Triple
T4398052
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manchester, Vermont |
E99540
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Mount Equinox |
E354234
|
NE FINISHED |
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 Equinox | Statement: [Manchester, Vermont, near, Mount Equinox]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Equinox Context triple: [Manchester, Vermont, near, Mount Equinox]
-
A.
Mount Equinox
chosen
Mount Equinox is a prominent peak in southwestern Vermont known for its scenic views, hiking trails, and status as the tallest mountain in the Taconic Range.
-
B.
Mount Twynam
Mount Twynam is one of the highest peaks in mainland Australia, located in the Snowy Mountains of New South Wales.
-
C.
Mount Curwood
Mount Curwood is a prominent peak in Michigan’s remote Huron Mountains, known as one of the state’s highest natural elevations.
-
D.
Mount Cirphis
Mount Cirphis is a mountain in the ancient Greek region of Phocis, near Delphi, known from classical geography and mythology.
-
E.
Mount Wister
Mount Wister is a prominent mountain peak in Wyoming’s Teton Range, known for its rugged terrain and challenging climbing routes.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69b345506b408190b0e3dee616738a7d |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b352adce588190b9e6ed53458aa1e1 |
completed | March 12, 2026, 11:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bfd42f73b88190bb69bffa6a8b9efe |
completed | March 22, 2026, 11:36 a.m. |
Created at: March 12, 2026, 11:20 p.m.