Triple

T4959933
Position Surface form Disambiguated ID Type / Status
Subject Swedavia E111378 entity
Predicate operates P24 FINISHED
Object Luleå Airport E520227 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: Luleå Airport | Statement: [Swedavia, operates, Luleå Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Luleå Airport
Context triple: [Swedavia, operates, Luleå Airport]
  • A. Luleå Airport chosen
    Luleå Airport is a major civilian and military airport in northern Sweden serving the city of Luleå and the wider Norrbotten region.
  • B. Torslanda Airport
    Torslanda Airport was the former main airport serving Gothenburg, Sweden, before being superseded by Gothenburg Landvetter Airport.
  • C. Landvetter Airport
    Landvetter Airport is an international airport serving the Gothenburg region in western Sweden and is one of the country’s major aviation hubs.
  • D. Jönköping Airport
    Jönköping Airport is a regional airport in southern Sweden serving the city of Jönköping with domestic and limited international flights.
  • E. Kemi-Tornio Airport
    Kemi-Tornio Airport is a regional airport in Finnish Lapland serving the twin towns of Kemi and Tornio, providing domestic connections and access to the northern Arctic area.
  • 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_69bf486d43488190b57e064b0272ece4 completed March 22, 2026, 1:39 a.m.
Created at: March 20, 2026, 1:32 p.m.