Triple

T21331148
Position Surface form Disambiguated ID Type / Status
Subject Lelystad E525900 entity
Predicate hasAirport P105 FINISHED
Object Lelystad 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: Lelystad Airport | Statement: [Lelystad, hasAirport, Lelystad Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lelystad Airport
Context triple: [Lelystad, hasAirport, Lelystad Airport]
  • A. Lelystad Airport chosen
    Lelystad Airport is a regional Dutch airport in the province of Flevoland that serves general aviation and is planned to handle overflow holiday and leisure traffic from Amsterdam Airport Schiphol.
  • B. Groningen Airport Eelde
    Groningen Airport Eelde is a regional airport in the north of the Netherlands that offers passenger flights, including holiday and charter services.
  • C. Texel International Airport
    Texel International Airport is a small regional airport on the Dutch island of Texel, primarily serving general aviation, skydiving, and tourist flights.
  • D. Sturup Airport
    Sturup Airport is the former name of Malmö Airport, an international airport serving the Malmö region in southern Sweden.
  • E. Eindhoven Airport
    Eindhoven Airport is a major regional airport in the Netherlands that serves as a key hub for low-cost and European short-haul flights.
  • 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_69e0b51b90788190a4dd823d962626da completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7ab530a1c81909bb37c2a3407d9e6 completed April 21, 2026, 4:52 p.m.
Created at: April 16, 2026, 4:42 p.m.