Upload data.jsonl with huggingface_hub

data.jsonl

@@ -96,6 +96,7 @@
 {"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 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.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)\n", "conversations": [{"role": "user", "content": "List appointment IDs, patient first and last names, and their chief complaint for appointments that have an associated medical record."}, {"role": "assistant", "content": "SELECT a.appointment_id, p.first_name, p.last_name, mr.chief_complaint\nFROM healthcare.appointments a\nJOIN healthcare.medical_records mr\n  ON a.appointment_id = mr.appointment_id\nJOIN healthcare.patients p\n  ON a.patient_id = p.patient_id;"}, {"role": "user", "content": "Also include the appointment_time and only include records from the past 30 days."}, {"role": "assistant", "content": "SELECT a.appointment_id, p.first_name, p.last_name, mr.chief_complaint, a.appointment_time\nFROM healthcare.appointments a\nJOIN healthcare.medical_records mr\n  ON a.appointment_id = mr.appointment_id\nJOIN healthcare.patients p\n  ON a.patient_id = p.patient_id\nWHERE mr.record_date >= NOW() - INTERVAL '30 days';"}]}
 {"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 healthcare.patients (\n    patient_id character varying(64) NOT NULL,  -- unique identifier for the patient\n    first_name character varying(100) NOT NULL, -- patient's first name\n    last_name character varying(100) NOT NULL, -- patient's last name\n    date_of_birth date NOT NULL, -- patient's date of birth\n    gender character varying(10), -- patient's gender (e.g., Male, Female, Other)\n    address text, -- patient's home address\n    phone_number character varying(20), -- patient's phone number\n    email character varying(128) UNIQUE, -- patient's email address\n    emergency_contact_name character varying(200), -- name of emergency contact\n    emergency_contact_phone character varying(20), -- phone number of emergency contact\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n    PRIMARY KEY (patient_id)\n)\nCREATE TABLE healthcare.doctors (\n    doctor_id character varying(64) NOT NULL,  -- unique identifier for the doctor\n    first_name character varying(100) NOT NULL, -- doctor's first name\n    last_name character varying(100) NOT NULL, -- doctor's last name\n    specialty character varying(100) NOT NULL, -- doctor's medical specialty\n    license_number character varying(50) UNIQUE NOT NULL, -- doctor's medical license number\n    phone_number character varying(20), -- doctor's contact phone\n    email character varying(128) UNIQUE, -- doctor's contact email\n    hospital_affiliation_id character varying(64), -- FK to hospitals table (optional)\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (doctor_id)\n)\nCREATE TABLE healthcare.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table\n    appointment_time timestamp with time zone NOT NULL, -- date and time of the appointment\n    duration_minutes integer NOT NULL, -- expected duration in minutes\n    reason text, -- reason for the visit\n    status character varying(32) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-show\n    location_id character varying(64), -- FK to a potential locations/clinics table\n    notes text, -- notes related to scheduling\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (appointment_id)\n)\nCREATE TABLE healthcare.medical_records (\n    record_id character varying(64) NOT NULL,  -- unique identifier for the medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n    record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n    chief_complaint text, -- patient's primary reason for visit\n    present_illness_history text, -- detailed history of the current issue\n    past_medical_history text, -- relevant past conditions/surgeries\n    physical_examination_notes text, -- findings from the physical exam\n    assessment text, -- doctor's assessment/diagnosis summary\n    treatment_plan text, -- planned course of action\n    vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (record_id)\n)\nCREATE TABLE healthcare.diagnoses (\n    diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n    record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n    diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n    code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n    description text, -- textual description of the diagnosis\n    diagnosis_date date NOT NULL, -- date the diagnosis was made\n    status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n    is_chronic boolean DEFAULT false, -- flag for chronic conditions\n    PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.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.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 a list of all appointments and the number of prescriptions that were issued on the same day for each appointment."}, {"role": "assistant", "content": "SELECT a.appointment_id, a.appointment_time::date AS appointment_date,\n       COUNT(pr.prescription_id) AS prescriptions_count\nFROM healthcare.appointments a\nLEFT JOIN healthcare.medical_records mr ON mr.appointment_id = a.appointment_id\nLEFT JOIN healthcare.prescriptions pr ON pr.record_id = mr.record_id\nGROUP BY a.appointment_id, a.appointment_time::date;"}, {"role": "user", "content": "Only include appointments where at least one prescription was made that day, and show the full names of the patient and doctor for each appointment."}, {"role": "assistant", "content": "SELECT a.appointment_id, a.appointment_time::date AS appointment_date,\n       p.first_name || ' ' || p.last_name AS patient_full_name,\n       d.first_name || ' ' || d.last_name AS doctor_full_name,\n       COUNT(pr.prescription_id) AS prescriptions_count\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\nLEFT JOIN healthcare.medical_records mr ON mr.appointment_id = a.appointment_id\nLEFT JOIN healthcare.prescriptions pr ON pr.record_id = mr.record_id\nGROUP BY a.appointment_id, a.appointment_time::date, p.first_name, p.last_name, d.first_name, d.last_name\nHAVING COUNT(pr.prescription_id) > 0;"}]}
 {"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 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)\n", "conversations": [{"role": "user", "content": "List the description and diagnosis date for all diagnoses that are marked as chronic and were made in the year 2023."}, {"role": "assistant", "content": "SELECT description, diagnosis_date FROM healthcare.diagnoses WHERE is_chronic = true AND diagnosis_date BETWEEN '2023-01-01' AND '2023-12-31';"}, {"role": "user", "content": "Also include the patient ID and order the results by diagnosis date ascending."}, {"role": "assistant", "content": "SELECT patient_id, description, diagnosis_date FROM healthcare.diagnoses WHERE is_chronic = true AND diagnosis_date BETWEEN '2023-01-01' AND '2023-12-31' ORDER BY diagnosis_date 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\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.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.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 prescriptions with medication details. Return prescription_id, patient full name, medication_name, and prescription_date."}, {"role": "assistant", "content": "SELECT pr.prescription_id,\n       p.first_name || ' ' || p.last_name AS patient_name,\n       m.medication_name,\n       pr.prescription_date\nFROM healthcare.prescriptions pr\nJOIN healthcare.patients p ON pr.patient_id = p.patient_id\nJOIN healthcare.medications m ON pr.medication_id = m.medication_id;"}, {"role": "user", "content": "Filter to only include prescriptions where the quantity_dispensed is greater than 30."}, {"role": "assistant", "content": "SELECT pr.prescription_id,\n       p.first_name || ' ' || p.last_name AS patient_name,\n       m.medication_name,\n       pr.prescription_date\nFROM healthcare.prescriptions pr\nJOIN healthcare.patients p ON pr.patient_id = p.patient_id\nJOIN healthcare.medications m ON pr.medication_id = m.medication_id\nWHERE pr.quantity_dispensed > 30;"}]}
 {"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 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.medical_records ( record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, appointment_id character varying(64) UNIQUE, doctor_id character varying(64) NOT NULL, record_date timestamp with time zone NOT NULL, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals jsonb, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (record_id) )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.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 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 patient's first and last name along with the insurance plan name they are enrolled in, including only primary policies. Return patient_id, first_name, last_name, and plan_name."}, {"role": "assistant", "content": "SELECT p.patient_id,\n       p.first_name,\n       p.last_name,\n       ip.plan_name\nFROM healthcare.patients AS p\nJOIN healthcare.patient_insurance AS pi\n  ON p.patient_id = pi.patient_id AND pi.is_primary = true\nJOIN healthcare.insurance_plans AS ip ON pi.plan_id = ip.plan_id;"}, {"role": "user", "content": "Now limit to plans with plan_type 'EPO' and sort by patient last name ascending."}, {"role": "assistant", "content": "SELECT p.patient_id,\n       p.first_name,\n       p.last_name,\n       ip.plan_name\nFROM healthcare.patients AS p\nJOIN healthcare.patient_insurance AS pi\n  ON p.patient_id = pi.patient_id AND pi.is_primary = true\nJOIN healthcare.insurance_plans AS ip ON pi.plan_id = ip.plan_id\nWHERE ip.plan_type = 'EPO'\nORDER BY p.last_name 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\nCREATE TABLE healthcare.doctors ( doctor_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, specialty character varying(100) NOT NULL, license_number character varying(50) UNIQUE NOT NULL, phone_number character varying(20), email character varying(128) UNIQUE, hospital_affiliation_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (doctor_id) )\nCREATE TABLE healthcare.medical_records ( record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, appointment_id character varying(64) UNIQUE, doctor_id character varying(64) NOT NULL, record_date timestamp with time zone NOT NULL, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals jsonb, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (record_id) )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\n", "conversations": [{"role": "user", "content": "Show a list of diagnoses along with the chief complaint noted in the corresponding medical record. Display diagnosis description, diagnosis date, and the chief complaint."}, {"role": "assistant", "content": "SELECT T1.description, T1.diagnosis_date, T2.chief_complaint FROM healthcare.diagnoses AS T1 JOIN healthcare.medical_records AS T2 ON T1.record_id = T2.record_id;"}]}
 {"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 healthcare.diagnoses ( diagnosis_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, diagnosis_code character varying(20) NOT NULL, code_type character varying(10) NOT NULL DEFAULT 'ICD-10', description text, diagnosis_date date NOT NULL, status character varying(32) NOT NULL, is_chronic boolean DEFAULT false, PRIMARY KEY (diagnosis_id) )\nCREATE TABLE healthcare.prescriptions ( prescription_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, medication_id character varying(64) NOT NULL, dosage character varying(100) NOT NULL, frequency character varying(100) NOT NULL, route character varying(50), start_date date NOT NULL, end_date date, quantity_dispensed numeric(10,2), refills_allowed integer NOT NULL DEFAULT 0, prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (prescription_id) )\nCREATE TABLE healthcare.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 each patient's policy number, the associated insurance plan ID, and any medications they have been prescribed, including the medication ID and prescription date."}, {"role": "assistant", "content": "SELECT pi.patient_id, pi.policy_number, pi.plan_id, pr.medication_id, pr.prescription_date\nFROM healthcare.patient_insurance pi\nJOIN healthcare.prescriptions pr ON pi.patient_id = pr.patient_id;"}, {"role": "user", "content": "Only include prescriptions that were made after the insurance policy's effective date."}, {"role": "assistant", "content": "SELECT pi.patient_id, pi.policy_number, pi.plan_id, pr.medication_id, pr.prescription_date\nFROM healthcare.patient_insurance pi\nJOIN healthcare.prescriptions pr ON pi.patient_id = pr.patient_id\nWHERE pr.prescription_date >= pi.effective_date;"}, {"role": "user", "content": "Add the expiration date of the insurance policy and only show records where the prescription was made before the policy expired."}, {"role": "assistant", "content": "SELECT pi.patient_id, pi.policy_number, pi.plan_id, pi.expiration_date, pr.medication_id, pr.prescription_date\nFROM healthcare.patient_insurance pi\nJOIN healthcare.prescriptions pr ON pi.patient_id = pr.patient_id\nWHERE pr.prescription_date >= pi.effective_date\n  AND (pi.expiration_date IS NULL OR pr.prescription_date < pi.expiration_date);"}]}
@@ -212,7 +213,6 @@
 {"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 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 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 web3.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\n", "conversations": [{"role": "user", "content": "For each user, what is the average time difference in days between their wallet creations? Return user_id and avg_diff_days."}, {"role": "assistant", "content": "WITH diffs AS (\n  SELECT\n    user_id,\n    EXTRACT(EPOCH FROM (created_at - LAG(created_at) OVER (PARTITION BY user_id ORDER BY created_at))) / 86400 AS diff_days\n  FROM web3.wallets\n)\nSELECT\n  user_id,\n  AVG(diff_days) AS avg_diff_days\nFROM diffs\nWHERE diff_days IS NOT NULL\nGROUP BY user_id;"}, {"role": "user", "content": "Actually, only include users who have created more than 2 wallets."}, {"role": "assistant", "content": "WITH diffs AS (\n  SELECT\n    user_id,\n    EXTRACT(EPOCH FROM (created_at - LAG(created_at) OVER (PARTITION BY user_id ORDER BY created_at))) / 86400 AS diff_days\n  FROM web3.wallets\n)\nSELECT\n  user_id,\n  AVG(diff_days) AS avg_diff_days\nFROM diffs\nWHERE diff_days IS NOT NULL\nGROUP BY user_id\nHAVING COUNT(diff_days) > 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\nCREATE TABLE web3.contracts ( contract_id text PRIMARY KEY, address text, abi text, bytecode text, deployer_address text, deployed_at timestamp, network_id text, status text )\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 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 )\nCREATE TABLE web3.tokens ( token_id.text, contract_address.text, token_name.text, token_symbol.text, decimals.integer, total_supply.numeric )\nCREATE TABLE web3.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, created_at timestamp )\n", "conversations": [{"role": "user", "content": "List all failed transactions along with the from and to addresses, and the gas used."}, {"role": "assistant", "content": "SELECT transaction_id, from_address, to_address, gas_used FROM web3.transactions WHERE status = 'failed';"}, {"role": "user", "content": "Actually, I also need to see the block number and timestamp for these failed transactions."}, {"role": "assistant", "content": "SELECT transaction_id, from_address, to_address, gas_used, block_number, timestamp FROM web3.transactions WHERE status = 'failed';"}, {"role": "user", "content": "There's a typo in your SQL, it should be 'timestamp' not 'timestamp'. Also, sort the results by block number in descending order."}, {"role": "assistant", "content": "SELECT transaction_id, from_address, to_address, gas_used, block_number, timestamp FROM web3.transactions WHERE status = 'failed' ORDER BY block_number DESC;"}, {"role": "user", "content": "Now filter to only show transactions with gas used greater than 100,000."}, {"role": "assistant", "content": "SELECT transaction_id, from_address, to_address, gas_used, block_number, timestamp FROM web3.transactions WHERE status = 'failed' AND gas_used > 100000 ORDER BY block_number DESC;"}]}
-{"system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE web3.token_transfers ( transfer_id text, token_id text, from_address text, to_address text, value numeric, transaction_id text, log_index integer )\n", "conversations": [{"role": "user", "content": "For each transaction, show its transaction_id and the count of tokens transferred within that transaction."}, {"role": "assistant", "content": "SELECT transaction_id, COUNT(token_id) AS tokens_transferred FROM web3.token_transfers GROUP BY transaction_id;"}]}
 {"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 web3.wallets ( wallet_id text PRIMARY KEY, user_id text, address text, private_key text, created_at timestamp )\n", "conversations": [{"role": "user", "content": "Find pairs of wallets that were created at the exact same timestamp but are owned by different users. List the IDs of both wallets and the shared creation timestamp."}, {"role": "assistant", "content": "SELECT\n    w1.wallet_id AS wallet1_id,\n    w2.wallet_id AS wallet2_id,\n    w1.created_at\nFROM\n    web3.wallets w1\nJOIN\n    web3.wallets w2 ON w1.created_at = w2.created_at\nWHERE\n    w1.wallet_id < w2.wallet_id\n    AND w1.user_id != w2.user_id;"}]}
 {"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 web3.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\n", "conversations": [{"role": "user", "content": "Find pairs of users who registered on the same weekday but in different years. List the user ID and registration date for both users, and the weekday name."}, {"role": "assistant", "content": "SELECT u1.user_id, u1.created_at AS user1_created_at, u2.user_id, u2.created_at AS user2_created_at, TO_CHAR(u1.created_at, 'Day') AS registration_weekday FROM web3.users u1 JOIN web3.users u2 ON TO_CHAR(u1.created_at, 'Day') = TO_CHAR(u2.created_at, 'Day') AND EXTRACT(YEAR FROM u1.created_at) <> EXTRACT(YEAR FROM u2.created_at) AND u1.user_id < u2.user_id ORDER BY TO_CHAR(u1.created_at, 'D'), u1.created_at;"}]}
 {"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 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": "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;"}]}
@@ -247,4 +247,4 @@
 {"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 healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.doctors ( doctor_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, specialty character varying(100) NOT NULL, license_number character varying(50) UNIQUE NOT NULL, phone_number character varying(20), email character varying(128) UNIQUE, hospital_affiliation_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (doctor_id) )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, diagnosis_code character varying(20) NOT NULL, code_type character varying(10) NOT NULL DEFAULT 'ICD-10', description text, diagnosis_date date NOT NULL, status character varying(32) NOT NULL, is_chronic boolean DEFAULT false, PRIMARY KEY (diagnosis_id) )\nCREATE TABLE healthcare.medications ( medication_id character varying(64) NOT NULL, medication_name character varying(255) NOT NULL, generic_name character varying(255), manufacturer character varying(100), ndc_code character varying(20) UNIQUE, description text, PRIMARY KEY (medication_id) )\nCREATE TABLE healthcare.insurance_plans ( plan_id character varying(64) NOT NULL, plan_name character varying(200) NOT NULL, insurance_provider character varying(100) NOT NULL, plan_type character varying(50), contact_phone character varying(20), website character varying(255), PRIMARY KEY (plan_id) )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n", "conversations": [{"role": "user", "content": "Which patients have a primary insurance policy and are subscribed to a plan provided by 'Cigna'? List patient ID, full name, policy number, plan ID, and insurance provider."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name, p.last_name, pi.policy_number, pi.plan_id, ip.insurance_provider\nFROM healthcare.patient_insurance pi\nJOIN healthcare.patients p ON pi.patient_id = p.patient_id\nJOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id\nWHERE pi.is_primary = true AND ip.insurance_provider = 'Cigna';"}, {"role": "user", "content": "Additionally, only show results where the policy has not expired yet."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name, p.last_name, pi.policy_number, pi.plan_id, ip.insurance_provider\nFROM healthcare.patient_insurance pi\nJOIN healthcare.patients p ON pi.patient_id = p.patient_id\nJOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id\nWHERE pi.is_primary = true AND ip.insurance_provider = 'Cigna' AND (pi.expiration_date IS NULL OR pi.expiration_date >= CURRENT_DATE);"}]}
 {"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 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.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.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.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 )\nCREATE TABLE legal_services.appointments ( appointment_id text, client_id text, lawyer_id text, case_id text, start_time timestamp, end_time timestamp, location text, subject text, notes text, status text, created_at timestamp )\n", "conversations": [{"role": "user", "content": "I need a list showing the name of each law firm and the full name of every lawyer employed by that firm."}, {"role": "assistant", "content": "SELECT T1.firm_name, T2.first_name, T2.last_name FROM law_firms AS T1 JOIN lawyers AS T2 ON T1.firm_id = T2.firm_id;"}]}
 {"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 financial_services.customers ( customer_id text, first_name text, last_name text, date_of_birth date, ssn_hash text, address text, city text, state text, zip_code text, country text, email text, phone_number text, created_at timestamp, status text, risk_profile text )\n", "conversations": [{"role": "user", "content": "Show me all customers (customer_id, first_name, last_name, email) who were born after 1985 (date_of_birth > '1985-12-31') and have an email address ending with '@yahoo.com', along with their city and state information."}, {"role": "assistant", "content": "SELECT customer_id, first_name, last_name, email, city, state FROM financial_services.customers WHERE date_of_birth > '1985-12-31' AND email LIKE '%@yahoo.com';"}]}
-{"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 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": "Find all service locations whose postal code starts with '75' and display their names, cities, and operating hours, including the agency ID."}, {"role": "assistant", "content": "SELECT location_name, city, operating_hours, agency_id FROM government_services.service_locations WHERE postal_code LIKE '75%';"}]}
+{"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 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": "Retrieve all active SUI coins with their owner, balance, symbol, and name."}, {"role": "assistant", "content": "SELECT sc.owner, sc.coin_type, sc.balance, scm.symbol, scm.name\nFROM sui_coins sc\nJOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type\nWHERE sc.status = 'active';"}, {"role": "user", "content": "Now filter to balances greater than 1000 and include only metadata entries where status is 'exists'."}, {"role": "assistant", "content": "SELECT sc.owner, sc.coin_type, sc.balance, scm.symbol, scm.name\nFROM sui_coins sc\nJOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type\nWHERE sc.status = 'active'\n  AND scm.status = 'exists'\n  AND CAST(sc.balance AS numeric) > 1000;"}, {"role": "user", "content": "Sort the results by balance descending."}, {"role": "assistant", "content": "SELECT sc.owner, sc.coin_type, sc.balance, scm.symbol, scm.name\nFROM sui_coins sc\nJOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type\nWHERE sc.status = 'active'\n  AND scm.status = 'exists'\n  AND CAST(sc.balance AS numeric) > 1000\nORDER BY CAST(sc.balance AS numeric) DESC;"}, {"role": "user", "content": "Finally, limit to the top 10 records and include the description from metadata."}, {"role": "assistant", "content": "SELECT sc.owner, sc.coin_type, sc.balance, scm.symbol, scm.name, scm.description\nFROM sui_coins sc\nJOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type\nWHERE sc.status = 'active'\n  AND scm.status = 'exists'\n  AND CAST(sc.balance AS numeric) > 1000\nORDER BY CAST(sc.balance AS numeric) DESC\nLIMIT 10;"}]}