Triple
T15302694
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Folgefonna |
E365826
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Søndre Folgefonna |
E365826
|
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: Søndre Folgefonna | Statement: [Folgefonna, hasPart, Søndre Folgefonna]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Søndre Folgefonna Context triple: [Folgefonna, hasPart, Søndre Folgefonna]
-
A.
Folgefonna
chosen
Folgefonna is one of Norway’s largest glacier systems, covering much of the Folgefonna peninsula in Vestland county and forming a prominent natural landmark in western Norway.
-
B.
Skraperudtjern
Skraperudtjern is a small lake located in the Østensjø area of Oslo, Norway, known for its natural surroundings and local recreational use.
-
C.
Kvitfjell
Kvitfjell is a Norwegian alpine ski resort renowned for hosting major international competitions, including Olympic and World Cup events.
-
D.
Hodnefjell
Hodnefjell is an island that forms part of the Finnøy archipelago in Norway.
-
E.
Kvitøyjøkulen
Kvitøyjøkulen is the main ice cap covering much of Kvitøya, a remote Arctic island in the Svalbard archipelago of Norway.
- 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_69d85a113ee881908e297a1d38dd79fa |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03ccd575c8190aa43262d3b73ef3c |
completed | April 16, 2026, 1:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff133d171c8190918c9624bcdb7451 |
completed | May 9, 2026, 10:58 a.m. |
Created at: April 10, 2026, 3:15 a.m.