Entity extractor
Which entities does a page surface? Extract them (Wikipedia/DBpedia), with their types, importance and relations.
Every page "talks about" a set of entities (places, brands, people, concepts) that search engines tie to their Knowledge Graph. This tool surfaces them, with their importance and links, to audit your pages' topical coverage.
How it works
- Paste a URL (fetched automatically) or the HTML directly if the site blocks fetching.
- Entities are detected and linked to Wikipedia and DBpedia.
- Each entity gets a type, an importance score and categories.
What you get
- The list of entities with their Wikipedia / DBpedia links.
- The key entities (importance) and the number of distinct types.
- Clusters by type, co-occurrences, and a CSV export.
Analyze a page
Go further with structured data
Check the same page's Schema.org markup with the structured data testing tool.
Privacy: the page text is sent to the Dandelion API (SpazioDati) for analysis. No data is stored beyond a temporary 1-hour cache.