Triple
T21387439
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Letnitsa Glacier |
E527541
|
entity |
| Predicate | boundedBy |
P224
|
FINISHED |
| Object | Mount Pisgah |
—
|
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: Mount Pisgah | Statement: [Letnitsa Glacier, boundedBy, Mount Pisgah]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Pisgah Context triple: [Letnitsa Glacier, boundedBy, Mount Pisgah]
-
A.
Mount Pisgah
Mount Pisgah is a prominent scenic peak in Vermont’s Northeast Kingdom, known for its hiking trails and dramatic cliffs overlooking Lake Willoughby.
-
B.
Mount Gilead
Mount Gilead is a small town in Montgomery County, North Carolina, known for its rural character and location near the Uwharrie National Forest.
-
C.
Mount Davidson
Mount Davidson is a mountain peak located in the Fitzsimmons Range of the Coast Mountains in British Columbia, Canada.
-
D.
Mount Davidson
Mount Davidson is the highest natural point in San Francisco, known for its prominent summit cross and panoramic city views.
-
E.
Mount Gaudry
chosen
Mount Gaudry is the highest mountain on Adelaide Island off the coast of the Antarctic Peninsula.
- 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_69e0b51ff3748190935c0a513c62a12b |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69ee62cb05288190a894f33850e22c03 |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 16, 2026, 5:12 p.m.