kermitt2/entity-fishing
A machine learning tool for fishing entities
This tool helps you quickly identify and link specific entities, like people, organizations, or concepts, within text documents or search queries across 15 different languages. You input raw text, PDFs, or search terms, and it outputs a list of recognized entities linked to their corresponding Wikidata entries. It's ideal for researchers, analysts, or anyone who needs to extract structured information from large volumes of unstructured text.
270 stars.
Use this if you need to automatically find and connect specific terms in text to a comprehensive knowledge base like Wikidata, especially when dealing with various document types or short queries.
Not ideal if your primary need is general natural language processing tasks beyond entity recognition and disambiguation, or if you require real-time, ultra-low-latency processing for very high-volume, live data streams without any setup.
Stars
270
Forks
24
Language
Java
License
Apache-2.0
Category
Last pushed
Feb 27, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/kermitt2/entity-fishing"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
rosette-api/java
Babel Street Analytics Client Library for Java
vinhkhuc/JFastText
Java interface for fastText
CeON/CERMINE
Content ExtRactor and MINEr
vinhkhuc/jcrfsuite
Java interface for CRFsuite: http://www.chokkan.org/software/crfsuite/
TechPrimers/core-nlp-example
Natural Language Processing Example using Stanford's Core NLP Java Library