Triple

T13804595
Position Surface form Disambiguated ID Type / Status
Subject Eastern Region of Uganda E331727 entity
Predicate hasDistrict P459 FINISHED
Object Kumi District E867505 NE FINISHED

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: Kumi District | Statement: [Eastern Region of Uganda, hasDistrict, Kumi District]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kumi District
Context triple: [Eastern Region of Uganda, hasDistrict, Kumi District]
  • A. Kumi District chosen
    Kumi District is an administrative region in eastern Uganda known for its predominantly Iteso population and agriculture-based economy.
  • B. Kisii District
    Kisii District was a former administrative district in southwestern Kenya, inhabited mainly by the Kisii (Abagusii) people and centered around the town of Kisii.
  • C. Nyando District
    Nyando District was a former administrative district in Kenya’s Nyanza Province, located in the western part of the country near Lake Victoria.
  • D. Ngora District
    Ngora District is an administrative district in eastern Uganda, predominantly inhabited by the Iteso people and known for its agricultural economy.
  • E. Mwenezi District
    Mwenezi District is a largely rural administrative district in southern Zimbabwe known for its cattle ranching, sugar estates, and semi-arid landscapes.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d81c59f8808190a851bc56afdc55e9 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de026c36108190a7436034a730a261 completed April 14, 2026, 9:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69fba1ba309c81908d83ba7efc663787 completed May 6, 2026, 8:16 p.m.
Created at: April 9, 2026, 10:12 p.m.