Triple
T22967413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unteraar Glacier |
E571083
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Finsteraarhorn |
—
|
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: Finsteraarhorn | Statement: [Unteraar Glacier, near, Finsteraarhorn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Finsteraarhorn Context triple: [Unteraar Glacier, near, Finsteraarhorn]
-
A.
Finsteraarhorn
chosen
Finsteraarhorn is a prominent, glaciated peak in the Swiss Alps known for its remote location and striking pyramidal shape.
-
B.
Fiescherhorn
Fiescherhorn is a prominent peak in the Bernese Alps of Switzerland, known for its glaciated slopes and challenging alpine climbs.
-
C.
Lauteraarhorn
Lauteraarhorn is a prominent, steep pyramidal peak in the Swiss Bernese Alps, known for its challenging climbs and striking glaciated surroundings.
-
D.
Täschhorn
Täschhorn is a prominent 4,491-meter alpine peak in the Swiss canton of Valais, known for its steep faces and challenging climbing routes near the Matterhorn.
-
E.
Riederhorn
Riederhorn is a mountain in the Swiss Alps overlooking the Aletsch Glacier in the canton of Valais.
- 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_69e245b2c6548190a0e4c7f2f7df2d48 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1822f57088190addc6857063b4cca |
completed | April 29, 2026, 3:59 a.m. |
Created at: April 17, 2026, 3:48 p.m.