Triple
T37364189
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 100 Pct |
E927663
|
entity |
| Predicate | isPrecinctOf |
P117385
|
FINISHED |
| Object | New York City Police Department |
—
|
NE NERFINISHED |
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: New York City Police Department | Statement: [100 Pct, isPrecinctOf, New York City Police Department]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPrecinctOf Context triple: [100 Pct, isPrecinctOf, New York City Police Department]
-
A.
partOfPrecinct
chosen
Indicates that one entity is a subdivision or component contained within a specific precinct.
-
B.
isMajorPrecinctFor
Indicates that one entity serves as the primary or main precinct responsible for another entity within a given jurisdiction or context.
-
C.
hasInnerPrecinct
Indicates that one area, structure, or zone contains another, more central or enclosed precinct within its boundaries.
-
D.
hasNearbyPrecinct
Indicates that one location has a police precinct or similar administrative station situated close to it in geographic proximity.
-
E.
hasNumberedPrecinct
Indicates that an entity is associated with a specific precinct identified by a number.
- 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_69f76eb701788190b40824bc4594d985 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb8c38a9688190be524246f5682107 |
completed | May 6, 2026, 6:45 p.m. |
| PD | Predicate disambiguation | batch_69fb5a9c6e0481908565bd849e869b24 |
completed | May 6, 2026, 3:13 p.m. |
Created at: May 3, 2026, 4:16 p.m.