Triple

T15866922
Position Surface form Disambiguated ID Type / Status
Subject Helicopter Wing Karup E384737 entity
Predicate basedAt P40 FINISHED
Object Karup Air Base E387684 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: Karup Air Base | Statement: [Helicopter Wing Karup, basedAt, Karup Air Base]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karup Air Base
Context triple: [Helicopter Wing Karup, basedAt, Karup Air Base]
  • A. Karup Air Base chosen
    Karup Air Base is one of Denmark’s largest and most important military air installations, serving as a central hub for Royal Danish Air Force operations and command.
  • B. Laage Air Base
    Laage Air Base is a major German Air Force installation in northeastern Germany that serves as a key hub for fighter aircraft operations and training.
  • C. Rygge Air Station
    Rygge Air Station is a major Norwegian military air base that has served as an important hub for the Royal Norwegian Air Force.
  • D. Schleswig Air Base
    Schleswig Air Base is a military airfield in northern Germany that serves as a key operational base for the German Air Force.
  • E. Ursel Air Base
    Ursel Air Base is a Belgian military airfield used primarily for training, exercises, and occasional civilian aviation events.
  • 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_69d86da4e86481909f1325fdc971b5ec completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e155603e908190acad1bce2eb6e210 completed April 16, 2026, 9:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbbff15c81909cb148a33b51a16e completed May 10, 2026, 1:13 a.m.
Created at: April 10, 2026, 4:50 a.m.