Triple

T16319316
Position Surface form Disambiguated ID Type / Status
Subject Côn Lôn Islands E396248 entity
Predicate hasAirport P105 FINISHED
Object Côn Đảo Airport E758512 NE FINISHED

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: Côn Đảo Airport | Statement: [Côn Lôn Islands, hasAirport, Côn Đảo Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Côn Đảo Airport
Context triple: [Côn Lôn Islands, hasAirport, Côn Đảo Airport]
  • A. Con Dao Airport chosen
    Con Dao Airport is a regional airport serving the Con Dao archipelago in southern Vietnam, providing vital air connectivity for residents and tourists to this remote island district.
  • B. Duong Dong Airport
    Duong Dong Airport was the former main airport serving Phu Quoc Island in Vietnam before being superseded by Phu Quoc International Airport.
  • C. Pleiku Airport
    Pleiku Airport is a regional airport in Vietnam’s Central Highlands that serves the city of Pleiku and nearby provinces such as Kon Tum.
  • D. Lien Khuong Airport
    Lien Khuong Airport is a regional airport serving Da Lat and the surrounding Central Highlands area of Vietnam.
  • E. Tuy Hoa Airport
    Tuy Hoa Airport is a regional domestic airport serving the city of Tuy Hòa and the surrounding Phú Yên Province on Vietnam’s south-central coast.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d87f255b788190a400eba031dd85d8 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e296b4ad448190b2b195a5e0032c6e completed April 17, 2026, 8:23 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00260904748190ae1eb5713a6daa68 completed May 10, 2026, 6:30 a.m.
Created at: April 10, 2026, 5:06 a.m.