Triple
T12892016
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wichita Mountains |
E308391
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Elk Mountain |
E1058742
|
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: Elk Mountain | Statement: [Wichita Mountains, contains, Elk Mountain]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elk Mountain Context triple: [Wichita Mountains, contains, Elk Mountain]
-
A.
Elk Mountain
chosen
Elk Mountain is a prominent granite peak in southwestern Oklahoma known for its scenic hiking trails and panoramic views within the Wichita Mountains region.
-
B.
Lone Peak
Lone Peak is a prominent natural summit located within Oklahoma’s Gloss Mountains State Park, known for its striking red mesas and scenic views.
-
C.
Boulder Mountain
Boulder Mountain is a high-elevation, forested plateau in south-central Utah known for its extensive aspen groves, numerous lakes, and scenic recreation opportunities within the Dixie National Forest.
-
D.
Regal Mountain
Regal Mountain is a prominent high peak in Alaska’s Wrangell Mountains, known for its extensive glaciation and remote, rugged terrain.
-
E.
West Mountain
West Mountain is one of the main ski slopes within the Rusutsu Resort in Hokkaido, Japan, offering a variety of runs for skiers and snowboarders.
- 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_69d7bdf7c1f0819098102569a8d8cbf5 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97146d2208190be5ae26e51193b67 |
completed | April 10, 2026, 9:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c0d12cd88190b6e205ad98296ed9 |
completed | May 3, 2026, 9:40 p.m. |
Created at: April 9, 2026, 5:39 p.m.