Triple

T7680780
Position Surface form Disambiguated ID Type / Status
Subject Magong E173986 entity
Predicate hasAirport P105 FINISHED
Object Penghu Airport E162851 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: Penghu Airport | Statement: [Magong, hasAirport, Penghu Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Penghu Airport
Context triple: [Magong, hasAirport, Penghu Airport]
  • A. Penghu Airport chosen
    Penghu Airport is a regional airport in Taiwan serving the Penghu (Pescadores) archipelago with domestic flights and acting as its main air transportation hub.
  • B. Hualien Airport
    Hualien Airport is a regional civil and military airport in eastern Taiwan that serves the city of Hualien and nearby tourist destinations such as Taroko Gorge.
  • C. Taitung Airport
    Taitung Airport is a regional airport in southeastern Taiwan that provides domestic flights and connects Taitung County with other major cities and offshore islands.
  • D. Lanyu Airport
    Lanyu Airport is a small regional airport serving Taiwan’s remote Orchid Island, providing vital air connections for residents and visitors.
  • E. Hengchun Airport
    Hengchun Airport is a small regional airport in southern Taiwan serving the Hengchun Peninsula and nearby tourist areas such as Kenting in Pingtung County.
  • 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_69c6995840408190a19de6c51090f46f completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c701ffc1fc8190bc9c2b1f3bb37f0d completed March 27, 2026, 10:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8a24de3a48190a92009b6092b09d0 completed March 29, 2026, 3:53 a.m.
Created at: March 27, 2026, 4:01 p.m.