I need to check for duplicate and near-duplicate rows in this dataset. Let me start by examining exact duplicates based on the business key (Restaurant ID), then look for near-duplicates based on other identifying attributes. {"action": "tool_call", "reasoning": "First, I'll check if there are any duplicate Restaurant IDs, which should be unique identifiers for each restaurant.", "tool": "query_sql", "purpose": "Check for duplicate Restaurant IDs", "args": {"sql": "SELECT \"Restaurant ID\", COUNT(*) as occurrence_count FROM raw.\"Zomato Restaurant Dataset\" GROUP BY \"Restaurant ID\" HAVING COUNT(*) > 1 ORDER BY occurrence_count DESC LIMIT 50"}}