Triple

T21175444
Position Surface form Disambiguated ID Type / Status
Subject Kwale County E521798 entity
Predicate hasEthnicGroup P1898 FINISHED
Object Digo 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: Digo | Statement: [Kwale County, hasEthnicGroup, Digo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Digo
Context triple: [Kwale County, hasEthnicGroup, Digo]
  • A. Digo chosen
    Digo are a coastal Bantu ethnic group of the Mijikenda people, primarily living along the southern Kenyan and northern Tanzanian coast, known for their Swahili-influenced culture and trade history.
  • B. Saca
    Saca is a Spanish-language surname most notably associated with former Salvadoran president Antonio Saca.
  • C. Justo
    Justo is a masculine given name of Spanish origin commonly used in Latin American and Spanish-speaking countries.
  • D. DioGuardi
    DioGuardi is the surname of Kara DioGuardi, an American songwriter, record producer, and former American Idol judge.
  • E. Hevioso
    Hevioso is a major Fon deity associated with thunder, lightning, and justice in the traditional religion of the Fon people of West Africa.
  • 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_69e0b50e30748190b186824a206d39b9 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7271597288190b04baff9ca8d866c completed April 21, 2026, 7:28 a.m.
Created at: April 16, 2026, 3 p.m.