Triple
T19658518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lewis Glacier |
E472013
|
entity |
| Predicate | isSmallRelativeTo |
P8238
|
FINISHED |
| Object | other Cascade Range glaciers |
—
|
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: other Cascade Range glaciers | Statement: [Lewis Glacier, isSmallRelativeTo, other Cascade Range glaciers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isSmallRelativeTo Context triple: [Lewis Glacier, isSmallRelativeTo, other Cascade Range glaciers]
-
A.
isSmall
Indicates that one entity has a size that is relatively small, either in absolute terms or compared to a reference standard or another entity.
-
B.
hasRelativeSize
chosen
Indicates that one entity’s size is being compared to another entity’s size, expressing a relative rather than absolute magnitude.
-
C.
isSmallestOf
Indicates that an entity has the minimum size or value within a specified set or group of entities.
-
D.
smallerThan
Indicates that one entity has a strictly lesser size, dimension, or magnitude than another entity.
-
E.
isRelativeTo
Indicates that one entity has a familial or kinship relationship to another entity.
- 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_69d8e51395348190ac1416d46dfc6db0 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e641485ce481908b3860fa5e3a9f6e |
completed | April 20, 2026, 3:07 p.m. |
| PD | Predicate disambiguation | batch_69e514e941008190898d978d7bde91e4 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:45 p.m.