Triple

T21713862
Position Surface form Disambiguated ID Type / Status
Subject Kinyankole language E535971 entity
Predicate primaryEthnicGroup P194 FINISHED
Object Banyankole 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: Banyankole | Statement: [Kinyankole language, primaryEthnicGroup, Banyankole]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Banyankole
Context triple: [Kinyankole language, primaryEthnicGroup, Banyankole]
  • A. Kasese
    Kasese is a town in western Uganda that serves as a key gateway to Queen Elizabeth National Park and the Rwenzori Mountains.
  • B. Bunyoro
    Bunyoro is a traditional kingdom and historical region in western Uganda that was once a powerful pre-colonial African state.
  • C. Rubanda District
    Rubanda District is an administrative district in southwestern Uganda known for its hilly terrain and rural communities.
  • D. Runyankole chosen
    Runyankole is a Bantu language spoken primarily by the Banyankole people in southwestern Uganda.
  • E. Mbarara District
    Mbarara District is an administrative district in southwestern Uganda known for its regional commercial center, agricultural activity, and role as a transport hub.
  • 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_69e0c46c6dd88190a595375fa6ebd701 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69efb5369be88190bafc10863d4d1bd7 completed April 27, 2026, 7:12 p.m.
Created at: April 16, 2026, 6:47 p.m.