Discover structured entities from the web with per-cell evidence
Examples:
Every cell links to a source URL, evidence snippet, and confidence
score.
Planning
Searching
Scraping
Reranking
Extracting
Merging
Gap-fill
Verifying
Starting…
Pipeline Error
Try a more specific query, or check server logs for details.
No entities found
The pipeline completed, but no stable candidates survived final
ranking and verification. Try adding a clearer entity type or
location, e.g. “best pizza restaurants in Manhattan”
rather than “food”.
0 rows0 URLs0 scraped0 extracted
Retrieval PlanQuality Controls AppliedRun Stats
Click any cell to view its source URL, evidence snippet, and
confidence score.
How it works
Normalize & Type — Clean the query, classify
its family, and choose a constrained schema
Search & Scrape — Multi-angle web search via
Brave, async scraping with caching
Rerank — Cross-encoder selects the most
query-relevant pages for extraction
Discover — Extract broad candidate entities
first, then fill missing attributes later
Canonicalize — Merge duplicates and prefer
official or canonical sources when they can be resolved
Rank & Verify — Score by evidence, source
quality, support, and diversity; prune obvious junk late