Triple
T3579238
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lysefjord |
E75760
|
entity |
| Predicate | hasCliff |
P11724
|
FINISHED |
| Object | Preikestolen |
E365816
|
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: Preikestolen | Statement: [Lysefjord, hasCliff, Preikestolen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Preikestolen Context triple: [Lysefjord, hasCliff, Preikestolen]
-
A.
Preikestolen
chosen
Preikestolen is a famous steep cliff and viewpoint in southwestern Norway that towers over the Lysefjord and attracts many hikers and tourists.
-
B.
Galdhøpiggen
Galdhøpiggen is the highest mountain in Norway and Scandinavia, located in the Jotunheimen range.
-
C.
Higravstinden
Higravstinden is a prominent mountain peak in Norway’s Lofoten archipelago, known for its rugged alpine terrain and striking coastal views.
-
D.
Haraldshaugen national monument
Haraldshaugen national monument is a historic memorial in Haugesund, Norway, traditionally regarded as marking the burial site of Norway’s first king, Harald Fairhair.
-
E.
St. Hanshaugen
St. Hanshaugen is a central borough of Oslo, Norway, known for its large hillside park and vibrant urban residential areas.
- 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_69ad85d5e3008190bdfe0bacdd1f5a1b |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc0defe14819095a337a840e33300 |
completed | March 8, 2026, 6:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b3bbc6bc948190a517639f5d79c0a3 |
completed | March 13, 2026, 7:24 a.m. |
Created at: March 8, 2026, 3:21 p.m.