Triple

T22024185
Position Surface form Disambiguated ID Type / Status
Subject Op Art E543916 entity
Predicate notableWork P4 FINISHED
Object Zebra 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: Zebra | Statement: [Op Art, notableWork, Zebra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zebra
Context triple: [Op Art, notableWork, Zebra]
  • A. Cebra
    Cebra is a Danish architectural firm known for its innovative, sculptural designs and contemporary urban projects.
  • B. zebra chosen
    A zebra is an African equid known for its distinctive black-and-white striped coat and social herd behavior on savannas and grasslands.
  • C. Grant's zebra
    Grant's zebra is the smallest and most numerous subspecies of plains zebra, known for its bold black-and-white striping and wide distribution across eastern Africa.
  • D. Burchell's zebra
    Burchell's zebra is a common subspecies of plains zebra native to southern Africa, recognizable by its broad black stripes and relatively faint or absent shadow stripes.
  • E. Grevy's zebra
    Grevy's zebra is the largest and most endangered species of zebra, native to arid regions of Kenya and Ethiopia and distinguished by its narrow stripes and large, rounded ears.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e2e8ea4819084210fe06d3a1b8d completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127ca45a08190b2d5d3a8eb37cb4b completed April 28, 2026, 9:34 p.m.
Created at: April 16, 2026, 8:23 p.m.