Triple
T31621482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Equitable Building (New York City interiors and alterations) |
E806905
|
entity |
| Predicate | architecturalFirmCity |
P148628
|
FINISHED |
| Object | New York City |
—
|
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 | Statement: [Equitable Building (New York City interiors and alterations), architecturalFirmCity, New York City]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: architecturalFirmCity Context triple: [Equitable Building (New York City interiors and alterations), architecturalFirmCity, New York City]
-
A.
architectureFirm
Indicates that one entity is an architecture firm responsible for providing architectural services or design work to another entity.
-
B.
architecturalFirmHeadquarters
chosen
Indicates the location where an architectural firm’s main offices or central headquarters are based.
-
C.
projectCity
Indicates that a project is located in, associated with, or primarily takes place within a specific city.
-
D.
hasArchitecturalFirmNationality
Indicates that an architectural firm is associated with or originates from a specific country or nationality.
-
E.
workCity
Indicates the city in which an entity (typically a person) performs their work or job.
- 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_69f348d7883c8190b6c13ab92b7ef076 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f791cc969c8190bf187d6031a030d5 |
completed | May 3, 2026, 6:19 p.m. |
| PD | Predicate disambiguation | batch_69f791033d288190b118029fe412b9c9 |
completed | May 3, 2026, 6:16 p.m. |
Created at: April 30, 2026, 10:41 p.m.