Triple

T23299214
Position Surface form Disambiguated ID Type / Status
Subject Nyeri County E590255 entity
Predicate borders P224 FINISHED
Object Embu County 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: Embu County | Statement: [Nyeri County, borders, Embu County]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Embu County
Context triple: [Nyeri County, borders, Embu County]
  • A. Embu County chosen
    Embu County is an administrative region in eastern Kenya, located on the southeastern slopes of Mount Kenya and inhabited predominantly by the Embu people.
  • B. Nandi County
    Nandi County is a highland county in Kenya’s Rift Valley region, known as a stronghold of the Kalenjin community and for producing many of the country’s elite long-distance runners.
  • C. Wanju County
    Wanju County is a largely rural administrative region in South Korea known for its agriculture and proximity to the city of Jeonju.
  • D. Siaya County
    Siaya County is an administrative county in western Kenya, located along the shores of Lake Victoria and known as the birthplace of several prominent Kenyan political figures.
  • E. Makueni County
    Makueni County is a semi-arid administrative region in southeastern Kenya known for its agriculture, water-scarcity challenges, and location along key transport and river basins.
  • 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_69e25d1c0ecc8190a355aa229f06d0e0 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f196d133448190bf350a9f51c1531c completed April 29, 2026, 5:27 a.m.
Created at: April 17, 2026, 5:03 p.m.