Triple

T5428970
Position Surface form Disambiguated ID Type / Status
Subject Visby E121435 entity
Predicate transport P230 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: [Visby, transport, Visby Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Visby Airport
Context triple: [Visby, transport, 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. Ronneby Airport
    Ronneby Airport is a regional airport in southern Sweden serving the Ronneby and Blekinge area with domestic flights and operated as part of the national airport network.
  • D. Gothenburg City Airport
    Gothenburg City Airport is a regional airport serving the Gothenburg area in western Sweden.
  • E. 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.
  • 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_69bd463c65f0819082ee6483ab4b466a completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd883d1bfc8190859bb05cfab065c8 completed March 20, 2026, 5:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69bfba21331481908fc43a47f06d7c87 completed March 22, 2026, 9:45 a.m.
Created at: March 20, 2026, 2:06 p.m.