Triple

T20669754
Position Surface form Disambiguated ID Type / Status
Subject 진주 E507987 entity
Predicate hasAirport P105 FINISHED
Object Sacheon 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: Sacheon Airport | Statement: [진주, hasAirport, Sacheon Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sacheon Airport
Context triple: [진주, hasAirport, Sacheon Airport]
  • A. Sacheon Airport chosen
    Sacheon Airport is a regional airport in South Korea serving the city of Jinju and the surrounding Gyeongsangnam-do area with domestic flights.
  • B. Gunsan Airport
    Gunsan Airport is a regional airport in Gunsan, South Korea, serving both civilian flights and military operations.
  • C. Cheongju International Airport
    Cheongju International Airport is a major regional airport in central South Korea that serves both domestic and international flights for the city of Cheongju and the surrounding Chungcheong region.
  • D. Pohang Airport
    Pohang Airport is a regional airport in Pohang, South Korea, serving both civilian flights and military operations.
  • E. Gimhae International Airport
    Gimhae International Airport is the main international airport serving the Busan metropolitan area in South Korea.
  • 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_69e0b4c059bc81908ea762cd73ea4424 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6b5c735048190a01cb7692928d66e completed April 20, 2026, 11:24 p.m.
Created at: April 16, 2026, 11:44 a.m.