Triple
T11364530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hunt Trail |
E269168
|
entity |
| Predicate | accesses |
P1985
|
FINISHED |
| Object | Katahdin summit |
E53474
|
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: Katahdin summit | Statement: [Hunt Trail, accesses, Katahdin summit]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Katahdin summit Context triple: [Hunt Trail, accesses, Katahdin summit]
-
A.
Mount Katahdin
chosen
Mount Katahdin is the highest peak in Maine and a prominent mountain in Baxter State Park, renowned as the northern terminus of the Appalachian Trail and a central symbol of the state's rugged wilderness.
-
B.
Killington Peak
Killington Peak is one of the highest and most prominent mountains in Vermont, known for its major ski resort and extensive outdoor recreation opportunities.
-
C.
Mount Harvard
Mount Harvard is one of Colorado's highest fourteeners, a prominent peak in the Rocky Mountains popular with climbers and hikers.
-
D.
Algonquin Peak
Algonquin Peak is the second-highest mountain in New York’s Adirondack High Peaks, popular with hikers for its alpine summit and expansive views.
-
E.
Nagog Hill
Nagog Hill is a modest, wooded rise in Acton, Massachusetts, known for its conservation land and network of hiking trails.
- 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_69d6aacca1048190b39dbbc2174616fa |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7ea4589908190948a8225768e1eec |
completed | April 9, 2026, 6:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f12fa07fc081909a42f9c19ad38511 |
completed | April 28, 2026, 10:07 p.m. |
Created at: April 8, 2026, 9:33 p.m.