:book_zyx\n// SADD schedule:sched_1122:bookings booking:book_zyx\n// Use Hashes for ticket details. Key format: ticket:<ticket_id>\n// HSET ticket:tkt_1a2b ticket_id \"tkt_1a2b\" booking_id \"book_zyx\" car_id \"car_abc\" seat_number \"12A\" ... is_checked_in 0 ...\n\n// To link tickets to bookings (optional):\n// SADD booking:book_zyx:tickets ticket:tkt_1a2b\n// Use Hashes for staff details. Key format: staff:<staff_id>\n// HSET staff:staff_mno staff_id \"staff_mno\" first_name \"Bob\" ... employee_number \"E12345\" ... is_active 1\n\n// To find staff by employee number (optional index):\n// SET staff_employee_number:\"E12345\" staff:staff_mno\n// Use Hashes for maintenance record details. Key format: maintenance_record:<record_id>\n// HSET maintenance_record:maint_rec_001 record_id \"maint_rec_001\" asset_id \"train_789\" asset_type \"Train\" ... status \"Completed\"\n\n// To link records to assets (optional):\n// SADD train:train_789:maintenance maintenance_record:maint_rec_001\n// SADD platform:plat_123:maintenance maintenance_record:maint_rec_002\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": "Show the first name, last name, and email of customers who have filed a claim, along with the status and estimated loss of each claim."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T1.email, T2.status, T2.estimated_loss FROM insurance.customers AS T1 INNER JOIN insurance.claims AS T2 ON T1.customer_id = T2.customer_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 character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\nCREATE TABLE insurance.insurance_products ( product_id.text, product_name.text, product_type.text, description.text, base_premium.numeric, coverage_details.text, underwriting_rules.text, is_active.boolean, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE insurance.agents ( agent_id.text, first_name.text, last_name.text, agency_name.text, license_number.text, license_state.text, contact_email.text, contact_phone.text, hire_date.date, termination_date.date, status.text, commission_rate.numeric, manager_id.text )\nCREATE TABLE insurance.premium_payments ( payment_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, amount_paid numeric(12, 2) NOT NULL, payment_method character varying(50), transaction_reference character varying(128) UNIQUE, due_date date, payment_period_start date, payment_period_end date, status character varying(30) NOT NULL DEFAULT 'Completed', PRIMARY KEY (payment_id) )\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": "Which vehicles have a total maintenance cost exceeding 10000 across all their maintenance logs?"}, {"role": "assistant", "content": "SELECT vehicle_id, SUM(cost) AS total_maintenance_cost FROM transportation.maintenance_logs GROUP BY vehicle_id HAVING SUM(cost) > 10000;"}, {"role": "user", "content": "For these vehicles, also show the count of maintenance logs and the average cost per log."}, {"role": "assistant", "content": "SELECT vehicle_id, COUNT(log_id) AS maintenance_log_count, AVG(cost) AS average_maintenance_cost FROM transportation.maintenance_logs GROUP BY vehicle_id HAVING SUM(cost) > 10000;"}], "system": "You are an SQL statement expert. Given the table structure 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 character varying(64) NOT NULL, license_plate character varying(32) NOT NULL UNIQUE, vin character varying(17) UNIQUE, make character varying(64) NOT NULL, model character varying(64) NOT NULL, year integer NOT NULL, type character varying(32) NOT NULL, capacity integer, fuel_type character varying(32) NOT NULL, status character varying(32) NOT NULL, depot_id character varying(64), acquisition_date date, PRIMARY KEY (vehicle_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) )\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": "Get the number of direct reports for each manager, showing manager_id and report_count."}, {"role": "assistant", "content": "SELECT manager_id,\n       COUNT(*) AS report_count\nFROM hospitality_technology.staff\nWHERE manager_id IS NOT NULL\nGROUP BY manager_id;"}, {"role": "user", "content": "Exclude managers who have fewer than 2 direct reports."}, {"role": "assistant", "content": "SELECT manager_id,\n       COUNT(*) AS report_count\nFROM hospitality_technology.staff\nWHERE manager_id IS NOT NULL\nGROUP BY manager_id\nHAVING COUNT(*) >= 2;"}, {"role": "user", "content": "Also include the manager's full name alongside their ID."}, {"role": "assistant", "content": "SELECT m.staff_id AS manager_id,\n       m.first_name || ' ' || m.last_name AS manager_full_name,\n       COUNT(s.staff_id) AS report_count\nFROM hospitality_technology.staff s\nJOIN hospitality_technology.staff m\n  ON s.manager_id = m.staff_id\nGROUP BY m.staff_id, m.first_name, m.last_name\nHAVING COUNT(s.staff_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 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": "Show me all maintenance logs for 'Oil Change' services performed in the last 3 months, including the vehicle ID, service date, and cost."}, {"role": "assistant", "content": "SELECT vehicle_id, service_date, cost FROM transportation.maintenance_logs WHERE service_type = 'Oil Change' AND service_date >= CURRENT_DATE - INTERVAL '3 months';"}, {"role": "user", "content": "Can you also include the mechanic name and filter to only show services that cost more than $100?"}, {"role": "assistant", "content": "SELECT vehicle_id, service_date, cost, mechanic_name FROM transportation.maintenance_logs WHERE service_type = 'Oil Change' AND service_date >= CURRENT_DATE - INTERVAL '3 months' AND cost > 100;"}, {"role": "user", "content": "Now order these results by service date with the most recent first and limit to 10 records."}, {"role": "assistant", "content": "SELECT vehicle_id, service_date, cost, mechanic_name FROM transportation.maintenance_logs WHERE service_type = 'Oil Change' AND service_date >= CURRENT_DATE - INTERVAL '3 months' AND cost > 100 ORDER BY service_date DESC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.maintenance_logs (\n    log_id character varying(64) NOT NULL,  -- unique identifier for the maintenance record\n    vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle serviced\n    service_date date NOT NULL, -- date the service was performed\n    odometer_reading integer, -- vehicle mileage at time of service\n    service_type character varying(128) NOT NULL, -- type of service (e.g., Oil Change, Tire Rotation, Engine Repair)\n    description text NOT NULL, -- detailed description of work done\n    cost numeric(10, 2), -- cost of the service\n    mechanic_name character varying(128), -- name or ID of the mechanic/shop\n    next_service_due_date date, -- recommended date for next service\n    PRIMARY KEY (log_id)\n)\n"}
{"conversations": [{"role": "user", "content": "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": "Show me all documents uploaded by lawyers from law firms located in 'New York'. Include the document name, upload timestamp, the first and last name of the uploading lawyer, and the firm name."}, {"role": "assistant", "content": "SELECT d.document_name, d.upload_timestamp, l.first_name AS lawyer_first_name, l.last_name AS lawyer_last_name, lf.firm_name FROM documents AS d JOIN lawyers AS l ON d.uploaded_by_lawyer_id = l.lawyer_id JOIN law_firms AS lf ON l.firm_id = lf.firm_id WHERE lf.address LIKE '%New York%';"}, {"role": "user", "content": "Okay, but only show documents where the document type is 'Contract'."}, {"role": "assistant", "content": "SELECT d.document_name, d.upload_timestamp, l.first_name AS lawyer_first_name, l.last_name AS lawyer_last_name, lf.firm_name FROM documents AS d JOIN lawyers AS l ON d.uploaded_by_lawyer_id = l.lawyer_id JOIN law_firms AS lf ON l.firm_id = lf.firm_id WHERE lf.address LIKE '%New York%' AND d.document_type = 'Contract';"}, {"role": "user", "content": "Also, sort the results by upload timestamp descending and include the document version."}, {"role": "assistant", "content": "SELECT d.document_name, d.upload_timestamp, d.version, l.first_name AS lawyer_first_name, l.last_name AS lawyer_last_name, lf.firm_name FROM documents AS d JOIN lawyers AS l ON d.uploaded_by_lawyer_id = l.lawyer_id JOIN law_firms AS lf ON l.firm_id = lf.firm_id WHERE lf.address LIKE '%New York%' AND d.document_type = 'Contract' ORDER BY d.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.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": "For each notification, list the next notification sent to the same citizen (if any). Show citizen_id, notification_id, sent_at, next_notification_id, and next_sent_at."}, {"role": "assistant", "content": "SELECT\n  n1.citizen_id,\n  n1.notification_id,\n  n1.sent_at,\n  n2.notification_id AS next_notification_id,\n  n2.sent_at         AS next_sent_at\nFROM government_services.notifications n1\nLEFT JOIN government_services.notifications n2\n  ON n1.citizen_id = n2.citizen_id\n  AND n2.sent_at = (\n    SELECT MIN(sent_at)\n    FROM government_services.notifications n3\n    WHERE n3.citizen_id = n1.citizen_id\n      AND n3.sent_at > n1.sent_at\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 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": "Which patients have insurance policies that are effective between May 1st, 2023 and October 1st, 2023? Show their patient_id, policy_number, and effective_date, and also include the related plan_id."}, {"role": "assistant", "content": "SELECT patient_id, policy_number, effective_date, plan_id FROM healthcare.patient_insurance WHERE effective_date >= '2023-05-01' AND effective_date <= '2023-10-01';"}, {"role": "user", "content": "I only want to see policies that are still primary. Could you adjust the query to add that condition?"}, {"role": "assistant", "content": "SELECT patient_id, policy_number, effective_date, plan_id FROM healthcare.patient_insurance WHERE effective_date >= '2023-05-01' AND effective_date <= '2023-10-01' AND is_primary = true;"}, {"role": "user", "content": "Actually, please also show only entries where the subscriber_name starts with the letter 'A'."}, {"role": "assistant", "content": "SELECT patient_id, policy_number, effective_date, plan_id FROM healthcare.patient_insurance WHERE effective_date >= '2023-05-01' AND effective_date <= '2023-10-01' AND is_primary = true AND subscriber_name LIKE 'A%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 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": "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": "Can you provide a breakdown of total and average account balance by account_type and currency for each account status?"}, {"role": "assistant", "content": "SELECT account_type, currency, status, COUNT(*) AS total_accounts, SUM(balance) AS total_balance, AVG(balance) AS average_balance\nFROM financial_services.accounts\nGROUP BY account_type, currency, status;"}, {"role": "user", "content": "Could you include the minimum and maximum interest rate for each group as well?"}, {"role": "assistant", "content": "SELECT account_type, currency, status, COUNT(*) AS total_accounts, SUM(balance) AS total_balance, AVG(balance) AS average_balance, MIN(interest_rate) AS min_interest_rate, MAX(interest_rate) AS max_interest_rate\nFROM financial_services.accounts\nGROUP BY account_type, currency, status;"}, {"role": "user", "content": "Only show groups where the total_accounts is greater than 20."}, {"role": "assistant", "content": "SELECT account_type, currency, status, COUNT(*) AS total_accounts, SUM(balance) AS total_balance, AVG(balance) AS average_balance, MIN(interest_rate) AS min_interest_rate, MAX(interest_rate) AS max_interest_rate\nFROM financial_services.accounts\nGROUP BY account_type, currency, status\nHAVING COUNT(*) > 20;"}, {"role": "user", "content": "Please sort the results by average_balance in descending order."}, {"role": "assistant", "content": "SELECT account_type, currency, status, COUNT(*) AS total_accounts, SUM(balance) AS total_balance, AVG(balance) AS average_balance, MIN(interest_rate) AS min_interest_rate, MAX(interest_rate) AS max_interest_rate\nFROM financial_services.accounts\nGROUP BY account_type, currency, status\nHAVING COUNT(*) > 20\nORDER BY average_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 (\n    account_id character varying(64) NOT NULL, -- unique identifier for the account\n    customer_id character varying(64) NOT NULL, -- foreign key linking to the customer\n    account_number character varying(128) NOT NULL UNIQUE, -- unique account number visible to customer\n    account_type character varying(50) NOT NULL, -- e.g., Checking, Savings, Investment, Loan, Credit Card\n    balance numeric(19, 4) NOT NULL DEFAULT 0.00, -- current account balance\n    currency character varying(3) NOT NULL, -- currency code (e.g., USD, EUR)\n    opened_date date NOT NULL, -- date the account was opened\n    status character varying(32) NOT NULL, -- e.g., Open, Closed, Frozen\n    interest_rate numeric(5, 4), -- annual interest rate, if applicable\n    last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last account update\n    PRIMARY KEY (account_id),\n    FOREIGN KEY (customer_id) REFERENCES financial_services.customers(customer_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show the number of achievements unlocked by each player per month. Display player_id, month (as YYYY-MM), and achievement_count."}, {"role": "assistant", "content": "SELECT player_id,\n       TO_CHAR(unlocked_at, 'YYYY-MM') AS year_month,\n       COUNT(*) AS achievement_count\nFROM gaming_technology.player_achievements\nGROUP BY player_id, TO_CHAR(unlocked_at, 'YYYY-MM');"}, {"role": "user", "content": "Filter to months where players unlocked at least 5 achievements."}, {"role": "assistant", "content": "SELECT player_id,\n       TO_CHAR(unlocked_at, 'YYYY-MM') AS year_month,\n       COUNT(*) AS achievement_count\nFROM gaming_technology.player_achievements\nGROUP BY player_id, TO_CHAR(unlocked_at, 'YYYY-MM')\nHAVING COUNT(*) >= 5;"}, {"role": "user", "content": "Sort the results by year_month ascending and then by achievement_count descending."}, {"role": "assistant", "content": "SELECT player_id,\n       TO_CHAR(unlocked_at, 'YYYY-MM') AS year_month,\n       COUNT(*) AS achievement_count\nFROM gaming_technology.player_achievements\nGROUP BY player_id, TO_CHAR(unlocked_at, 'YYYY-MM')\nHAVING COUNT(*) >= 5\nORDER BY year_month ASC, achievement_count DESC;"}, {"role": "user", "content": "Limit the results to 10 rows."}, {"role": "assistant", "content": "SELECT player_id,\n       TO_CHAR(unlocked_at, 'YYYY-MM') AS year_month,\n       COUNT(*) AS achievement_count\nFROM gaming_technology.player_achievements\nGROUP BY player_id, TO_CHAR(unlocked_at, 'YYYY-MM')\nHAVING COUNT(*) >= 5\nORDER BY year_month ASC, achievement_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 gaming_technology.player_achievements ( player_achievement_id uuid, player_id uuid, achievement_id uuid, unlocked_at timestamp with time zone )\n"}
{"conversations": [{"role": "user", "content": "Show me all active policies with coverage limits above $1,000,000, along with their customer IDs and agent IDs, sorted by coverage limit in descending order."}, {"role": "assistant", "content": "SELECT p.policy_id, p.customer_id, p.agent_id, p.coverage_limit FROM insurance.policies p WHERE p.status = 'Active' AND p.coverage_limit > 1000000 ORDER BY p.coverage_limit DESC;"}, {"role": "user", "content": "Now include the policy start date and end date, and sort them by coverage limit in descending order."}, {"role": "assistant", "content": "SELECT p.policy_id, p.customer_id, p.agent_id, p.coverage_limit, p.start_date, p.end_date FROM insurance.policies p WHERE p.status = 'Active' AND p.coverage_limit > 1000000 ORDER BY p.coverage_limit DESC;"}, {"role": "user", "content": "I also want to see only policies that started in the last year."}, {"role": "assistant", "content": "SELECT p.policy_id, p.customer_id, p.agent_id, p.coverage_limit, p.start_date, p.end_date FROM insurance.policies p WHERE p.status = 'Active' AND p.coverage_limit > 1000000 AND p.start_date >= CURRENT_DATE - INTERVAL '1 year' ORDER BY p.coverage_limit DESC;"}, {"role": "user", "content": "Finally, show me the count of such policies per agent ID."}, {"role": "assistant", "content": "SELECT p.agent_id, COUNT(*) as policy_count FROM insurance.policies p WHERE p.status = 'Active' AND p.coverage_limit > 1000000 AND p.start_date >= CURRENT_DATE - INTERVAL '1 year' GROUP BY p.agent_id ORDER 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 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.agents ( agent_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, agency_name character varying(150), license_number character varying(100) NOT NULL UNIQUE, license_state character varying(50) NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(30), hire_date date, termination_date date, status character varying(20) NOT NULL DEFAULT 'Active', commission_rate numeric(5, 4) NOT NULL DEFAULT 0.05, manager_id character varying(64), PRIMARY KEY (agent_id) )\nCREATE TABLE insurance.premium_payments ( payment_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, amount_paid numeric(12, 2) NOT NULL, payment_method character varying(50), transaction_reference character varying(128) UNIQUE, due_date date, payment_period_start date, payment_period_end date, status character varying(30) NOT NULL DEFAULT 'Completed', PRIMARY KEY (payment_id) )\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) )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, relationship character varying(50) NOT NULL, percentage_share numeric(5, 2) NOT NULL CHECK (percentage_share > 0 AND percentage_share <= 100), contact_info text, added_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (beneficiary_id), UNIQUE (policy_id, customer_id) )\n"}
{"conversations": [{"role": "user", "content": "Show me 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": "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 asset types along with the count of distinct assets and the count of log actions for each type."}, {"role": "assistant", "content": "SELECT a.type, COUNT(DISTINCT a.asset_id) AS asset_count, COUNT(l.log_id) AS action_count FROM trading_platform.assets a LEFT JOIN trading_platform.logs l ON a.asset_id = l.details->>'asset_id' GROUP BY a.type ORDER BY action_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.assets ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.logs ( log_id text, user_id text, action text, details text, logged_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all users who have bought assets, along with their wallet addresses."}, {"role": "assistant", "content": "SELECT DISTINCT T1.user_id, T1.address FROM wallets AS T1 JOIN trades AS T2 ON T1.user_id = T2.buyer_id;"}, {"role": "user", "content": "Filter this list to include only trades made in the last 30 days."}, {"role": "assistant", "content": "SELECT DISTINCT T1.user_id, T1.address FROM wallets AS T1 JOIN trades AS T2 ON T1.user_id = T2.buyer_id WHERE T2.traded_at >= datetime('now', '-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 trading_platform.wallets ( wallet_id.text, user_id.text, address.text, private_key.text, created_at.timestamp )\nCREATE TABLE trading_platform.trades ( trade_id.text, 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, 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.peers ( peer_id.text, ip_address.text, port.integer, last_seen.timestamp )\nCREATE TABLE trading_platform.logs ( log_id.text, user_id.text, action.text, details.text, logged_at.timestamp )\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": "What is the average interest rate for auto loans (loan_type = 'Auto') with a principal amount between $20,000 and $50,000?"}, {"role": "assistant", "content": "SELECT AVG(interest_rate) AS average_interest_rate FROM financial_services.loans WHERE loan_type = 'Auto' AND principal_amount BETWEEN 20000 AND 50000"}], "system": "You are an SQL statement expert. Given the table structure 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": "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": "For each user, list all pairs of read and unread notifications, showing the recipient_user_id, the unread notification_id and type, and the read notification_id and type."}, {"role": "assistant", "content": "SELECT\n  n_unread.recipient_user_id,\n  n_unread.notification_id   AS unread_id,\n  n_unread.notification_type AS unread_type,\n  n_read.notification_id     AS read_id,\n  n_read.notification_type   AS read_type\nFROM social_media.notifications n_unread\nJOIN social_media.notifications n_read\n  ON n_unread.recipient_user_id = n_read.recipient_user_id\nWHERE n_unread.read_at IS NULL\n  AND n_read.read_at IS NOT NULL;"}, {"role": "user", "content": "Actually, only include pairs where the unread notification_type is 'message'."}, {"role": "assistant", "content": "SELECT\n  n_unread.recipient_user_id,\n  n_unread.notification_id   AS unread_id,\n  n_unread.notification_type AS unread_type,\n  n_read.notification_id     AS read_id,\n  n_read.notification_type   AS read_type\nFROM social_media.notifications n_unread\nJOIN social_media.notifications n_read\n  ON n_unread.recipient_user_id = n_read.recipient_user_id\nWHERE n_unread.read_at IS NULL\n  AND n_read.read_at IS NOT NULL\n  AND n_unread.notification_type = 'message';"}], "system": "You are an SQL statement expert. Given the table structure 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.notifications ( notification_id character varying(64) NOT NULL, recipient_user_id character varying(64) NOT NULL, sender_user_id character varying(64), notification_type character varying(30) NOT NULL, target_entity_id character varying(64), target_entity_type character varying(20), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, read_at timestamp, PRIMARY KEY (notification_id) )\n"}
{"conversations": [{"role": "user", "content": "Find all pairs of distinct medications manufactured by the same company, showing med1.medication_id, med1.medication_name, med2.medication_id, med2.medication_name, and the manufacturer."}, {"role": "assistant", "content": "SELECT m1.medication_id AS med1_id, m1.medication_name AS med1_name, m2.medication_id AS med2_id, m2.medication_name AS med2_name, m1.manufacturer\nFROM healthcare.medications m1\nJOIN healthcare.medications m2\n  ON m1.manufacturer = m2.manufacturer\n AND m1.medication_id <> m2.medication_id;"}, {"role": "user", "content": "Actually, exclude duplicate pairs by ensuring med1_id is less than med2_id."}, {"role": "assistant", "content": "SELECT m1.medication_id AS med1_id, m1.medication_name AS med1_name, m2.medication_id AS med2_id, m2.medication_name AS med2_name, m1.manufacturer\nFROM healthcare.medications m1\nJOIN healthcare.medications m2\n  ON m1.manufacturer = m2.manufacturer\n AND m1.medication_id < m2.medication_id;"}, {"role": "user", "content": "Also, sort the results by manufacturer ascending and then med1_id ascending."}, {"role": "assistant", "content": "SELECT m1.medication_id AS med1_id, m1.medication_name AS med1_name, m2.medication_id AS med2_id, m2.medication_name AS med2_name, m1.manufacturer\nFROM healthcare.medications m1\nJOIN healthcare.medications m2\n  ON m1.manufacturer = m2.manufacturer\n AND m1.medication_id < m2.medication_id\nORDER BY m1.manufacturer ASC, m1.medication_id 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.medications ( medication_id.text, medication_name.text, generic_name.text, manufacturer.text, ndc_code.text, description.text )\n"}
{"conversations": [{"role": "user", "content": "Find all users whose usernames contain numbers and have email addresses from either Gmail or Yahoo."}, {"role": "assistant", "content": "SELECT username, email FROM blockchain.users WHERE (username ~ '[0-9]') AND (email LIKE '%@gmail.com' OR email LIKE '%@yahoo.com');"}, {"role": "user", "content": "Now, order these results by username length in descending order."}, {"role": "assistant", "content": "SELECT username, email FROM blockchain.users WHERE (username ~ '[0-9]') AND (email LIKE '%@gmail.com' OR email LIKE '%@yahoo.com') ORDER BY LENGTH(username) DESC;"}, {"role": "user", "content": "Can you modify this to only show the top 5 longest usernames?"}, {"role": "assistant", "content": "SELECT username, email FROM blockchain.users WHERE (username ~ '[0-9]') AND (email LIKE '%@gmail.com' OR email LIKE '%@yahoo.com') ORDER BY LENGTH(username) 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 blockchain.users ( user_id text, username text, email text, password_hash text )\n"}
{"conversations": [{"role": "user", "content": "What is the current location of train number Acela 2151?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to real-time location data for trains. The database only contains static information such as train ID, model, capacity, and maintenance schedules. For current location updates, please check with the train operator or a tracking service."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.trains (\n    train_id character varying(64) NOT NULL, -- Unique identifier for the train set\n    train_number character varying(32) NOT NULL, -- Operational number of the train (e.g., 'Acela 2151')\n    model character varying(128), -- Model of the train (e.g., 'Siemens Velaro')\n    manufacturer character varying(128), -- Manufacturer of the train\n    year_manufactured integer, -- Year the train was built\n    capacity integer NOT NULL, -- Total passenger capacity\n    status character varying(32) NOT NULL DEFAULT 'Active', -- e.g., Active, Maintenance, Retired\n    last_maintenance_date date, -- Date of last scheduled maintenance\n    next_maintenance_date date, -- Date of next scheduled maintenance\n    PRIMARY KEY (train_id),\n    UNIQUE (train_number)\n)\n"}
{"conversations": [{"role": "user", "content": "List the booking ID, the first name, and the last name of the passenger for all bookings."}, {"role": "assistant", "content": "SELECT T1.booking_id , T2.first_name , T2.last_name FROM transportation.bookings AS T1 JOIN transportation.passengers AS T2 ON T1.passenger_id = T2.passenger_id"}, {"role": "user", "content": "Now, only include bookings where the fare is greater than 100."}, {"role": "assistant", "content": "SELECT T1.booking_id , T2.first_name , T2.last_name FROM transportation.bookings AS T1 JOIN transportation.passengers AS T2 ON T1.passenger_id = T2.passenger_id WHERE T1.fare > 100"}, {"role": "user", "content": "For these bookings with fares over 100, also show the booking status and order the results by fare in descending order."}, {"role": "assistant", "content": "SELECT T1.booking_id , T2.first_name , T2.last_name , T1.status FROM transportation.bookings AS T1 JOIN transportation.passengers AS T2 ON T1.passenger_id = T2.passenger_id WHERE T1.fare > 100 ORDER BY T1.fare DESC"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id.text, license_plate.text, vin.text, make.text, model.text, year.integer, type.text, capacity.integer, fuel_type.text, status.text, depot_id.text, acquisition_date.date )\nCREATE TABLE transportation.drivers ( driver_id.text, employee_id.text, first_name.text, last_name.text, license_number.text, license_expiry_date.date, contact_number.text, email.text, hire_date.date, status.text )\nCREATE TABLE transportation.routes ( route_id.text, route_number.text, description.text, origin_location_id.text, destination_location_id.text, distance_km.numeric, estimated_duration_minutes.integer, type.text )\nCREATE TABLE transportation.trips ( trip_id.text, route_id.text, vehicle_id.text, driver_id.text, scheduled_departure.timestamp, actual_departure.timestamp, scheduled_arrival.timestamp, actual_arrival.timestamp, origin_location_id.text, destination_location_id.text, status.text, passenger_count.integer, cargo_manifest_id.text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\nCREATE TABLE transportation.passengers ( passenger_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, loyalty_program_id.text, created_at.timestamp )\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"}
{"conversations": [{"role": "user", "content": "Show me the total number of token transfers for each token symbol on the network."}, {"role": "assistant", "content": "SELECT tk.token_symbol, COUNT(tt.transfer_id) AS total_transfers FROM web3.tokens tk JOIN web3.token_transfers tt ON tk.token_id = tt.token_id GROUP BY tk.token_symbol;"}, {"role": "user", "content": "Actually, I only want to see tokens with more than 100 transfers."}, {"role": "assistant", "content": "SELECT tk.token_symbol, COUNT(tt.transfer_id) AS total_transfers FROM web3.tokens tk JOIN web3.token_transfers tt ON tk.token_id = tt.token_id GROUP BY tk.token_symbol HAVING COUNT(tt.transfer_id) > 100;"}, {"role": "user", "content": "There's a syntax error in your SQL, you're missing a closing parenthesis."}, {"role": "assistant", "content": "SELECT tk.token_symbol, COUNT(tt.transfer_id) AS total_transfers FROM web3.tokens tk JOIN web3.token_transfers tt ON tk.token_id = tt.token_id GROUP BY tk.token_symbol HAVING COUNT(tt.transfer_id) > 100;"}, {"role": "user", "content": "Now sort the results by total_transfers in descending order."}, {"role": "assistant", "content": "SELECT tk.token_symbol, COUNT(tt.transfer_id) AS total_transfers FROM web3.tokens tk JOIN web3.token_transfers tt ON tk.token_id = tt.token_id GROUP BY tk.token_symbol HAVING COUNT(tt.transfer_id) > 100 ORDER BY total_transfers 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.contracts ( contract_id character varying(64) NOT NULL, address character varying(128) NOT NULL, abi text NOT NULL, bytecode text NOT NULL, deployer_address character varying(128) NOT NULL, deployed_at timestamp NOT NULL, network_id character varying(64) NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (contract_id) )\nCREATE TABLE web3.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 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.token_transfers ( transfer_id character varying(64) NOT NULL, token_id character varying(64) NOT NULL, from_address character varying(128) NOT NULL, to_address character varying(128) NOT NULL, value numeric(38,14) NOT NULL, transaction_id character varying(64) NOT NULL, log_index integer NOT NULL, PRIMARY KEY (transfer_id) )\nCREATE TABLE web3.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) )\n"}
{"conversations": [{"role": "user", "content": "List all maintenance logs for vehicles that had 'Oil Change' service in the last 3 months, showing vehicle ID, service date, and cost."}, {"role": "assistant", "content": "SELECT vehicle_id, service_date, cost FROM transportation.maintenance_logs WHERE service_type = 'Oil Change' AND service_date >= CURRENT_DATE - INTERVAL '3 months';"}, {"role": "user", "content": "Can you include the mechanic name and show only services that cost more than $100?"}, {"role": "assistant", "content": "SELECT vehicle_id, service_date, cost, mechanic_name FROM transportation.maintenance_logs WHERE service_type = 'Oil Change' AND service_date >= CURRENT_DATE - INTERVAL '3 months' AND cost > 100;"}, {"role": "user", "content": "Actually, I need to see the vehicle make and model as well. Can you include that information?"}, {"role": "assistant", "content": "Sorry, I can't include vehicle make and model as those fields aren't present in the provided table schemas. The maintenance_logs table only contains vehicle_id but not make/model information."}, {"role": "user", "content": "Then just add the odometer reading to the previous query and order by the most recent services first."}, {"role": "assistant", "content": "SELECT vehicle_id, service_date, cost, mechanic_name, odometer_reading FROM transportation.maintenance_logs WHERE service_type = 'Oil Change' AND service_date >= CURRENT_DATE - INTERVAL '3 months' AND cost > 100 ORDER BY service_date DESC;"}], "system": "You are an SQL statement expert. Given the table structure 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 (\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 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": "Give me the total billed amount for each invoice in 2024."}, {"role": "assistant", "content": "SELECT invoice_id, SUM(hours_spent * billing_rate) AS total_billed_amount FROM legal_services.time_entries WHERE is_billed = TRUE AND EXTRACT(YEAR FROM date_worked) = 2024 GROUP BY invoice_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.time_entries ( entry_id text PRIMARY KEY, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable bool, is_billed bool, invoice_id text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List the top 5 tokens by 24 hour trading volume on DEX pools."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, volume_24h \nFROM token_dexpool_info \nORDER BY volume_24h DESC LIMIT 5;"}, {"role": "user", "content": "Show only their token symbols and the related chain, ordered by volume descending."}, {"role": "assistant", "content": "SELECT token_symbol, chain, volume_24h \nFROM token_dexpool_info \nORDER BY volume_24h DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\n \"CREATE TABLE project_fundraising_record (\",\n    \"id character varying(32) NOT NULL,  -- fundraising record id\",\n    \"project_id character varying(32) NOT NULL, -- the invested project's id\",\n    \"project_name character varying(128) NOT NULL, -- name of the invested project\",\n    \"rounds_name character varying(32), -- name of the fundraising round\",\n    \"investment_value numeric(38,14), -- amount of the fundraising in USD\",\n    \"investment_date character varying(128), -- the date of the investment happened\",\n    \"introduction character varying(128), -- the introduction of the invested project\",\n    \"valuation numeric(38,14), -- the valuation of the project in USD when invested\",\n\n \"CREATE TABLE token_basic_info (\",\n    \"coin_id character varying(100) NOT NULL, -- the id of the token\",\n    \"token_name character varying(100) NOT NULL, -- the token's name\",\n    \"token_symbol character varying(100) NOT NULL, -- the token's symbol\",\n    \"token_address character varying(100) NOT NULL, -- the token's address\",\n    \"chain text, -- the chain that the token resides\",\n    \"price double precision, -- the current price of the token\",\n    \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour\",\n    \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours\",\n    \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days\",\n    \"highest_price_24h double precision, -- the highest price of the token in 24 hours\",\n    \"lowest_price_24h double precision,  -- the lowest price of the token in 24 hours\",\n    \"market_cap double precision, -- the market cap of the token\",\n    \"market_cap_rank bigint, -- the rank of the token market cap in desc\",\n    \"market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours\",\n    \"total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX)\",    \n    \"narrative text, -- the category or narrative of the token\",\n    \"trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token.\",\n    \",PRIMARY KEY (coin_id, chain));\",\n\n \"CREATE TABLE narrative_info (\",\n    \"narrative character varying(512) NOT NULL, -- the id of narrative\",\n    \"top_3_coins text, -- the top 3 tokens in the narrative\",\n    \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative\",\n    \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative\",\n    \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative\",\n    \"market_cap double precision, -- the market cap of the narrative\",\n    \"volume_24h double precision, -- the trade volume of the narrative\",\n    \"trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative\",\n    \"token_num bigint, -- total token number in the narrative\",\n    \",PRIMARY KEY (narrative));\"\n\n  \"CREATE TABLE token_dexpool_info (\",\n    \"pair_address character varying(512) NOT NULL, -- the id of dexpool\",\n    \"token_name character varying(100) NOT NULL, -- the name of the token in the dexpool\",\n    \"token_symbol character varying(100) NOT NULL, -- the token's symbol\",\n    \"chain text, -- the chain that the dexpool resides\",\n    \"price double precision, -- the current price of the token\",\n    \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour\",\n    \"price_change_percentage_6h double precision, -- change in value divided by the absolute price value of the original token price in 6 hours\",\n    \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours\",\n    \"makers_24h double precision, -- the makers of the dex pool in 24 hours\",\n    \"volume_24h double precision, -- the trade volume of the dex pool in 24 hours\",\n    \"liquidity double precision, -- the liquidity of the dex pool\",\n    \"market_cap double precision, -- the market cap of the token\",\n    \"trend_rank bigint, -- the rank of token in the dex pool of recent trending, value 1 expresses the most popular token.\",\n    \",PRIMARY KEY (pair_address, chain);\"\n\n  \"CREATE TABLE cex_token_balance (\",\n    \"snapshot_time character varying(32) NOT NULL,  -- the snapshot time of record, converted from original timestamp\",\n    \"chain character varying(128) NOT NULL, -- the chain that the token resides\",\n    \"address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX\",\n    \"exchange character varying(512) NOT NULL, -- a centralized exchange name\",\n    \"token_address character varying(128) NOT NULL, -- token contract address\",\n    \"token_symbol character varying(512), --token symbol\",\n    \"balance numeric(38,10), -- token balance\",\n    \"usd_value numeric(38,14), -- value of the token held in USD\",\n    \"price double precision, --price of the token in USD\",\n    \",PRIMARY KEY (snapshot_time, exchange, address, chain, token_address));\"\n\n  \"CREATE TABLE smart_money_profit (\",\n    \"address character varying(100) NOT NULL, -- the user's address\",\n    \"rank INT, -- the rank of the address in trade performance, value 1 expresses the best address.\",\n    \"profit numeric(38,6), -- the profit user made in a month\",\n    \"roi numeric(38,2), -- the roi of the user in a month\",\n    \"realized_ratio numeric(38,2), -- the percentage of the user's realized profit\",\n    \"most_profit_token character varying(100), -- the token symbol of the user's most profitable trade\",\n    \"last_trade_time character varying(100), -- the last trade time of the user\",\n    \"chain character varying(100), -- the chain that the address resides\",\n    \"PRIMARY KEY (address, chain));\",\n\n  \"CREATE TABLE smart_money_token_inflow (\",\n    \"token_address character varying(100) NOT NULL, -- the token's address\",\n    \"token_symbol character varying(100), -- the tokens's symbol\",\n    \"token_amount numeric(38,2), -- the absolute value of the amount if user bought minus  the amount user sold of this token\",\n    \"usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token\",\n    \"avg_price numeric(38,6), -- the average cost price of user spent on this token\",\n    \"type int, -- the direction of the trade on this token. 1 means buying, 2 means selling\",\n    \"address_amount integer, -- the amount of the user bought this token\",\n    \"narrative character varying(100), -- the category or narrative of the token\",\n    \"chain character varying(100), -- the chain that the token resides\",\n    \",PRIMARY KEY (token_address, chain)\",\n\n"}
{"conversations": [{"role": "user", "content": "List all 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": "List all services provided by the property named 'Grand Plaza Hotel' and include their category and price."}, {"role": "assistant", "content": "SELECT T1.service_name, T1.category, T1.price FROM hospitality_technology.services AS T1 JOIN hospitality_technology.properties AS T2 ON T1.property_id = T2.property_id WHERE T2.property_name = 'Grand Plaza Hotel';"}, {"role": "user", "content": "Only show available services from the 'Spa' department at 'Grand Plaza Hotel'."}, {"role": "assistant", "content": "SELECT T1.service_name, T1.category, T1.price FROM hospitality_technology.services AS T1 JOIN hospitality_technology.properties AS T2 ON T1.property_id = T2.property_id WHERE T2.property_name = 'Grand Plaza Hotel' AND T1.is_available = TRUE AND T1.department = 'Spa';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.services ( service_id 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) )\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": "Show me the notification ID, recipient user ID, and notification type for notifications received by users that user 'user123' is following."}, {"role": "assistant", "content": "SELECT n.notification_id, n.recipient_user_id, n.notification_type FROM social_media.notifications AS n JOIN social_media.follows AS f ON n.recipient_user_id = f.following_user_id WHERE f.follower_user_id = 'user123';"}, {"role": "user", "content": "Filter this list to only include notifications created after '2024-06-01' and also show the notification creation time."}, {"role": "assistant", "content": "SELECT n.notification_id, n.recipient_user_id, n.notification_type, n.created_at FROM social_media.notifications AS n JOIN social_media.follows AS f ON n.recipient_user_id = f.following_user_id WHERE f.follower_user_id = 'user123' AND n.created_at >= '2024-06-01';"}], "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 ( comment_id.text, post_id.text, user_id.text, parent_comment_id.text, content.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE social_media.follows ( follow_id.text, follower_user_id.text, following_user_id.text, created_at.timestamp )\nCREATE TABLE social_media.conversations ( conversation_id.text, created_at.timestamp, last_message_at.timestamp, is_group_chat.boolean, group_name.text )\nCREATE TABLE social_media.notifications ( notification_id.text, recipient_user_id.text, sender_user_id.text, notification_type.text, target_entity_id.text, target_entity_type.text, created_at.timestamp, read_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all security_ids that had at least one day where the high_price was more than twice the low_price, along with the maximum price difference (high_price - low_price) observed for each security."}, {"role": "assistant", "content": "SELECT security_id, MAX(high_price - low_price) AS max_price_difference FROM financial_services.market_data WHERE high_price > 2 * low_price GROUP BY security_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.market_data ( data_point_id bigint, security_id text, data_timestamp timestamp, open_price numeric, high_price numeric, low_price numeric, close_price numeric, adjusted_close_price numeric, volume bigint, source text )\n"}
{"conversations": [{"role": "user", "content": "Show the usernames of players and a count of how many different item types they have in their inventory."}, {"role": "assistant", "content": "SELECT T1.username, count(DISTINCT T3.item_type) FROM gaming_technology.players AS T1 JOIN gaming_technology.player_inventory AS T2 ON T1.player_id = T2.player_id JOIN gaming_technology.in_game_items AS T3 ON T2.item_id = T3.item_id GROUP BY T1.username;"}, {"role": "user", "content": "Only include players who have 3 or more different item types."}, {"role": "assistant", "content": "SELECT T1.username, count(DISTINCT T3.item_type) FROM gaming_technology.players AS T1 JOIN gaming_technology.player_inventory AS T2 ON T1.player_id = T2.player_id JOIN gaming_technology.in_game_items AS T3 ON T2.item_id = T3.item_id GROUP BY T1.username HAVING count(DISTINCT T3.item_type) >= 3;"}, {"role": "user", "content": "Order the results by the count of unique item types in descending order."}, {"role": "assistant", "content": "SELECT T1.username, count(DISTINCT T3.item_type) FROM gaming_technology.players AS T1 JOIN gaming_technology.player_inventory AS T2 ON T1.player_id = T2.player_id JOIN gaming_technology.in_game_items AS T3 ON T2.item_id = T3.item_id GROUP BY T1.username HAVING count(DISTINCT T3.item_type) >= 3 ORDER BY count(DISTINCT T3.item_type) DESC;"}, {"role": "user", "content": "For these players, could you also show the total quantity of all items they possess?"}, {"role": "assistant", "content": "SELECT T1.username, count(DISTINCT T3.item_type), sum(T2.quantity) FROM gaming_technology.players AS T1 JOIN gaming_technology.player_inventory AS T2 ON T1.player_id = T2.player_id JOIN gaming_technology.in_game_items AS T3 ON T2.item_id = T3.item_id GROUP BY T1.username HAVING count(DISTINCT T3.item_type) >= 3 ORDER BY count(DISTINCT T3.item_type) 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, username text, email text, password_hash text, registration_date timestamp with time zone, last_login timestamp with time zone, 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 timestamp with time zone )\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid, player_id uuid, game_id uuid, server_id uuid, start_time timestamp with time zone, end_time timestamp with time zone, 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 )\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 timestamp with time zone, instance_data jsonb )\n"}
{"conversations": [{"role": "user", "content": "Can you list the number of citizens registered each month in 2024? Please show the month and the citizen count."}, {"role": "assistant", "content": "SELECT TO_CHAR(registration_date, 'YYYY-MM') AS registration_month, COUNT(*) AS citizen_count FROM government_services.citizens WHERE registration_date >= '2024-01-01' AND registration_date < '2025-01-01' GROUP BY registration_month ORDER BY registration_month;"}, {"role": "user", "content": "Now, can you also show the number of verified citizens for each month?"}, {"role": "assistant", "content": "SELECT TO_CHAR(registration_date, 'YYYY-MM') AS registration_month, COUNT(*) AS citizen_count, SUM(CASE WHEN is_verified = true THEN 1 ELSE 0 END) AS verified_citizen_count FROM government_services.citizens WHERE registration_date >= '2024-01-01' AND registration_date < '2025-01-01' GROUP BY registration_month ORDER BY registration_month;"}, {"role": "user", "content": "I see some months with zero verified citizens, but they still show up. Can you exclude months with zero verified citizens from the result?"}, {"role": "assistant", "content": "SELECT registration_month, citizen_count, verified_citizen_count FROM (SELECT TO_CHAR(registration_date, 'YYYY-MM') AS registration_month, COUNT(*) AS citizen_count, SUM(CASE WHEN is_verified = true THEN 1 ELSE 0 END) AS verified_citizen_count FROM government_services.citizens WHERE registration_date >= '2024-01-01' AND registration_date < '2025-01-01' GROUP BY registration_month) sub WHERE verified_citizen_count > 0 ORDER BY registration_month;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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) )\n"}
{"conversations": [{"role": "user", "content": "I want a list of game_id and the count of hidden achievements for each game."}, {"role": "assistant", "content": "SELECT game_id, COUNT(*) AS hidden_achievement_count\nFROM gaming_technology.achievements\nWHERE hidden = TRUE\nGROUP BY game_id;"}, {"role": "user", "content": "Now only include games where the hidden_achievement_count is greater than 5."}, {"role": "assistant", "content": "SELECT game_id, COUNT(*) AS hidden_achievement_count\nFROM gaming_technology.achievements\nWHERE hidden = TRUE\nGROUP BY game_id\nHAVING COUNT(*) > 5;"}, {"role": "user", "content": "Also order the results by hidden_achievement_count in descending order."}, {"role": "assistant", "content": "SELECT game_id, COUNT(*) AS hidden_achievement_count\nFROM gaming_technology.achievements\nWHERE hidden = TRUE\nGROUP BY game_id\nHAVING COUNT(*) > 5\nORDER BY hidden_achievement_count DESC;"}, {"role": "user", "content": "Finally, include the average points of those hidden achievements as avg_hidden_points."}, {"role": "assistant", "content": "SELECT game_id,\n       COUNT(*) AS hidden_achievement_count,\n       AVG(points) AS avg_hidden_points\nFROM gaming_technology.achievements\nWHERE hidden = TRUE\nGROUP BY game_id\nHAVING COUNT(*) > 5\nORDER BY hidden_achievement_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id uuid NOT NULL DEFAULT gen_random_uuid(), username character varying(100) NOT NULL UNIQUE, email character varying(255) NOT NULL UNIQUE, password_hash text NOT NULL, registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, last_login timestamp with time zone, country_code character(2), status character varying(20) NOT NULL DEFAULT 'active', profile_data jsonb, PRIMARY KEY (player_id) )\nCREATE TABLE gaming_technology.games ( game_id uuid PRIMARY KEY, title text, developer_id uuid, publisher_id uuid, genre text, release_date date, description text, platform text, engine text, website text )\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, game_id uuid NOT NULL, server_id uuid, start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, end_time timestamp with time zone, duration_seconds integer, score integer, session_data jsonb, PRIMARY KEY (session_id) )\nCREATE TABLE gaming_technology.servers ( server_id uuid PRIMARY KEY, game_id uuid, server_name text, region text, ip_address text, port int, current_players int, max_players int, status text, last_heartbeat timestamptz )\nCREATE TABLE gaming_technology.achievements ( achievement_id.uuid, game_id.uuid, name.text, description.text, icon_url.text, points.integer, hidden.boolean )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid PRIMARY KEY, player_id uuid, achievement_id uuid, unlocked_at timestamptz )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid PRIMARY KEY, 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 PRIMARY KEY, player_id uuid, item_id uuid, quantity int, acquired_at timestamptz, instance_data jsonb )\n"}
{"conversations": [{"role": "user", "content": "Show the total transfer volume and number of transfers for each Avalanche token in the past 7 days, including token tick and its creator."}, {"role": "assistant", "content": "SELECT ta.tick, ti.creator, SUM(ta.amt) AS total_volume, COUNT(*) AS transfer_count\nFROM token_activities ta\nJOIN token_info ti ON ta.tick = ti.tick\nWHERE ta.block_timestamp >= now() - interval '7 days'\nGROUP BY ta.tick, ti.creator;"}, {"role": "user", "content": "Only include tokens where total_volume > 1000 and sort by total_volume descending."}, {"role": "assistant", "content": "SELECT ta.tick, ti.creator, SUM(ta.amt) AS total_volume, COUNT(*) AS transfer_count\nFROM token_activities ta\nJOIN token_info ti ON ta.tick = ti.tick\nWHERE ta.block_timestamp >= now() - interval '7 days'\nGROUP BY ta.tick, ti.creator\nHAVING SUM(ta.amt) > 1000\nORDER BY total_volume DESC;"}, {"role": "user", "content": "Limit the output to the top 5 tokens."}, {"role": "assistant", "content": "SELECT ta.tick, ti.creator, SUM(ta.amt) AS total_volume, COUNT(*) AS transfer_count\nFROM token_activities ta\nJOIN token_info ti ON ta.tick = ti.tick\nWHERE ta.block_timestamp >= now() - interval '7 days'\nGROUP BY ta.tick, ti.creator\nHAVING SUM(ta.amt) > 1000\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 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 sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata ( object_id.text, coin_type.text, status.text, decimals.bigint, description.text, icon_url.text, symbol.text, name.text )\nCREATE TABLE sui_nfts ( object_id.text, status.text, collection_type.text, package_id.text, previous_transaction.text, display.text, owner.text, name.text )\nCREATE TABLE token_prices_latest (\n    blockchain varchar(36) NOT NULL, -- blockchain fields for the functionType  in contract\n    address varchar(42) NOT NULL, -- address fields for the functionType  in contract\n    decimals bigint NOT NULL, -- decimals fields for the functionType  in contract\n    symbol varchar(36) NOT NULL, -- symbol fields for the functionType  in contract\n    price real NOT NULL, -- price fields for the functionType  in contract\n    timestamp timestamp(6) NOT NULL  -- timestamp fields for the functionType  in contract\n)\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_info ( 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 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, 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 ( 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": "特定の職種の従業員情報を取得したいです。従業員ID、名前、職種、雇用日を表示してください。"}, {"role": "assistant", "content": "db.employees.find(\n    { job_title: '<specific_job_title>' },\n    { employee_id: 1, first_name: 1, last_name: 1, job_title: 1, hire_date: 1, _id: 0 }\n).sort({ hire_date: -1 })"}, {"role": "user", "content": "雇用日が2020年1月1日以降の従業員だけに絞り込むことはできますか？"}, {"role": "assistant", "content": "db.employees.find(\n    { \n        job_title: '<specific_job_title>',\n        hire_date: { $gte: ISODate('2020-01-01') }\n    },\n    { employee_id: 1, first_name: 1, last_name: 1, job_title: 1, hire_date: 1, _id: 0 }\n).sort({ hire_date: -1 })"}, {"role": "user", "content": "雇用ステータスが「Active」の従業員だけをさらに条件に加えられますか？"}, {"role": "assistant", "content": "db.employees.find(\n    { \n        job_title: '<specific_job_title>',\n        hire_date: { $gte: ISODate('2020-01-01') },\n        employment_status: 'Active'\n    },\n    { employee_id: 1, first_name: 1, last_name: 1, job_title: 1, hire_date: 1, _id: 0 }\n).sort({ hire_date: -1 })"}, {"role": "user", "content": "スキル認定情報も結果に含めてください。"}, {"role": "assistant", "content": "db.employees.find(\n    { \n        job_title: '<specific_job_title>',\n        hire_date: { $gte: ISODate('2020-01-01') },\n        employment_status: 'Active'\n    },\n    { employee_id: 1, first_name: 1, last_name: 1, job_title: 1, hire_date: 1, skill_certifications: 1, _id: 0 }\n).sort({ hire_date: -1 })"}], "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: <ObjectId (or step_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: <ObjectId (or employee_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": "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": "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 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": "List all pairs of service orders that share the same bill_id, showing order1_id, order2_id, and the bill_id."}, {"role": "assistant", "content": "SELECT s1.order_id AS order1_id,\n       s2.order_id AS order2_id,\n       s1.bill_id\nFROM hospitality_technology.service_orders s1\nJOIN hospitality_technology.service_orders s2\n  ON s1.bill_id = s2.bill_id\n AND s1.order_id < s2.order_id;"}, {"role": "user", "content": "Exclude pairs where bill_id is null."}, {"role": "assistant", "content": "SELECT s1.order_id AS order1_id,\n       s2.order_id AS order2_id,\n       s1.bill_id\nFROM hospitality_technology.service_orders s1\nJOIN hospitality_technology.service_orders s2\n  ON s1.bill_id = s2.bill_id\n AND s1.order_id < s2.order_id\nWHERE s1.bill_id IS NOT NULL;"}, {"role": "user", "content": "Also include only those pairs where the first order's total_price is greater than the second order's total_price."}, {"role": "assistant", "content": "SELECT s1.order_id AS order1_id,\n       s2.order_id AS order2_id,\n       s1.bill_id\nFROM hospitality_technology.service_orders s1\nJOIN hospitality_technology.service_orders s2\n  ON s1.bill_id = s2.bill_id\n AND s1.order_id < s2.order_id\nWHERE s1.bill_id IS NOT NULL\n  AND s1.total_price > s2.total_price;"}], "system": "You are an SQL statement expert. Given the table structure 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": "Find the total number of documents uploaded by each citizen along with their first and last names."}, {"role": "assistant", "content": "SELECT c.citizen_id, c.first_name, c.last_name, COUNT(d.document_id) AS document_count\nFROM government_services.citizens c\nLEFT JOIN government_services.documents d ON c.citizen_id = d.citizen_id\nGROUP BY c.citizen_id, c.first_name, c.last_name;"}, {"role": "user", "content": "Actually, I only want to include those citizens who have uploaded documents in the last 30 days."}, {"role": "assistant", "content": "SELECT c.citizen_id, c.first_name, c.last_name, COUNT(d.document_id) AS document_count\nFROM government_services.citizens c\nJOIN government_services.documents d ON c.citizen_id = d.citizen_id\nWHERE d.upload_timestamp >= NOW() - INTERVAL '30 days'\nGROUP BY c.citizen_id, c.first_name, c.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.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.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.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 (\n    employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(150) NOT NULL,\n    department character varying(100),\n    work_email character varying(128) NOT NULL UNIQUE,\n    work_phone character varying(32),\n    hire_date date NOT NULL,\n    termination_date date, -- null if currently employed\n    access_level character varying(50), -- Role or permission level\n    manager_employee_id character varying(64), -- FK to self for reporting structure\n    PRIMARY KEY (employee_id)\n)\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\n"}
{"conversations": [{"role": "user", "content": "Show me all reviews with ratings of 5 stars, including the property name and review date."}, {"role": "assistant", "content": "SELECT r.review_id, p.property_name, r.review_date FROM hospitality_technology.reviews r JOIN hospitality_technology.properties p ON r.property_id = p.property_id WHERE r.rating_overall = 5;"}, {"role": "user", "content": "Now, include only reviews that have staff responses and show the response date as well."}, {"role": "assistant", "content": "SELECT r.review_id, p.property_name, r.review_date, r.response_date FROM hospitality_technology.reviews r JOIN hospitality_technology.properties p ON r.property_id = p.property_id WHERE r.rating_overall = 5 AND r.staff_response IS NOT NULL;"}, {"role": "user", "content": "The query is missing the staff member who responded. Can you include their first and last name?"}, {"role": "assistant", "content": "SELECT r.review_id, p.property_name, r.review_date, r.response_date, s.first_name, s.last_name FROM hospitality_technology.reviews r JOIN hospitality_technology.properties p ON r.property_id = p.property_id JOIN hospitality_technology.staff s ON r.response_staff_id = s.staff_id WHERE r.rating_overall = 5 AND r.staff_response IS NOT NULL;"}, {"role": "user", "content": "Actually, I only need reviews from the last 6 months, ordered by review date in descending order."}, {"role": "assistant", "content": "SELECT r.review_id, p.property_name, r.review_date, r.response_date, s.first_name, s.last_name FROM hospitality_technology.reviews r JOIN hospitality_technology.properties p ON r.property_id = p.property_id JOIN hospitality_technology.staff s ON r.response_staff_id = s.staff_id WHERE r.rating_overall = 5 AND r.staff_response IS NOT NULL AND r.review_date >= NOW() - INTERVAL '6 months' ORDER BY r.review_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 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 )\nCREATE TABLE hospitality_technology.service_orders ( order_id text, reservation_id text, guest_id text, service_id text, staff_id_ordered text, staff_id_delivered text, order_timestamp timestamp, delivery_timestamp timestamp, quantity integer, unit_price numeric, total_price numeric, status text, notes text, bill_id text )\nCREATE TABLE hospitality_technology.reviews ( review_id 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"}