Triple

T10747672
Position Surface form Disambiguated ID Type / Status
Subject Sibulan E253492 entity
Predicate hasAirport P105 FINISHED
Object Sibulan Airport E235325 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: Sibulan Airport | Statement: [Sibulan, hasAirport, Sibulan Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sibulan Airport
Context triple: [Sibulan, hasAirport, Sibulan Airport]
  • A. Sibulan Airport chosen
    Sibulan Airport is a domestic airport serving Dumaguete and the surrounding areas in Negros Oriental, in the Central Visayas region of the Philippines.
  • B. Pakyong Airport
    Pakyong Airport is a domestic airport in the Indian state of Sikkim that serves as the primary air gateway to the region’s capital and surrounding Himalayan areas.
  • C. Loakan Airport
    Loakan Airport is a small domestic airport serving the city of Baguio in the mountainous Cordillera region of the Philippines.
  • D. Dumna Airport
    Dumna Airport is a domestic airport serving the city of Jabalpur in the Indian state of Madhya Pradesh.
  • E. Begumpet Airport
    Begumpet Airport is the former primary airport of Hyderabad, India, now used mainly for military, training, and charter operations after being superseded by Rajiv Gandhi International Airport.
  • 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_69d6aa5e51e8819095f06881cecf152e completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d711b9242c81908dbf3fa155159b3c completed April 9, 2026, 2:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69de84a63de0819085f1e982c8348811 completed April 14, 2026, 6:17 p.m.
Created at: April 8, 2026, 9:15 p.m.