Triple
T26287084
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ordre de Saint-Michel |
E661165
|
entity |
| Predicate | ceremoniesHeldOn |
P2731
|
FINISHED |
| Object | Feast of Saint Michael |
—
|
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: Feast of Saint Michael | Statement: [Ordre de Saint-Michel, ceremoniesHeldOn, Feast of Saint Michael]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ceremoniesHeldOn Context triple: [Ordre de Saint-Michel, ceremoniesHeldOn, Feast of Saint Michael]
-
A.
ceremonyHeldOn
chosen
Indicates that a specific ceremony took place on a particular date or day.
-
B.
ceremonyHeld
Indicates that a formal ceremony or ritual event has taken place at a particular time and/or location.
-
C.
hasCeremonies
Indicates that an entity conducts, includes, or is associated with one or more formal ceremonies or ritual events.
-
D.
ceremonyHeldNear
Indicates that a ceremony takes place at a location that is geographically close to a specified reference place or object.
-
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_69ee812bbd448190be4d7478b057990a |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f60e781b108190b5479e4992d58695 |
completed | May 2, 2026, 2:47 p.m. |
| PD | Predicate disambiguation | batch_69f5f7ff548c8190a23e98c5e66e0bc7 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 10:05 p.m.