Triple
T275736
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York City government |
E5244
|
entity |
| Predicate | legislatureSize |
P7799
|
FINISHED |
| Object | 51-member city council |
—
|
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: 51-member city council | Statement: [New York City government, legislatureSize, 51-member city council]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legislatureSize Context triple: [New York City government, legislatureSize, 51-member city council]
-
A.
totalNumberOfLegislators
chosen
Indicates the total count of legislators associated with a given political body, jurisdiction, or legislative session.
-
B.
numberOfRepresentatives
Indicates the quantity of representatives associated with a given entity or unit.
-
C.
legislatureNumber
Indicates the specific numbered session or term of a legislative body associated with an entity or event.
-
D.
numberOfSenators
Indicates the total count of senators associated with a given political body, region, or entity.
-
E.
legislature
Indicates that an entity serves as, or is part of, a law-making body or assembly responsible for creating or amending laws for a political unit.
- 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_69a257e6c8788190987dfe705ca2912a |
completed | Feb. 28, 2026, 2:50 a.m. |
| NER | Named-entity recognition | batch_69a25dec53ac8190912f3d79576131fa |
completed | Feb. 28, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_69a25b7480e881909399beccfc7ffb81 |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 2:59 a.m.