Triple

T22327481
Position Surface form Disambiguated ID Type / Status
Subject Dangriga E551936 entity
Predicate hasAirport P105 FINISHED
Object Dangriga 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: Dangriga Airport | Statement: [Dangriga, hasAirport, Dangriga Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dangriga Airport
Context triple: [Dangriga, hasAirport, Dangriga Airport]
  • A. Dangriga Airport chosen
    Dangriga Airport is a small public airstrip serving the coastal town of Dangriga in southern Belize, providing domestic connections to other parts of the country.
  • B. Manda Airport
    Manda Airport is a small regional airport serving the Lamu Archipelago and surrounding areas on Kenya’s coast.
  • C. Muanda Airport
    Muanda Airport is a public airport serving the coastal town of Muanda in the western Democratic Republic of the Congo, providing regional air connectivity for passengers and cargo.
  • D. Dumna Airport
    Dumna Airport is a domestic airport serving the city of Jabalpur in the Indian state of Madhya Pradesh.
  • E. Lolowai Airport
    Lolowai Airport is a small regional airfield serving the island of Ambae in Vanuatu, providing vital domestic air connections for local residents and visitors.
  • 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_69e11e482f788190b78d1588fc26d606 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f157693460819087c165481eb9e128 completed April 29, 2026, 12:57 a.m.
Created at: April 16, 2026, 8:42 p.m.