Triple

T4959938
Position Surface form Disambiguated ID Type / Status
Subject Swedavia E111378 entity
Predicate owns P347 FINISHED
Object Visby Airport E121436 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: Visby Airport | Statement: [Swedavia, owns, Visby Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Visby Airport
Context triple: [Swedavia, owns, Visby Airport]
  • A. Visby Airport chosen
    Visby Airport is the main commercial airport serving the island of Gotland in Sweden, handling domestic and seasonal international flights.
  • B. Jönköping Airport
    Jönköping Airport is a regional airport in southern Sweden serving the city of Jönköping with domestic and limited international flights.
  • C. Gothenburg City Airport
    Gothenburg City Airport is a regional airport serving the Gothenburg area in western Sweden.
  • D. Malmö Airport
    Malmö Airport is an international airport in southern Sweden serving the city of Malmö and the wider Øresund Region, including nearby parts of Denmark.
  • E. Uppsala Airport
    Uppsala Airport is a Swedish airfield near the city of Uppsala, primarily used for military and general aviation rather than large-scale commercial passenger traffic.
  • 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_69bf832e0da88190aa6b09dd88fb6157 completed March 22, 2026, 5:50 a.m.
Created at: March 20, 2026, 1:32 p.m.