Triple
T24836614
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Église des Frères-Prêcheurs |
E621488
|
entity |
| Predicate | festivalVenueFor |
P112843
|
FINISHED |
| Object | Rencontres d’Arles |
—
|
NE NERFINISHED |
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: Rencontres d’Arles | Statement: [Église des Frères-Prêcheurs, festivalVenueFor, Rencontres d’Arles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: festivalVenueFor Context triple: [Église des Frères-Prêcheurs, festivalVenueFor, Rencontres d’Arles]
-
A.
hasVenueFor
chosen
Indicates that one entity provides or serves as the location or setting where an event, activity, or function takes place for another entity.
-
B.
internationalVenueFor
Indicates that a location serves as a host or site for events, activities, or functions involving participants or audiences from multiple countries.
-
C.
festivalOrganiser
Indicates that one entity is responsible for planning, coordinating, or managing a festival for another entity or context.
-
D.
festivalPresence
Indicates that an entity is present at, participates in, or is associated with a particular festival event.
-
E.
festivalHeldIn
Indicates that a festival takes place or is hosted at a specific location or venue.
- 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_69e2fac185d48190a0a6073ad1f6b792 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f43043512481909501a3979cac9947 |
completed | May 1, 2026, 4:46 a.m. |
| PD | Predicate disambiguation | batch_69f420fd375c81908ea4a4e60b76ee8f |
completed | May 1, 2026, 3:41 a.m. |
Created at: April 18, 2026, 5:18 a.m.