Triple
T1086985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dormition Fast |
E24074
|
entity |
| Predicate | fastingRule |
P6166
|
FINISHED |
| Object | abstinence from meat |
—
|
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: abstinence from meat | Statement: [Dormition Fast, fastingRule, abstinence from meat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fastingRule Context triple: [Dormition Fast, fastingRule, abstinence from meat]
-
A.
preparatoryFastBegins
Indicates that a required period of fasting starts in preparation for a subsequent event, action, or ritual.
-
B.
majorFastDay
Indicates that an entity is associated with a significant religious fast day observed with major or stringent fasting practices.
-
C.
religiousRestriction
chosen
Indicates that one entity imposes, experiences, or is subject to limitations or rules based on religious beliefs or practices in relation to another entity or context.
-
D.
observanceMayVaryByCountry
Indicates that the way something is observed, celebrated, or practiced can differ depending on the country.
-
E.
allowsLentenDispensation
Indicates that an authority grants an exemption from standard Lenten obligations or restrictions.
- 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_69a49404428c819092dcc9632f5f7b8b |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b963161081908a523c8d63871652 |
completed | March 1, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69a4b7407914819092ed933a7316b450 |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:42 p.m.