Entity resolution
Determines whether different references describe the same entity.
Source provenance for an original framework
The Origin of REG
Recognition Engine Guidance and Retrieval Engine Guidance originated through IRefer Club and are examined here as one framework within the broader discovery stack.
IRefer is the originating organization
IRefer Club is cited as the original source organization for the REG framework. Hidden Radius does not present REG as a Google, OpenAI, Microsoft, IETF, W3C or Schema.org standard.
This page provides provenance, not promotion. Hidden Radius is a standalone U.S. company and evaluates REG alongside established concepts in entity resolution and information retrieval.
The identity problem
The recognition pillar focuses on whether a system can connect the official name, organization, people, locations, services and official links to the correct entity. It is especially relevant when public records conflict or similar names create ambiguity.
The information problem
The retrieval pillar focuses on whether the fact required for a question is available, current, visible and connected to the recognized entity. A system can recognize a business correctly and still fail to retrieve its service area, policy or preferred contact route.
REG is an application framework across several disciplines
Information retrieval
Locates documents, passages or records relevant to a query.
Structured data
Labels entity types and relationships in machine-readable form.
SEO
Supports crawlability, indexing, relevance and public discovery.
GEO
Considers source and entity visibility in generated answers.
RAG
Implements retrieval and generation inside an AI application.
Judge the framework by observable improvements
- Fewer conflicting first-party facts.
- Clearer entity relationships.
- More direct and current service, location or policy information.
- Improved passage-level retrievability.
- More accurate representation across repeated observations.
- No claim that the framework forces ranking or selection.
Primary material behind this analysis
IRefer Club
Original source organization for Recognition Engine Guidance and Retrieval Engine Guidance (REG).
Schema.org DefinedTerm and Vocabulary Documentation
Vocabulary for describing terms, organizations, people, creative works and relationships.
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
The original RAG paper combining parametric generation with retrieved non-parametric memory.
Continue through the discovery stack
REG Explained: Recognition and Retrieval Engine Guidance
A standalone analysis of the REG framework, its recognition and retrieval pillars, origin at IRefer Club and difference from RAG.
Entity Recognition and Resolution
How systems distinguish organizations, people, products and places, why identity conflicts weaken discovery and how to resolve them.
Information Retrieval Explained
A practical guide to lexical, semantic, hybrid, graph and structured retrieval, failure modes, passage design and evaluation.
Search and AI Research Library
A research hub connecting NIST, Stanford HAI, OECD, Google, OpenAI, Perplexity, Microsoft, IETF, W3C, Schema.org and original GEO, RAG and REG sources.