Triple

T23368634
Position Surface form Disambiguated ID Type / Status
Subject Moundang E593395 entity
Predicate neighboringEthnicGroups P11274 FINISHED
Object Kotoko 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: Kotoko | Statement: [Moundang, neighboringEthnicGroups, Kotoko]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kotoko
Context triple: [Moundang, neighboringEthnicGroups, Kotoko]
  • A. Kotoko chosen
    The Kotoko are an ethnic group of fishing and farming communities living around the Lake Chad region in Cameroon, Chad, and Nigeria, known historically for their riverine kingdoms and distinctive Chadic language.
  • B. Baroka F.C.
    Baroka F.C. is a South African professional football club that competes in the country’s league system and is based in Limpopo province.
  • C. Kashiwa Reysol
    Kashiwa Reysol is a professional Japanese football club based in Kashiwa, Chiba, that competes in the J.League.
  • D. Albirex Niigata
    Albirex Niigata is a professional Japanese football club based in Niigata that competes in the J.League.
  • E. Sagan Tosu
    Sagan Tosu is a professional Japanese football club based in Tosu, Saga Prefecture, that competes in the J.League.
  • 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.