Triple
T35436751
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Col de la Bonette |
E1024229
|
entity |
| Predicate | opensTypically |
P56215
|
FINISHED |
| Object | late spring to early autumn |
—
|
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: late spring to early autumn | Statement: [Col de la Bonette, opensTypically, late spring to early autumn]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: opensTypically Context triple: [Col de la Bonette, opensTypically, late spring to early autumn]
-
A.
opensOn
chosen
Indicates that an entity begins operating, becomes accessible, or starts being available at a specified time or on a specified date.
-
B.
opensBy
Indicates that one entity is opened, unlocked, or made accessible through the use or action of another entity.
-
C.
opensWhen
Indicates that one entity becomes open or accessible in response to a condition, trigger, or action associated with another entity.
-
D.
opens
Indicates that one entity causes or allows another entity (such as an object, space, or resource) to become accessible or no longer closed.
-
E.
opensInto
Indicates that one space, structure, or passage directly leads or provides access into another space or area.
- 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_69f76df743c48190aecb6dd79efb0d95 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f795bd7d40819087be4fe0e15a5ed3 |
completed | May 3, 2026, 6:36 p.m. |
| PD | Predicate disambiguation | batch_69f7910770108190bdd39ddb5d304f54 |
completed | May 3, 2026, 6:16 p.m. |
Created at: May 3, 2026, 4:04 p.m.