Triple
T21052936
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Visby Airport |
E518634
|
entity |
| Predicate | serves |
P98
|
FINISHED |
| Object | Visby |
—
|
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: Visby | Statement: [Visby Airport, serves, Visby]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Visby Context triple: [Visby Airport, serves, Visby]
-
A.
Visby
chosen
Visby is a well-preserved medieval Hanseatic town on the Swedish island of Gotland, renowned for its historic city wall and UNESCO World Heritage status.
-
B.
Karlskrona
Karlskrona is a historic Swedish coastal city and naval base known for its well-preserved maritime architecture and UNESCO-listed naval port.
-
C.
Halmstad
Halmstad is a coastal city in southwestern Sweden known for its historic town center, harbor, and role as a strategic site in Scandinavian conflicts.
-
D.
Halmstad
Halmstad is a village in Moss municipality in Viken county, southeastern Norway.
-
E.
Kristianstad
Kristianstad is a historic city in southern Sweden known for its well-preserved Renaissance architecture and proximity to the wetlands of the Kristianstad Vattenrike Biosphere Reserve.
- 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_69e0b5053ac48190921529544959e906 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fd7cabe881909e6b258a14d501a6 |
completed | April 21, 2026, 4:30 a.m. |
Created at: April 16, 2026, 2:36 p.m.