Organise

Reference & Citation Resolution

Turn dead-text references into live, traversable links.

Finds citations, name mentions, hyperlinks, and footnote pointers inside content, then looks each up against an authority — CrossRef, ORCID, an internal entity registry — and writes back a canonical identifier. References stop being dead strings and become structured, navigable links your systems can traverse and your users can follow.

Shape

Operational dimensions

No human in loop

Runs without a person in the path.

Event-triggered

Fires when an upstream condition occurs.

Medium data gravity

Holds working state that compounds over runs.

Two-way integration

Reads from and writes to external systems.

Inputs

content with embedded references (citations, mentions, links, footnotes)
reference grammar / parser config
target authority or entity registry
disambiguation rules or model

Outputs

structured reference links (canonical id + confidence + provenance per mention)
unresolved / ambiguous mention exceptions
updated content with embedded structured identifiers

Mechanism

Resolves textual mentions, citation strings, links, or footnote pointers to canonical identifiers in a target authority — turning unstructured references into structured links.

Why this is a primitive

Cannot be decomposed: the parse-mention → candidate-lookup → disambiguate → bind-to-canonical-id operation over reference strings is one act of linking. It is distinct from entity-resolution (which works on full records, not in-text mentions) and from classification (which assigns categories, not authority links). Strip it and references stay as free text.

Where it shows up

Academic publisher — resolves citation strings in submitted manuscripts to DOIs and ORCID author ids so the reference graph is machine-traversable at publication

Policy analysis firm — links legislation mentions in briefing documents to official statute identifiers so analysts can navigate from report to law in one click

Biomedical platform — resolves gene, protein, and compound mentions in research papers to canonical database ids (UniProt, ChEMBL) for downstream graph queries

Internal knowledge base — resolves @mentions and document references across wiki pages to canonical team-member and asset ids so stale links surface as exceptions

Related primitives

Composes with

Controlled Vocabulary Authoring →Schema Normalisation →Entity Resolution & Record Linkage →Knowledge Graph Instantiation →Classification Application →

Alternative to

Entity Resolution & Record Linkage →