Triple

T22044264
Position Surface form Disambiguated ID Type / Status
Subject Terminal 5 (Stockholm Arlanda Airport) E544719 entity
Predicate operator P179 FINISHED
Object Swedavia 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: Swedavia | Statement: [Terminal 5 (Stockholm Arlanda Airport), operator, Swedavia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Swedavia
Context triple: [Terminal 5 (Stockholm Arlanda Airport), operator, Swedavia]
  • A. Swedavia chosen
    Swedavia is a Swedish state-owned company that owns, operates, and develops several of Sweden’s major airports.
  • B. Swedien
    Swedien is the surname of Bruce Swedien, the renowned American audio engineer best known for his work on Michael Jackson’s classic albums.
  • C. Sweden
    Sweden is a Nordic country in Northern Europe known for its high standard of living, strong welfare state, and long-standing policy of neutrality.
  • D. Svea
    Svea is a patriotic poem by Swedish poet Esaias Tegnér that celebrates Sweden and helped establish his reputation in early 19th-century Swedish literature.
  • E. Sweden and Finland
    Sweden and Finland are two neighboring Nordic countries in Northern Europe known for their advanced welfare systems, high quality of life, and extensive shared border.
  • 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_69e11e32445c8190ab97089b48a130bb completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1282d5bb08190849d5084962bf3a5 completed April 28, 2026, 9:35 p.m.
Created at: April 16, 2026, 8:25 p.m.