skills.rest
Tzeusy
TzeusyCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

fact-extraction

Resolve person and organization mentions into entities and store facts.

Updated Feb 9, 2026
Search Tags:#knowledge graph#memory management#conversational AI#fact extraction#entity resolution#relationship mapping
One-click install
npx skills add https://github.com/Tzeusy/butlers --skill fact-extraction
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: fact-extraction
Source: https://github.com/Tzeusy/butlers/tree/main/roster/relationship/.agents/skills/fact-extraction
Command: npx skills add https://github.com/Tzeusy/butlers --skill fact-extraction

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the process of identifying, resolving, and storing factual information about people and organizations mentioned in conversations, ensuring a consistent and accurate knowledge base.

Core Features & Use Cases

  • Entity Resolution: Accurately identifies and disambiguates mentions of people and organizations.
  • Fact Storage: Extracts and stores relationship-based facts (e.g., "works at", "friend of") and property-based facts (e.g., "birthday", "preference").
  • Use Case: When a user mentions "Sarah started at Google," this Skill will identify "Sarah" and "Google" as entities, store the "works at" relationship, and log the event for future reference.

Quick Start

Use the fact-extraction skill to process the message "John and Lisa are siblings."

Frequently Asked Questions about fact-extraction

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract facts and relationship mappings from conversational AI text?▼

Fact extraction in conversational AI uses a 7-step pipeline to identify people and organizations, resolve entity mentions through disambiguation policies, and store relationship-based or property-based facts into a knowledge base.

How does entity resolution work for unknown individuals mentioned in a conversation?▼

Entity resolution handles unknown individuals by applying disambiguation policies during the extraction pipeline. If a person or organization is truly new, the Skill creates a new entity record to accurately map and log the mention.

Can I store property-based facts like birthdays alongside relationship mappings?▼

Yes, you can store property-based facts like birthdays alongside relationship mappings. The Skill extracts and logs both types of factual information, updating domain records to maintain a consistent knowledge base.

What is the best way to build a knowledge graph from unstructured dialogue?▼

Building a knowledge graph from unstructured dialogue is best handled by an orchestrated extraction pipeline. This Skill processes conversational messages, resolves entities, extracts facts, and logs interactions to enrich domain records.

Does this fact extraction pipeline support question answering flows?▼

Yes, the fact extraction pipeline supports question answering flows. It orchestrates conversational interactions to resolve person mentions, apply disambiguation policies, extract facts, and log events while updating domain records.

Related Skills

Explore More Software Engineering Skills→
inbrainfuninbrainfun
174

meeting-ingestion

Parse meeting transcripts into brain pages with attendee enrichment and timeline merge.

Community
Advanced
wosnatwosnat

cypher-queries

Run Cypher queries against a Neo4j knowledge graph using prepared templates.

Community
Advanced
bizzybaebizzybae

open-gstack-browser

Launch GStack Browser with a live activity feed and sidebar chat.

Community
Intermediate
vignesh2027vignesh2027
6

knowledge-graph-builder

Turn unstructured documents into queryable knowledge graphs with entity extraction and relationship mapping.

Community
Advanced