Named Entity Recognizer
Spot every person, organization, location and other named entity in a piece of text. An AI model (bert-base-NER) reads your text and tags each entity, then the tool highlights them inline with a color per type, shows a legend, and counts how many of each it found. It runs entirely in your browser, so the text you paste is never uploaded. The model downloads once on first use, then is cached.
How to recognize named entities
- Paste the article, paragraph, or any text into the box.
- Click Find entities and wait a moment while the model loads on first use.
- Read your text with people, organizations and places highlighted, plus a per-type count.
Examples
Tagging a news sentence
Tim Cook said Apple will open a new store in Paris next spring.
Tim Cook (Person), Apple (Organization) and Paris (Location) highlighted inline, with a 1-each count.
Frequently asked questions
What is named entity recognition?
Named entity recognition (NER) is the task of finding and classifying the real-world entities mentioned in text, such as people, organizations and locations. This tool runs an AI model over your text and labels each entity it finds, then highlights them so you can see them at a glance.
Is my text uploaded anywhere?
No. Nothing is uploaded. The bert-base-NER model runs entirely in your browser via WebAssembly, so your text is analyzed on your device and never sent to a server. Only the model itself is downloaded, once, then cached.
Which entity types does it detect?
Four types from the bert-base-NER model: Person (PER), Organization (ORG), Location (LOC) and Miscellaneous (MISC), each shown in its own color. MISC covers named things that are not a person, org or place, such as nationalities, events or works.
Which AI model does this use?
It uses bert-base-NER, a BERT model fine-tuned on the CoNLL-2003 named-entity dataset. It runs locally in your browser through transformers.js and ONNX, with no API calls, and tags tokens that the tool merges into whole entities.
How accurate is it?
It is strong on well-formed English text and common names, but no NER model is perfect: it can miss unusual names, split or merge entities, or mislabel ambiguous words. Treat the highlights as a fast draft and verify anything important against the source.
Related tools
PII Redactor
Redact PII from text in your browser. AI finds names, orgs and places; regex catches emails, phones, cards, SSNs and IPs. Nothing uploaded.
AI Sentiment Analyzer
Analyze the sentiment of any text with AI in your browser. Paste a review or comment, get a positive or negative score plus a per-sentence breakdown.
AI Text Summarizer
Summarize any text with AI, right in your browser. Paste an article, pick a length, and get a short abstractive summary. Nothing is uploaded.
Acronym Generator
Turn any phrase into an acronym from the first letter of each main word. Skip small words like the and of, keep them, or add dot separators.
Add Line Numbers
Add line numbers to any text online. Set the start value, step, and separator, pad numbers to align, and copy or download the result. Free and private.
AI Translator
Translate text between 100 languages with AI in your browser. Pick a source and target language. Nothing is uploaded; works offline after setup.