Triple

T18635237
Position Surface form Disambiguated ID Type / Status
Subject Peter Mathuki E455528 entity
Predicate nationality P2 FINISHED
Object Kenyan 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: Kenyan | Statement: [Peter Mathuki, nationality, Kenyan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kenyan
Context triple: [Peter Mathuki, nationality, Kenyan]
  • A. Kenyan chosen
    Kenyan refers to a person from Kenya, an East African country known for its diverse cultures, languages, and rich history.
  • B. Kenyan Luo
    Kenyan Luo is a Nilotic ethnic group in western Kenya, primarily around Lake Victoria, known for its Dholuo language and rich cultural traditions in music, storytelling, and fishing.
  • C. Gikuyu
    Gikuyu is an alternative name for the Kikuyu, the largest ethnic group in Kenya known for their Bantu language and significant cultural and political influence in the country.
  • D. Nandi–Kalenjin
    Nandi–Kalenjin refers to the Kalenjin-speaking communities of Kenya, particularly associated with the Nandi subgroup known for their distinct cultural traditions and notable success in middle- and long-distance running.
  • E. Kenya
    Kenya is an East African country known for its diverse wildlife, scenic landscapes from savannas to highlands, and a coastline along the Indian Ocean.
  • 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_69d8d38cc7948190a55ea64e5638994e completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e54fc80b308190932303231524d372 completed April 19, 2026, 9:57 p.m.
Created at: April 10, 2026, 11:46 a.m.