Triple
T31228314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aeolian Hall |
E796204
|
entity |
| Predicate | buildingUseAfterConcertEra |
P58931
|
FINISHED |
| Object | office building |
—
|
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: office building | Statement: [Aeolian Hall, buildingUseAfterConcertEra, office building]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: buildingUseAfterConcertEra Context triple: [Aeolian Hall, buildingUseAfterConcertEra, office building]
-
A.
buildingUseBeforeVenue
Indicates that a building was used for a particular purpose or function prior to its use as a venue.
-
B.
buildingUseAfterClosure
chosen
Indicates how a building is used or repurposed after its original function or operation has ceased.
-
C.
sportsVenueUse
Indicates that a sports venue is used or designated for hosting a particular sport, team, or sporting event.
-
D.
usedVenuesFrom
Indicates that one entity has made use of or operated in venues associated with another entity.
-
E.
reopenedAsConcertVenue
Indicates that a previously closed or differently used place has been opened again specifically to function as a concert venue.
- 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_69f224da98f88190ab32f690cce5d303 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69dfdda708190be290c7bec205445 |
completed | May 3, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69f69d1a37e081908d1d86b90ff502bd |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 9:10 p.m.