Triple
T3579239
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lysefjord |
E75760
|
entity |
| Predicate | hasCliff |
P11724
|
FINISHED |
| Object | Kjerag |
E365817
|
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: Kjerag | Statement: [Lysefjord, hasCliff, Kjerag]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kjerag Context triple: [Lysefjord, hasCliff, Kjerag]
-
A.
Kjerag
chosen
Kjerag is a famous mountain in Norway’s Lysefjord known for its towering cliffs, popular hiking routes, and the iconic Kjeragbolten boulder wedged between two rock faces.
-
B.
Okertal
Okertal is a scenic valley in the Harz Mountains of Germany, known for its rugged rock formations, forests, and the Oker River running through it.
-
C.
Stetind
Stetind is a distinctive, obelisk-shaped granite mountain in Nordland, Norway, often called Norway’s national mountain and renowned among climbers and photographers.
-
D.
Kinsarvik
Kinsarvik is a small village in western Norway known for its scenic fjord landscape, waterfalls, and role as a gateway to hiking areas in the Hardanger region.
-
E.
Koma Kulshan
Koma Kulshan is the Indigenous (primarily Lummi) name for Mount Baker, a prominent glaciated stratovolcano in the North Cascades of Washington State.
- 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.