Triple
T23231001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bøverdalen |
E581152
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Glittertind |
—
|
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: Glittertind | Statement: [Bøverdalen, locatedNear, Glittertind]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Glittertind Context triple: [Bøverdalen, locatedNear, Glittertind]
-
A.
Glittertind
chosen
Glittertind is one of Norway’s highest mountains, located in the Jotunheimen range and known for its glacier-capped summit.
-
B.
Heilefjellet
Heilefjellet is a mountain located in the coastal municipality of Bremanger in Vestland county, western Norway.
-
C.
Børvasstindan
Børvasstindan is a striking mountain range in Nordland county, Norway, known for its sharp peaks, rugged alpine terrain, and popular hiking and climbing routes.
-
D.
Hermannsdalstinden
Hermannsdalstinden is a prominent mountain peak in Norway’s Lofoten archipelago, renowned for its dramatic alpine scenery and challenging hiking routes.
-
E.
Milorgfjella
Milorgfjella is a mountain subrange in Queen Maud Land, Antarctica, forming part of the larger Heimefront Range.
- 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_69e246043c48819089bae72c9a9c306c |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f19231ef908190a791b4967916a66f |
completed | April 29, 2026, 5:08 a.m. |
Created at: April 17, 2026, 4:09 p.m.