Triple
T30192399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yamunotri region |
E767526
|
entity |
| Predicate | hasGlacierSource |
P168835
|
FINISHED |
| Object | Bandarpunch massif |
—
|
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: Bandarpunch massif | Statement: [Yamunotri region, hasGlacierSource, Bandarpunch massif]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGlacierSource Context triple: [Yamunotri region, hasGlacierSource, Bandarpunch massif]
-
A.
hasGlacier
Indicates that one entity possesses, contains, or is characterized by the presence of a glacier.
-
B.
hasGlacierOutlet
Indicates that a glacier has a specific outlet feature or location through which its ice or meltwater flows or exits.
-
C.
hasGlacierAccess
Indicates that an entity has direct access to, or is reachable from, a glacier (e.g., via paths, routes, or physical adjacency).
-
D.
isGlaciallyFed
Indicates that something (typically a body of water) receives its primary input or supply from melting glacial ice.
-
E.
hasGlacierArm
Indicates that a glacier possesses or extends into a subsidiary arm or branch of ice connected to it.
- F. None of above. chosen
Provenance (4 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_69f2247db1108190835c0727c97637c3 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67f8572f081909dd920b4b55f488b |
completed | May 2, 2026, 10:49 p.m. |
| PD | Predicate disambiguation | batch_69f675ff62c48190a634bbb8896973b9 |
completed | May 2, 2026, 10:09 p.m. |
| PDg | Predicate description generation | batch_69f676f73c3481909f01fa69851b7298 |
completed | May 2, 2026, 10:13 p.m. |
Created at: April 29, 2026, 7:29 p.m.