Triple
T13172904
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Henry Mountains |
E313022
|
entity |
| Predicate | highestPoint |
P210
|
FINISHED |
| Object | Mount Ellen |
E592532
|
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 Ellen | Statement: [Henry Mountains, highestPoint, Mount Ellen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Ellen Context triple: [Henry Mountains, highestPoint, Mount Ellen]
-
A.
Mount Ellen
chosen
Mount Ellen is a prominent peak in Utah’s remote Henry Mountains, known for its rugged terrain, high elevation, and expansive views over the surrounding canyonlands.
-
B.
Mount Ellen
Mount Ellen is a prominent Vermont peak in the Green Mountains, known for its alpine hiking trails and as part of the Sugarbush ski area.
-
C.
Bishop Hill
Bishop Hill is a prominent hill in the Lomond Hills range of Fife, Scotland, known for its open moorland and panoramic views over Loch Leven and the surrounding countryside.
-
D.
Hallglen
Hallglen is a residential area and housing estate within the town of Falkirk in central Scotland.
-
E.
Mount Pleasant
Mount Pleasant is a suburban town in Westchester County, New York, known for its residential communities and proximity to major reservoirs and parklands.
- 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_69d806ac3ee081909b2fd27d060aa974 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98c2f22b881908a0af3af0a0af971 |
completed | April 10, 2026, 11:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6eafb81288190a6dcc3bd872998d8 |
completed | May 3, 2026, 6:28 a.m. |
Created at: April 9, 2026, 9:14 p.m.