Triple

T18213987
Position Surface form Disambiguated ID Type / Status
Subject BRN E436104 entity
Predicate refersTo P37 FINISHED
Object Bern Airport 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: Bern Airport | Statement: [BRN, refersTo, Bern Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bern Airport
Context triple: [BRN, refersTo, Bern Airport]
  • A. Bern Airport chosen
    Bern Airport is a small regional airport in Switzerland serving the city of Bern and offering domestic and limited international flights.
  • B. Copenhagen Airport Kastrup
    Copenhagen Airport Kastrup is Denmark’s largest and busiest international airport, serving as the main air hub for Copenhagen and much of Scandinavia.
  • C. Hans Christian Andersen Airport
    Hans Christian Andersen Airport is a regional airport serving the city of Odense on the island of Funen in Denmark.
  • D. Midtjyllands Airport
    Midtjyllands Airport is a regional airport in central Jutland, Denmark, serving domestic and limited international flights for the surrounding Midtjylland area.
  • E. Bost Airport
    Bost Airport is a regional airport serving the city of Lashkargah in Helmand Province, Afghanistan.
  • 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_69d8b90dba6481908e119eb9aa4ca0cb completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e475953c81909f792793ded2057e completed April 19, 2026, 2:19 p.m.
Created at: April 10, 2026, 10:32 a.m.