Triple
T18345712
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spiez |
E439532
|
entity |
| Predicate | hasScenicViewOf |
P9193
|
FINISHED |
| Object | Niesen mountain |
—
|
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: Niesen mountain | Statement: [Spiez, hasScenicViewOf, Niesen mountain]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Niesen mountain Context triple: [Spiez, hasScenicViewOf, Niesen mountain]
-
A.
Niesen mountain
chosen
Niesen mountain is a prominent, pyramid-shaped peak in the Bernese Alps of Switzerland, overlooking Lake Thun and popular for hiking and panoramic views.
-
B.
Agil Mountain
Agil Mountain is an alternative name for Mount Taron, a prominent peak in Papua New Guinea’s New Ireland Province and one of the highest mountains in the Bismarck Archipelago.
-
C.
Unaka Mountain
Unaka Mountain is a prominent peak along the Appalachian range on the Tennessee–North Carolina border, noted for its high elevation, dense forests, and scenic vistas.
-
D.
Yudu Mountain
Yudu Mountain is a scenic natural area in Beijing’s Yanqing District, known for its mountainous landscapes and outdoor recreation opportunities.
-
E.
Berya Mountain
Berya Mountain is the tallest peak in Russia’s remote Stanovoy Range in eastern Siberia.
- 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_69d8b9175fec8190af865699b4e64d8c |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e514f3bb888190bdeea4c4d114a43b |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 10:37 a.m.