Triple
T22590554
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Olympus Wilderness |
E564935
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Blue Glacier |
—
|
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: Blue Glacier | Statement: [Olympus Wilderness, contains, Blue Glacier]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Blue Glacier Context triple: [Olympus Wilderness, contains, Blue Glacier]
-
A.
Blue Glacier
chosen
Blue Glacier is a prominent mountain glacier on Washington State’s Mount Olympus within Olympic National Park.
-
B.
Glacier
Glacier is a light, cool-toned color finish used as one of the available options for the Microsoft Surface Duo device.
-
C.
Glacier
Glacier is a small unincorporated community in Whatcom County, Washington, serving as a gateway to the Mount Baker-Snoqualmie National Forest and Mount Baker ski area.
-
D.
Black Glacier
Black Glacier is a mountain glacier located on the slopes of Mount Olympus in Washington's Olympic Mountains.
-
E.
Glacier Noir
Glacier Noir is a large, debris-covered valley glacier in the Écrins massif of the French Alps, known for its dark, rock-strewn surface and dramatic high-mountain setting.
- 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_69e245836014819091b91ed3074742a3 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f16160651081909d23735336fd7a16 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 2:48 p.m.