Triple

T22407365
Position Surface form Disambiguated ID Type / Status
Subject Akure South E553910 entity
Predicate sharesBoundaryWith P62639 FINISHED
Object Akure North 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: Akure North | Statement: [Akure South, sharesBoundaryWith, Akure North]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Akure North
Context triple: [Akure South, sharesBoundaryWith, Akure North]
  • A. Akure North chosen
    Akure North is a local government area in Ondo State, southwestern Nigeria, that administers the communities surrounding the city of Akure.
  • B. Akure South
    Akure South is a local government area in Ondo State, Nigeria, that encompasses much of the urban and administrative core of the city of Akure.
  • C. Akure Division
    Akure Division is an administrative area in Ondo State, Nigeria, encompassing Akure and its surrounding local government jurisdictions.
  • D. Nordlandet
    Nordlandet is one of the main islands and districts of the coastal Norwegian city of Kristiansund.
  • E. Nordre Land
    Nordre Land is a rural municipality in Innlandet county, Norway, known for its forests, lakes, and agricultural landscape in the traditional district of Land.
  • 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_69e11e4da7048190b4387d422a9a0de5 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f158ba1c6481908e4b9b3635ed3a49 completed April 29, 2026, 1:02 a.m.
Created at: April 16, 2026, 8:46 p.m.