Triple
T15866793
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karup Air Base |
E384733
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Karup, Denmark |
E384733
|
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, Denmark | Statement: [Karup Air Base, locatedIn, Karup, Denmark]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karup, Denmark Context triple: [Karup Air Base, locatedIn, Karup, Denmark]
-
A.
Karup, Denmark
chosen
Karup, Denmark is a village in central Jutland best known as a major military hub and home to the primary air base of the Royal Danish Air Force.
-
B.
Farum, Denmark
Farum, Denmark is a suburban town in Furesø Municipality on the island of Zealand, known for its residential character and proximity to Copenhagen.
-
C.
Billund, Denmark
Billund, Denmark is a small Danish town best known as the birthplace of LEGO and home to the original LEGOLAND theme park.
-
D.
Hammelev, Denmark
Hammelev, Denmark is a small Danish village best known as the birthplace of the early 20th-century painter and illustrator Gerda Wegener.
-
E.
Strib, Denmark
Strib, Denmark is a small coastal town on the island of Funen, known as the birthplace of shipping magnate Mærsk Mc-Kinney Møller.
- 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_69ffa947ba3881909c602f2fc60dd6e8 |
completed | May 9, 2026, 9:38 p.m. |
Created at: April 10, 2026, 4:50 a.m.