Triple
T11211624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fête des Vignerons |
E265321
|
entity |
| Predicate | 2019EditionDuration |
P84227
|
FINISHED |
| Object | approximately three weeks |
—
|
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: approximately three weeks | Statement: [Fête des Vignerons, 2019EditionDuration, approximately three weeks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 2019EditionDuration Context triple: [Fête des Vignerons, 2019EditionDuration, approximately three weeks]
-
A.
edition2019Host
Indicates that the subject served as the host of the 2019 edition of a particular event or series.
-
B.
durationOfFestivalContext
chosen
Indicates the length of time for which a festival takes place within a given contextual setting or event instance.
-
C.
finalVenue2019–2021
Indicates that an entity served as the final venue for the referenced event or activity during the years 2019 through 2021.
-
D.
intendedDuration
Indicates the planned or expected length of time for which an action, event, or state is meant to occur or remain in effect.
-
E.
eraDuration
Indicates the length of time that a particular era or period spans.
- 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_69d6aac59460819089b9848b27f57848 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8d6f5d4819086dcb776a0d469e8 |
completed | April 9, 2026, 5:58 p.m. |
| PD | Predicate disambiguation | batch_69d75cfbbb188190861efd5d94fe27da |
completed | April 9, 2026, 8:02 a.m. |
Created at: April 8, 2026, 9:30 p.m.