I need to check for duplicate rows across the tables in this dataset. Let me start by examining the largest tables for exact duplicates, then look for near-duplicates if needed. {"action": "tool_call", "reasoning": "Starting with the largest table (columns_catalog) to check for exact duplicate rows. I'll use GROUP BY on all key columns and look for rows that appear more than once.", "tool": "inspect_columns", "args": {"table": "columns_catalog", "columns": null}}