Triple
T27656191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brooklyn-Queens Expressway triple cantilever structure |
E696997
|
entity |
| Predicate | sitsAtBaseOf |
P15591
|
FINISHED |
| Object | Brooklyn Heights bluff |
—
|
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: Brooklyn Heights bluff | Statement: [Brooklyn-Queens Expressway triple cantilever structure, sitsAtBaseOf, Brooklyn Heights bluff]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sitsAtBaseOf Context triple: [Brooklyn-Queens Expressway triple cantilever structure, sitsAtBaseOf, Brooklyn Heights bluff]
-
A.
locatedAtBaseOf
chosen
Indicates that one entity is positioned at or near the bottom or lowest supporting part of another entity.
-
B.
sitsAtop
Indicates that one entity is positioned directly on top of another, typically resting upon its upper surface.
-
C.
seatOrBase
Indicates that one entity serves as the seat, base, or supporting foundation for another entity.
-
D.
sitsAbove
Indicates that one entity is positioned directly higher than and vertically over another entity.
-
E.
hasPlinth
Indicates that one object is supported by or mounted on a plinth (a base or pedestal).
- 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_69ef590abd3c8190834d0193bde12007 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f631d8bb9881908a1b01a501d96cfc |
completed | May 2, 2026, 5:18 p.m. |
| PD | Predicate disambiguation | batch_69f62c1a92648190835a2c5250d8c758 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:34 p.m.