Triple
T28463318
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 182nd–183rd Streets (IND Concourse Line) |
E720218
|
entity |
| Predicate | hasPillarType |
P16808
|
FINISHED |
| Object | IND-style I-beam columns |
—
|
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: IND-style I-beam columns | Statement: [182nd–183rd Streets (IND Concourse Line), hasPillarType, IND-style I-beam columns]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPillarType Context triple: [182nd–183rd Streets (IND Concourse Line), hasPillarType, IND-style I-beam columns]
-
A.
recognizesPillar
Indicates that one entity acknowledges or identifies another entity as a fundamental support, key element, or core principle within a given context.
-
B.
hasBlueprintPillars
Indicates that something includes or is associated with foundational structural elements that serve as key supporting pillars in its blueprint or design.
-
C.
belongsToPillar
Indicates that something is a component or member of a specific pillar or foundational category.
-
D.
haveType
chosen
Indicates that an entity belongs to or is classified under a specified type or category.
-
E.
hasPackageType
Indicates that an entity is associated with or classified under a particular type or category of package.
- 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_69f01a58a67c819097936d9e8da8d6e6 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f65876c52c8190bc889c7a67bd07f3 |
completed | May 2, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 2:42 a.m.