Triple
T19555049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sandefjord Airport Torp |
E489284
|
entity |
| Predicate | cityServed |
P82
|
FINISHED |
| Object | Larvik |
—
|
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: Larvik | Statement: [Sandefjord Airport Torp, cityServed, Larvik]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Larvik Context triple: [Sandefjord Airport Torp, cityServed, Larvik]
-
A.
Larvik
chosen
Larvik is a coastal town and municipality in Vestfold, Norway, known for its harbor, beaches, and historic connections to the shipping and timber industries.
-
B.
Lyngdal
Lyngdal is a coastal town and municipality in southern Norway known for its beaches, fjords, and tourism.
-
C.
Sokna
Sokna is an extinct Eastern Berber language formerly spoken around the oasis town of Sokna in central Libya.
-
D.
Levanger
Levanger is a historic town and municipality in Trøndelag county, Norway, known for its traditional wooden architecture and role as a regional commercial and educational center.
-
E.
Lørenskog
Lørenskog is a suburban municipality in Viken county, Norway, located just east of Oslo and known for its residential areas and commercial centers.
- 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_69d8e8dc5d8c8190a6d7bd8864f43ca0 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63d335f888190abfc5ba974d3c65e |
completed | April 20, 2026, 2:50 p.m. |
Created at: April 10, 2026, 1:42 p.m.