Triple
T48396
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Labor Relations Act |
E950
|
entity |
| Predicate | titleInUSCode |
P1119
|
FINISHED |
| Object | 29 U.S.C. §§ 151–169 |
—
|
LITERAL FINISHED |
How this triple was built (2 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: 29 U.S.C. §§ 151–169 | Statement: [National Labor Relations Act, titleInUSCode, 29 U.S.C. §§ 151–169]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titleInUSCode Context triple: [National Labor Relations Act, titleInUSCode, 29 U.S.C. §§ 151–169]
-
A.
titleOfU.S.Code
chosen
Indicates that a specified title number or name corresponds to a particular section or portion of the United States Code.
-
B.
title
Indicates that one entity serves as the formal name or designation of another entity.
-
C.
libraryOfCongressClassification
Indicates that one entity is assigned a Library of Congress Classification code that organizes it within the Library of Congress subject-based cataloging system.
-
D.
divisionTitles
Indicates that an entity holds or is associated with one or more titles or championships within a specific division or category.
-
E.
codifiedIn
Indicates that something is formally recorded, defined, or established within a specific document, code, or legal/institutional text.
- F. None of above.
Provenance (3 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_69a2480baefc81909951b14058479aa2 |
completed | Feb. 28, 2026, 1:42 a.m. |
| NER | Named-entity recognition | batch_69a24c1a5c14819088748317a3f262c8 |
completed | Feb. 28, 2026, 1:59 a.m. |
| PD | Predicate disambiguation | batch_69a24abe7cb481908d969e54032f6c75 |
completed | Feb. 28, 2026, 1:54 a.m. |
Created at: Feb. 28, 2026, 1:47 a.m.