Triple
T13692265
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Serpentine Sackler Gallery |
E328294
|
entity |
| Predicate | buildingUseBeforeConversion |
P55864
|
FINISHED |
| Object | gunpowder magazine |
—
|
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: gunpowder magazine | Statement: [Serpentine Sackler Gallery, buildingUseBeforeConversion, gunpowder magazine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: buildingUseBeforeConversion Context triple: [Serpentine Sackler Gallery, buildingUseBeforeConversion, gunpowder magazine]
-
A.
previousBuildingUse
chosen
Indicates that a building previously served a specified use or function before its current one.
-
B.
buildingConvertedTo
Indicates that one building has been transformed, repurposed, or adapted into another type or use of building.
-
C.
buildingReuseType
Indicates the manner or purpose for which an existing building is reused or repurposed.
-
D.
buildingReuse
Indicates that an existing building is being repurposed or adapted for a new use rather than being newly constructed or demolished.
-
E.
hasFormerBuilding
Indicates that an entity previously occupied or used a different building, which is identified as its former building.
- 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_69d8076ff62081908a7bd79889edd7a0 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc8746458819095ec1ba3c01ef31b |
completed | April 12, 2026, 4:29 p.m. |
| PD | Predicate disambiguation | batch_69dbbe9059488190a8113177c83e1481 |
completed | April 12, 2026, 3:47 p.m. |
Created at: April 9, 2026, 9:53 p.m.