Triple

T23023015
Position Surface form Disambiguated ID Type / Status
Subject Penghu County E573217 entity
Predicate hasAirport P105 FINISHED
Object Penghu 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: Penghu Airport | Statement: [Penghu County, hasAirport, Penghu Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Penghu Airport
Context triple: [Penghu County, 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 (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_69e245b821008190b0e09cb02092aae1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f183ea23088190b2f42d9bf01514ac completed April 29, 2026, 4:07 a.m.
Created at: April 17, 2026, 3:52 p.m.