Triple

T13876601
Position Surface form Disambiguated ID Type / Status
Subject Karamoja region E333598 entity
Predicate borders P224 FINISHED
Object Teso sub-region E867504 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: Teso sub-region | Statement: [Karamoja region, borders, Teso sub-region]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Teso sub-region
Context triple: [Karamoja region, borders, Teso sub-region]
  • A. Teso sub-region chosen
    The Teso sub-region is an area in eastern Uganda that serves as the cultural and historical homeland of the Iteso people.
  • B. Sebei sub-region
    The Sebei sub-region is a mountainous area in eastern Uganda inhabited mainly by the Sebei (Kalenjin) people, known for its highland agriculture and proximity to Mount Elgon.
  • C. Lango sub-region
    The Lango sub-region is an area in northern Uganda that serves as the traditional homeland of the Lango people, known for its distinct Luo-related language and culture.
  • D. Ave Subregion
    Ave Subregion is an administrative and statistical region in northern Portugal known for its industrial cities, historical heritage, and dense urban development.
  • E. Kigezi sub-region
    Kigezi sub-region is a highland area in southwestern Uganda known for its terraced hills, cool climate, and dense rural population.
  • 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_69d81c5ced9c8190b0e9bcc6effe5959 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de0be556708190bbcf0b3583f677e3 completed April 14, 2026, 9:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7ce6df2ac819089024b9ede7b205f completed May 3, 2026, 10:38 p.m.
Created at: April 9, 2026, 10:15 p.m.