OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

spaCy fishing

spaCy fishing is a Python library that wraps Entity-Fishing as a spaCy pipeline component, disambiguating named entities and linking them to Wikidata.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

spaCy fishing — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a spaCy workflow needs to resolve recognized entity mentions to Wikidata records and pass those links or associated metadata to later processing.

Who it is for

  • Developers building spaCy text-processing pipelines that need entity disambiguation or Wikidata identifiers.
  • NLP practitioners using pretrained or custom spaCy named-entity recognition models.

Documented uses

  • Attach Wikidata QIDs, URLs and scores to recognized entity mentions.
  • Retrieve additional entity descriptions, standardized terms or related knowledge-base identifiers.
  • Process multiple texts through a spaCy pipeline.
Before you choose

Requirements & limits

  • The documented workflow requires spaCy and a pretrained or custom NER model; the README's example uses the English en_core_web_sm model.
  • English is the default disambiguation-resource language; the documentation describes specifying another language.
  • The component's default span attributes include a Wikidata QID, URL and score; extra_info enables additional fields.
  • The repository identifies the library as MIT-licensed.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Add Wikidata entity linking to a spaCy pipeline

Process text with a spaCy NER model and attach Wikidata identifiers, URLs, and disambiguation scores to detected entities.

Before you start

  • Python 3.7 or later, as indicated by the repository’s Python version badge.
  • The spacyfishing package and spaCy installed.
  • A pretrained spaCy language model for NER, or a custom NER model.

Steps

  1. Install the component with the command below.

    Documented command
    pip install spacyfishing

  2. Install a pretrained spaCy model for NER; the documented English example uses the command below.

    Documented command
    python -m spacy download en_core_web_sm

  3. Load the model with spacy.load("en_core_web_sm") and add the component using nlp_model.add_pipe("entityfishing").

  4. Pass text to the pipeline, then inspect doc.ents and each entity’s ent._.kb_qid, ent._.url_wikidata, and ent._.nerd_score attributes.

Expected outcome

The pipeline’s detected entities are linked and disambiguated against Wikidata, with a QID, Wikidata URL, and score attached to each entity span.

Guide limitations

  • The documented default attributes are the QID, Wikidata URL, and score; additional Wikidata information requires extra_info=True in the component configuration.
  • The README provides an example and sample output but does not establish that these results are guaranteed for other text or environments.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
Lucaterre/spacyfishing · Official homepage title · retained in its source language
How we review sourcesSuggest a correction