Triple
T15464164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sunnmørsalpene |
E371983
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Stranda |
E494773
|
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: Stranda | Statement: [Sunnmørsalpene, near, Stranda]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stranda Context triple: [Sunnmørsalpene, near, Stranda]
-
A.
Stranda
chosen
Stranda is a village and municipality in western Norway known for its scenic fjord landscapes and winter sports opportunities.
-
B.
Barstrand
Barstrand is a small coastal settlement on the island of Gimsøya in Norway’s Lofoten archipelago.
-
C.
Marstrand
Marstrand is a historic seaside town and popular sailing destination on Sweden’s west coast, known for its fortress and picturesque archipelago setting.
-
D.
Nordstrand
Nordstrand is a low-lying, dike-protected island off the coast of Schleswig-Holstein in northern Germany, known for its North Sea marshland landscape and traditional Frisian culture.
-
E.
Nordstrand
Nordstrand is a mainly residential borough in the southeastern part of Oslo, Norway, known for its hillside location overlooking the Oslofjord.
- 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_69d85cc8bd308190886949510b42e764 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f1927708190a0d2b63e75469a0e |
completed | April 16, 2026, 1:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff2cff942081908a2f5351079666a3 |
completed | May 9, 2026, 12:47 p.m. |
Created at: April 10, 2026, 3:33 a.m.