Triple
T35795911
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kootenay Pass |
E1034829
|
entity |
| Predicate | hasSnowShed |
P183685
|
FINISHED |
| Object | no |
—
|
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: no | Statement: [Kootenay Pass, hasSnowShed, no]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSnowShed Context triple: [Kootenay Pass, hasSnowShed, no]
-
A.
sheds
Indicates that one entity naturally loses, discards, or lets fall something from itself, such as hair, skin, leaves, or other material.
-
B.
homeShed
Indicates that one entity is a shed located at or belonging to another entity’s home.
-
C.
hasSnowShelter
Indicates that an entity possesses or provides a structure or feature that offers shelter or protection from snow.
-
D.
hasPorch
Indicates that one entity (typically a building or residence) includes or is equipped with a porch as part of its structure.
-
E.
hasSnowFenceInfrastructure
Indicates that there is infrastructure specifically installed or present to serve as a snow fence at the referenced location or object.
- 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_69f76e169bd081909f16cd8c9ee7870c |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7a25541c081909a2c3780af82c516 |
completed | May 3, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69f7a070e23881909a233370acb57384 |
completed | May 3, 2026, 7:22 p.m. |
| PDg | Predicate description generation | batch_69f7a162672481909773f8383d91159a |
completed | May 3, 2026, 7:26 p.m. |
Created at: May 3, 2026, 4:06 p.m.