Triple
T27058540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ritacuba Blanco Glacier |
E684969
|
entity |
| Predicate | typeOfSnowAndIceFeature |
P16701
|
FINISHED |
| Object | valley glacier |
—
|
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: valley glacier | Statement: [Ritacuba Blanco Glacier, typeOfSnowAndIceFeature, valley glacier]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfSnowAndIceFeature Context triple: [Ritacuba Blanco Glacier, typeOfSnowAndIceFeature, valley glacier]
-
A.
glacierType
chosen
Indicates the specific classification or category of a glacier based on its form, dynamics, or setting.
-
B.
hasSnowType
Indicates that something possesses or is characterized by a particular type or category of snow.
-
C.
hasIceSurface
Indicates that an entity possesses or is characterized by a surface composed primarily of ice.
-
D.
hasSnowAndIce
Indicates that the subject is covered with or contains both snow and ice.
-
E.
snowCover
Indicates that one entity is covered by or blanketed with snow.
- 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_69ef14829fac8190914bef9ecc3005d7 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69fd82ed2a4c81908bd7797fbd2e3d08 |
completed | May 8, 2026, 6:30 a.m. |
| PD | Predicate disambiguation | batch_69fd814cc10481908e4f8123d35a5d0c |
completed | May 8, 2026, 6:23 a.m. |
Created at: April 27, 2026, 8:19 a.m.