Triple
T32688702
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Powell-Cotton Museum |
E835796
|
entity |
| Predicate | hasDiorama |
P106338
|
FINISHED |
| Object | African savannah dioramas |
—
|
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: African savannah dioramas | Statement: [Powell-Cotton Museum, hasDiorama, African savannah dioramas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDiorama Context triple: [Powell-Cotton Museum, hasDiorama, African savannah dioramas]
-
A.
hasNotableDiorama
chosen
Indicates that an entity features or includes a diorama that is considered notable or significant.
-
B.
has3DModels
Indicates that an entity is associated with one or more three-dimensional (3D) digital models representing it.
-
C.
hasAltarPieceFrom
Indicates that an altar piece originates from, or is sourced from, a particular place, creator, or context.
-
D.
hasDentalArcade
Indicates that an entity possesses a specific arrangement or series of teeth (a dental arcade) within its mouth.
-
E.
hasDomeDesigner
Indicates that an entity’s dome was designed or created by a specific designer or architect.
- 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_69f3493211388190993801216afbc2a7 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fea2d0a4d08190aa06aeb902a02d5a |
completed | May 9, 2026, 2:58 a.m. |
| PD | Predicate disambiguation | batch_69fea24698348190b9b992a8e7cdbcd0 |
completed | May 9, 2026, 2:56 a.m. |
Created at: May 1, 2026, 1:09 a.m.