Triple
T15054157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Talum Glacier |
E379444
|
entity |
| Predicate | hasPrimaryAccumulationSource |
P60019
|
FINISHED |
| Object | snowfall |
—
|
LITERAL 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: snowfall | Statement: [Talum Glacier, hasPrimaryAccumulationSource, snowfall]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryAccumulationSource Context triple: [Talum Glacier, hasPrimaryAccumulationSource, snowfall]
-
A.
hasMainSource
chosen
Indicates that one entity serves as the primary or principal source or origin for another entity.
-
B.
hasPrimaryPool
Indicates that an entity is associated with or designated to use a particular pool as its main or default pool.
-
C.
hasPrimary
Indicates that one entity is designated as the main or most important instance (the primary) in relation to another entity.
-
D.
hasPrimaryAssociation
Indicates that one entity is chiefly or most directly connected, linked, or related to another among possible associations.
-
E.
hasSecondarySource
Indicates that an entity is supported, documented, or referenced by a secondary source rather than by a primary or original source.
- F. None of above.
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_69d85cd64d108190853797a95c11cc45 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69deda92091c81909180f486edf01405 |
completed | April 15, 2026, 12:23 a.m. |
| PD | Predicate disambiguation | batch_69deb95a182081908fffc4402b02a394 |
completed | April 14, 2026, 10:02 p.m. |
Created at: April 10, 2026, 3:01 a.m.