Triple
T36667113
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Feast of the Meeting of Our Lord |
E905295
|
entity |
| Predicate | forefeastLength |
P186147
|
FINISHED |
| Object | 1 day (in Byzantine usage) |
—
|
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: 1 day (in Byzantine usage) | Statement: [Feast of the Meeting of Our Lord, forefeastLength, 1 day (in Byzantine usage)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: forefeastLength Context triple: [Feast of the Meeting of Our Lord, forefeastLength, 1 day (in Byzantine usage)]
-
A.
feastEndsOn
Indicates that a feast or celebratory event concludes on a specific date or time.
-
B.
extendedFeast
Indicates a situation where a feast or celebratory meal continues for an unusually long or prolonged period of time.
-
C.
feast
Indicates that an entity participates in or hosts a large, elaborate meal or celebration involving abundant food and communal dining.
-
D.
feastOf
Indicates that one entity is the religious or ceremonial feast day associated with another entity (such as a person, event, or deity).
-
E.
feastBeginsOn
Indicates that the start time or date of a feast coincides with a specified time or date.
- F. None of above. chosen
Provenance (4 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_69f76e6f10008190aea41746aa1b186e |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c83f5960819089610ed39c839678 |
completed | May 3, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69f7c4796ebc819084a0dc08505e5f14 |
completed | May 3, 2026, 9:56 p.m. |
| PDg | Predicate description generation | batch_69f7c776b4088190bef550c869da530d |
completed | May 3, 2026, 10:08 p.m. |
Created at: May 3, 2026, 4:12 p.m.