Triple
T312734
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Library of Congress Subject Headings |
E7641
|
entity |
| Predicate | hasDataModel |
P535
|
FINISHED |
| Object | MARC 21 authority format |
E4784
|
NE FINISHED |
How this triple was built (3 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: MARC 21 authority format | Statement: [Library of Congress Subject Headings, hasDataModel, MARC 21 authority format]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MARC 21 authority format Context triple: [Library of Congress Subject Headings, hasDataModel, MARC 21 authority format]
-
A.
MARC
MARC is a commuter rail service in Maryland that connects Washington, D.C. with Baltimore and other regional destinations.
-
B.
MARC standards
chosen
MARC standards are a set of bibliographic data formats used worldwide to structure and exchange library catalog information in a consistent, machine-readable way.
-
C.
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.
-
D.
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.
-
E.
Library of Congress catalogers
Library of Congress catalogers are professional librarians and metadata specialists at the U.S. Library of Congress who create and maintain authoritative bibliographic records for materials in its collections.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDataModel Context triple: [Library of Congress Subject Headings, hasDataModel, MARC 21 authority format]
-
A.
dataModel
chosen
Indicates a relationship where an entity defines, uses, or is structured according to a specific data model or schema.
-
B.
hasModelType
Indicates that an entity is associated with or classified under a specific model type.
-
C.
hasMetadata
Indicates that one entity is associated with descriptive or informational data about another entity.
-
D.
hasTradingModel
Indicates that one entity uses, is governed by, or is associated with a particular trading model.
-
E.
hasView
Indicates that one entity provides a visual perspective or outlook onto another entity or scene.
- F. None of above.
Provenance (4 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_69a2e7e7af7881908890039d6be4e9b8 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ea4aa16881909b2c8404b85992df |
completed | Feb. 28, 2026, 1:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a3bc2963b48190b5bd7ac84c952486 |
completed | March 1, 2026, 4:10 a.m. |
| PD | Predicate disambiguation | batch_69a2e9428098819089d5950cd2c96dc4 |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:07 p.m.