Triple

T22521852
Position Surface form Disambiguated ID Type / Status
Subject Akure North E556799 entity
Predicate hasVehicleRegistrationCode P1173 FINISHED
Object OND 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: OND | Statement: [Akure North, hasVehicleRegistrationCode, OND]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: OND
Context triple: [Akure North, hasVehicleRegistrationCode, OND]
  • A. OND chosen
    OND is the official vehicle registration code used on license plates to identify vehicles registered in Ondo State, Nigeria.
  • B. ONA
    ONA is the IATA airport code for Winona Municipal Airport – Max Conrad Field, a public airport serving Winona, Minnesota.
  • C. BND
    BND is the three-letter station code used to identify Bond Street station on the London Underground network.
  • D. BND
    BND is Germany’s federal foreign intelligence service responsible for gathering and analyzing information on international affairs and security threats.
  • E. BND
    BND is the official currency code for the Brunei dollar, the national currency of Brunei Darussalam.
  • 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_69e11e5657e881909f16ca58352c50da completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15e32b8a88190ac335d4298dd5ee3 completed April 29, 2026, 1:26 a.m.
Created at: April 16, 2026, 8:50 p.m.