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.