Triple

T23368478
Position Surface form Disambiguated ID Type / Status
Subject Oroko E593391 entity
Predicate relatedGroup P37 FINISHED
Object Isubu 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: Isubu | Statement: [Oroko, relatedGroup, Isubu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Isubu
Context triple: [Oroko, relatedGroup, Isubu]
  • A. Isubu chosen
    The Isubu are a coastal Bantu-speaking ethnic group of Cameroon historically known for early contact and trade with Europeans around the port of Bimbia.
  • B. Iwakuma
    Iwakuma is a Japanese surname most notably associated with former professional baseball pitcher Hisashi Iwakuma, who played in both Nippon Professional Baseball and Major League Baseball.
  • C. Osubi
    Osubi is a town in Delta State, Nigeria, known for hosting a regional airport that serves the nearby city of Warri and surrounding communities.
  • D. Ebisucho
    Ebisucho is a commercial and entertainment district in Osaka’s Naniwa Ward, known for its proximity to Den Den Town and its mix of electronics shops, eateries, and local businesses.
  • E. Bunzo
    Bunzo is the pet belonging to someone named Kumiko, likely a beloved animal companion in their household.
  • 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_69e25d2593c88190bcdf4a716a94ccb2 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a0aed374819097d38f51894bee44 completed April 29, 2026, 6:09 a.m.
Created at: April 17, 2026, 5:32 p.m.