Triple
T4630273
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frosinone |
E101395
|
entity |
| Predicate | celebratesLocalFeastDay |
P27473
|
FINISHED |
| Object | 20 August |
—
|
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: 20 August | Statement: [Frosinone, celebratesLocalFeastDay, 20 August]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: celebratesLocalFeastDay Context triple: [Frosinone, celebratesLocalFeastDay, 20 August]
-
A.
feastDayObservedOn
chosen
Indicates that a particular feast day is celebrated or formally observed on a specified calendar date.
-
B.
majorFeast
Indicates that an event or celebration is recognized as a major religious or cultural feast of high importance.
-
C.
sharesFeastDayWith
Indicates that two entities are commemorated or celebrated on the same feast day in a liturgical or religious calendar.
-
D.
feastDayHonors
Indicates that a particular feast day is dedicated to honoring or commemorating a specific person, group, or event.
-
E.
hasFeastOrCommemoration
Indicates that a particular day, event, or context includes an associated religious feast, liturgical celebration, or commemorative observance.
- 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_69bd43d2f1c081908cd4b7ec48ecc73d |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd5a316ef48190831970ec914cf5a2 |
completed | March 20, 2026, 2:31 p.m. |
| PD | Predicate disambiguation | batch_69bd5233cb5081908807e2b150f0ca06 |
completed | March 20, 2026, 1:57 p.m. |
Created at: March 20, 2026, 1:13 p.m.