Triple
T16243743
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Porsanger |
E394315
|
entity |
| Predicate | hasGeographicalFeature |
P1094
|
FINISHED |
| Object | Stabburselva river |
E389725
|
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: Stabburselva river | Statement: [Porsanger, hasGeographicalFeature, Stabburselva river]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stabburselva river Context triple: [Porsanger, hasGeographicalFeature, Stabburselva river]
-
A.
Stabburselva
chosen
Stabburselva is a river in northern Norway known for flowing through Stabbursdalen National Park and for its rich salmon fishing.
-
B.
Hellelandselva river
Hellelandselva river is a watercourse in southwestern Norway that flows through the municipality of Eigersund in Rogaland county.
-
C.
Beisfjordelva river
Beisfjordelva river is a Norwegian river in Nordland county that flows through the Beisfjord area before emptying into the Ofotfjord.
-
D.
Randselva
Randselva is a river in eastern Norway that drains into Randsfjorden and is known for flowing through the Hønefoss area.
-
E.
Steinsdalselva
Steinsdalselva is a river in the municipality of Kvam in Vestland county, western Norway, known for flowing through a scenic valley landscape.
- 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_69d87f2171208190951025e526947816 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e24560060c8190ace4f4c0bd0d886d |
completed | April 17, 2026, 2:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a001f8ae4288190b59e4af3e3d95000 |
completed | May 10, 2026, 6:02 a.m. |
Created at: April 10, 2026, 5:04 a.m.