Triple
T31865114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chinook winds |
E813429
|
entity |
| Predicate | occursOnSideOf |
P86049
|
FINISHED |
| Object | leeward side of mountain ranges |
—
|
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: leeward side of mountain ranges | Statement: [Chinook winds, occursOnSideOf, leeward side of mountain ranges]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: occursOnSideOf Context triple: [Chinook winds, occursOnSideOf, leeward side of mountain ranges]
-
A.
isBSideOf
Indicates that one entity is located on the B side or secondary face of another entity, typically in a two-sided or dual-orientation context.
-
B.
wasOnSideOf
Indicates that one entity supported, aligned with, or took the same side as another entity in a conflict, dispute, or opposing situation.
-
C.
situatedOnSideOf
Indicates that one entity is located along or beside the lateral part or edge of another entity.
-
D.
onSide
chosen
Indicates that one entity is positioned along or adjacent to the side of another entity.
-
E.
operatesOnSide
Indicates that an action or process is performed specifically on a particular side or lateral aspect of an object or 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_69f348ecb07481909c8f72619131b115 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b07340088190a0cd5b1ebecc5424 |
completed | May 3, 2026, 2:18 a.m. |
| PD | Predicate disambiguation | batch_69f6aca59d4881908d14ed47962703bd |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 30, 2026, 11:53 p.m.