Triple
T22545465
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lucy Walker |
E557410
|
entity |
| Predicate | climbed |
P6287
|
FINISHED |
| Object | Bishorn |
—
|
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: Bishorn | Statement: [Lucy Walker, climbed, Bishorn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bishorn Context triple: [Lucy Walker, climbed, Bishorn]
-
A.
Bishorn
chosen
Bishorn is a 4,153-meter-high glaciated mountain in the Swiss Alps, popular with climbers for its relatively accessible ascent and panoramic views.
-
B.
Hösthorn
Hösthorn is a poetry collection by Swedish Nobel laureate Erik Axel Karlfeldt, known for its evocative depictions of nature and rural life.
-
C.
Arbengrat
Arbengrat is a prominent alpine ridge associated with the Ober Gabelhorn in the Swiss Alps, known as one of its main climbing routes.
-
D.
Strahlhorn
Strahlhorn is a prominent 4,190-meter alpine peak in the Pennine Alps of Switzerland, popular with mountaineers for its glaciated routes and panoramic views.
-
E.
Driestichorn
Driestichorn is a mountain in the Swiss Alps that forms part of the rugged cirque enclosing the Oberaletsch Glacier.
- 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_69e11e58662081909ae346ab384514ca |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15f35b9888190b4e1b50d5097b211 |
completed | April 29, 2026, 1:30 a.m. |
Created at: April 16, 2026, 8:51 p.m.