Triple
T21880236
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madonna di San Luca |
E540257
|
entity |
| Predicate | feastOrProcessionSeason |
P29256
|
FINISHED |
| Object | spring |
—
|
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: spring | Statement: [Madonna di San Luca, feastOrProcessionSeason, spring]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: feastOrProcessionSeason Context triple: [Madonna di San Luca, feastOrProcessionSeason, spring]
-
A.
festivalSeason
chosen
Indicates that a time period is designated or recognized as the season during which a particular festival or set of festivals takes place.
-
B.
feast
Indicates that an entity participates in or hosts a large, elaborate meal or celebration involving abundant food and communal dining.
-
C.
feastType
Indicates the specific kind or category of feast associated with an event or occasion.
-
D.
feastFollows
Indicates that a feast or celebratory meal occurs after and as a consequence of a preceding event or action.
-
E.
hasPilgrimageOrFeast
Indicates that there is a religious pilgrimage or feast associated with, dedicated to, or occurring in relation to the referenced entity.
- 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_69e0c479a98081908ce333853fdd4348 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f118e600c08190bc96203f03f1e58a |
completed | April 28, 2026, 8:30 p.m. |
| PD | Predicate disambiguation | batch_69e6be9394f88190945ddd1dc004d29d |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 7:04 p.m.