Identifique <strong>pessoas</strong>, <strong>organizações</strong>, <strong>locais</strong> e outras entidades nomeadas em qualquer texto. Roda localmente.
100% Privado. Seu texto nunca é enviado.
Roda completamente no seu navegador. Seus dados nunca saem do seu dispositivo.
BERT-base-NER clasifica cada token en BIO-tags (B-PER, I-PER, O, etc.) y agrupa entidades consecutivas.
The BERT-base-NER model extracts 4 entity types: PER (Person — names of people), ORG (Organization — companies, institutions), LOC (Location — cities, countries, landmarks), and MISC (Miscellaneous — other proper nouns like titles, events, products).
No. The NER model runs entirely in your browser using WebAssembly. Your text never leaves your device. The ~108MB model downloads once from CDN and caches locally in IndexedDB.
BERT-base-NER achieves ~89% F1-score on the CoNLL-2003 benchmark for 4-class NER. Performance may vary for short text, informal writing, or non-English content.
Yes. Copy entities as JSON (with text, type, confidence, start/end positions) or CSV for spreadsheet analysis.