Triple

T4959936
Position Surface form Disambiguated ID Type / Status
Subject Swedavia E111378 entity
Predicate owns P347 FINISHED
Object Åre Östersund Airport E199663 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: Åre Östersund Airport | Statement: [Swedavia, owns, Åre Östersund Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Åre Östersund Airport
Context triple: [Swedavia, owns, Åre Östersund Airport]
  • A. Åre Östersund Airport chosen
    Åre Östersund Airport is a regional airport in central Sweden serving the city of Östersund and the nearby Åre ski resort, providing both domestic and seasonal international flights.
  • B. Luleå Airport
    Luleå Airport is a major civilian and military airport in northern Sweden serving the city of Luleå and the wider Norrbotten region.
  • C. Jönköping Airport
    Jönköping Airport is a regional airport in southern Sweden serving the city of Jönköping with domestic and limited international flights.
  • D. Umeå Airport
    Umeå Airport is a regional airport in northern Sweden serving the city of Umeå with domestic and limited international flights.
  • E. Linköping City Airport
    Linköping City Airport is a regional airport in Linköping, Sweden, serving both commercial passenger flights and general aviation.
  • 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_69bd4418390c8190b7e9766a2512ce55 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd71da80008190a0d606d5091822b8 completed March 20, 2026, 4:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf77a49ddc819082fdfe7389b0d8a1 completed March 22, 2026, 5:01 a.m.
Created at: March 20, 2026, 1:32 p.m.