Triple

T22369846
Position Surface form Disambiguated ID Type / Status
Subject Akure South Local Government Area E553009 entity
Predicate hosts P186 FINISHED
Object Akure Airport 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 Airport | Statement: [Akure South Local Government Area, hosts, Akure Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Akure Airport
Context triple: [Akure South Local Government Area, hosts, Akure Airport]
  • A. Akure Airport chosen
    Akure Airport is a domestic airport serving the city of Akure and the surrounding Ondo State region in southwestern Nigeria.
  • B. Hokksund Airport
    Hokksund Airport is a small general aviation airfield serving the town of Hokksund in Norway.
  • C. Rygge Airport
    Rygge Airport is a former civil and military airport in Rygge, near Moss in southeastern Norway, which once served as a low-cost hub before closing to regular commercial traffic.
  • D. Torp Airport
    Torp Airport is a regional international airport in Sandefjord, Norway, serving the Oslo area with both domestic and European flights.
  • E. Berlevåg Airport
    Berlevåg Airport is a small regional airport in Berlevåg, Norway, primarily serving local communities with short-haul domestic flights along the northern coast.
  • 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_69e11e4affcc8190ba7c27d29062558d completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f158032b748190ad36c7e3809304e9 completed April 29, 2026, 12:59 a.m.
Created at: April 16, 2026, 8:44 p.m.