Triple

T656844

Position	Surface form	Disambiguated ID	Type / Status
Subject	Library of Congress authority record	`E11666`	entity
Predicate	usedIn	`P98`	FINISHED
Object	Library of Congress Linked Data Service The Library of Congress Linked Data Service is an online platform that publishes the Library of Congress’s controlled vocabularies and authority data in machine-readable linked data formats for use in cataloging and semantic web applications.	`E82115`	NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini

Instruction

Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).

Input

Phrase: Library of Congress Linked Data Service | Statement: [Library of Congress authority record, usedIn, Library of Congress Linked Data Service]

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07

Target entity: Library of Congress Linked Data Service
Context triple: [Library of Congress authority record, usedIn, Library of Congress Linked Data Service]

A. Library of Congress Online Catalog
The Library of Congress Online Catalog is the digital search system that provides public access to the Library of Congress’s vast collections of books, recordings, photographs, maps, and other materials.
B. BIBFRAME
BIBFRAME (Bibliographic Framework) is a linked data model and standard developed by the Library of Congress to replace MARC for describing and sharing bibliographic information on the web.
C. Open Library project
The Open Library project is an online initiative to create a comprehensive, publicly accessible catalog of every book ever published, offering digital borrowing and reading where possible.
D. Library of Congress authority record
A Library of Congress authority record is a standardized cataloging entry that establishes the authorized form of names, subjects, and titles to ensure consistent identification and retrieval of bibliographic information.
E. Wikidata
Wikidata is a collaboratively edited, multilingual knowledge base that provides structured data to support Wikipedia and other Wikimedia projects.
F. None of above. chosen
G. Unsure - the case is ambiguous/there is not enough information to decide.

NEDg Description generation gpt-5.1

Instruction

Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"

Input

Entity: Library of Congress Linked Data Service
Triple: [Library of Congress authority record, usedIn, Library of Congress Linked Data Service]

Generated description

The Library of Congress Linked Data Service is an online platform that publishes the Library of Congress’s controlled vocabularies and authority data in machine-readable linked data formats for use in cataloging and semantic web applications.

NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07

Target entity: Library of Congress Linked Data Service
Target entity description: The Library of Congress Linked Data Service is an online platform that publishes the Library of Congress’s controlled vocabularies and authority data in machine-readable linked data formats for use in cataloging and semantic web applications.

A. Library of Congress Online Catalog
The Library of Congress Online Catalog is the digital search system that provides public access to the Library of Congress’s vast collections of books, recordings, photographs, maps, and other materials.
B. BIBFRAME
BIBFRAME (Bibliographic Framework) is a linked data model and standard developed by the Library of Congress to replace MARC for describing and sharing bibliographic information on the web.
C. Open Library project
The Open Library project is an online initiative to create a comprehensive, publicly accessible catalog of every book ever published, offering digital borrowing and reading where possible.
D. Library of Congress authority record
A Library of Congress authority record is a standardized cataloging entry that establishes the authorized form of names, subjects, and titles to ensure consistent identification and retrieval of bibliographic information.
E. Wikidata
Wikidata is a collaboratively edited, multilingual knowledge base that provides structured data to support Wikipedia and other Wikimedia projects.
F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step	Stage	Batch ID	Status	When
creating	Elicitation	`batch_69a4932862a0819098be659c814e4981`	completed	March 1, 2026, 7:27 p.m.
NER	Named-entity recognition	`batch_69a49f4e87408190b5276d2b913d0426`	completed	March 1, 2026, 8:19 p.m.
NED1	Entity disambiguation (via context triple)	`batch_69a5914abe2c8190a27f520f445554d8`	completed	March 2, 2026, 1:31 p.m.
NEDg	Description generation	`batch_69a5ab066d348190bbe5956cce0407ef`	completed	March 2, 2026, 3:21 p.m.
NED2	Entity disambiguation (via description)	`batch_69a5c240eebc819098cd79447ed95b08`	completed	March 2, 2026, 5 p.m.

Created at: March 1, 2026, 7:36 p.m.