Triple
T12441360
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yosemite National Park road network |
E297277
|
entity |
| Predicate | seasonalClosureReason |
P8451
|
FINISHED |
| Object | snow |
—
|
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: snow | Statement: [Yosemite National Park road network, seasonalClosureReason, snow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seasonalClosureReason Context triple: [Yosemite National Park road network, seasonalClosureReason, snow]
-
A.
temporarilyClosedFrom
Indicates that an entity is not accessible or operating for a specific, limited time period starting from a given point.
-
B.
seasonOpeningOrClosing
Indicates that an event marks either the beginning or the end of a particular season.
-
C.
closureReason
chosen
Indicates the reason or cause for which an entity, process, or case has been closed or terminated.
-
D.
restaurantClosureDate
Indicates the date on which a restaurant ceases or ceased operations, marking its official closure.
-
E.
peakSeasonReason
Indicates that there is a specific cause or justification for why a given time period is considered the peak season for something.
- 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_69d6ada166c48190b902972cd2408fa3 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94df948308190ace333230a4a3b38 |
completed | April 10, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_69d94d391c548190996a8c698357f273 |
completed | April 10, 2026, 7:19 p.m. |
Created at: April 8, 2026, 9:55 p.m.