Triple
T18769928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Custer County, Idaho |
E458990
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Borah Peak |
—
|
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: Borah Peak | Statement: [Custer County, Idaho, contains, Borah Peak]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Borah Peak Context triple: [Custer County, Idaho, contains, Borah Peak]
-
A.
Borah Peak
chosen
Borah Peak is the tallest mountain in Idaho, known for its rugged terrain and prominence in the Lost River Range.
-
B.
Larkya Peak
Larkya Peak is a high Himalayan mountain in Nepal, known as one of the prominent summits of the Mansiri Himal range near the Manaslu region.
-
C.
Birobong Peak
Birobong Peak is a prominent summit of North Korea’s Mount Kumgang (Kumgangsan), known for its scenic, rugged granite landscapes.
-
D.
Gondogoro Peak
Gondogoro Peak is a high mountain in Pakistan’s Karakoram range, popular with trekkers and climbers for its challenging ascent and views of nearby 8,000-meter giants.
-
E.
Tilicho Peak
Tilicho Peak is a high mountain in the Annapurna range of the Himalayas in Nepal, known for its dramatic slopes above Tilicho Lake and challenging climbing routes.
- 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_69d8d395dba0819087568404508590cb |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e58d8782b4819080513fb46798c4db |
completed | April 20, 2026, 2:20 a.m. |
Created at: April 10, 2026, 11:52 a.m.