SQL query generator from a plain-English request

**Assumptions**

- `order_items.order_id` joins to `orders.id`, and `products.category_id` joins to `categories.id`. These are inferred from the naming convention, since no foreign keys were listed.
- "Last 90 days" is measured against `orders.order_date` relative to today, inclusive of today.
- Revenue is `quantity * unit_price` summed over line items; there is no discount or tax column in the schema, so none is applied.
- Cancelled orders are excluded. If `status` uses different values than `'cancelled'`, adjust the filter.
- `COUNT(DISTINCT o.id)` is used rather than `COUNT(*)` because the join to `order_items` multiplies order rows by line item.

**Query**

```sql
SELECT c.name AS category,
       COUNT(DISTINCT o.id) AS order_count,
       SUM(oi.quantity * oi.unit_price) AS total_revenue
FROM orders AS o
JOIN order_items AS oi ON oi.order_id = o.id
JOIN products AS p ON p.id = oi.product_id
JOIN categories AS c ON c.id = p.category_id
WHERE o.order_date >= CURRENT_DATE - INTERVAL '90 days'
  AND o.status <> 'cancelled'
GROUP BY c.id, c.name
HAVING COUNT(DISTINCT o.id) > 50
ORDER BY total_revenue DESC;
```

Grouping by `c.id` as well as `c.name` keeps the result correct if two categories share a display name. If `order_date` is a timestamp rather than a date, cast it (`o.order_date::date`) or the boundary day will be partially excluded.