Triple
T31883614
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Basílica de Nossa Senhora de Nazaré |
E813946
|
entity |
| Predicate | festivalOccurs |
P165779
|
FINISHED |
| Object | annually in October |
—
|
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: annually in October | Statement: [Basílica de Nossa Senhora de Nazaré, festivalOccurs, annually in October]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: festivalOccurs Context triple: [Basílica de Nossa Senhora de Nazaré, festivalOccurs, annually in October]
-
A.
festivalCalendar
Indicates that there is a scheduled festival or celebration associated with a particular time or date in a calendar.
-
B.
festivalFunction
Indicates that an event serves as a festival or is functioning in the role of a festival within a given context.
-
C.
festivalHeldIn
Indicates that a festival takes place or is hosted at a specific location or venue.
-
D.
festivalActivity
Indicates that an entity is an event, performance, or engagement that takes place as part of a festival’s organized program.
-
E.
festivalHeldOnOrAround
chosen
Indicates that a festival customarily takes place on or near a specified date or time period.
- 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_69f348ed74bc81909846aaa6a3c7318c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b0d99fe08190897822f9b6406e11 |
completed | May 3, 2026, 2:20 a.m. |
| PD | Predicate disambiguation | batch_69f6aca59d4881908d14ed47962703bd |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 30, 2026, 11:56 p.m.