Triple
T158297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paschal candle |
E3225
|
entity |
| Predicate | firstLitAt |
P5495
|
FINISHED |
| Object | Easter Vigil fire |
—
|
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: Easter Vigil fire | Statement: [Paschal candle, firstLitAt, Easter Vigil fire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstLitAt Context triple: [Paschal candle, firstLitAt, Easter Vigil fire]
-
A.
firstLetter
Indicates that one entity is the initial character or starting letter of another entity (typically a string or word).
-
B.
firstArticulatedIn
Indicates the time or context in which something was originally expressed, formulated, or clearly stated for the first time.
-
C.
firstOccupied
Indicates that an entity was the initial or earliest occupant of a particular place, position, or resource.
-
D.
firstAppeared
Indicates the earliest known time or context in which an entity was introduced, observed, or came into existence.
-
E.
firstNode
Indicates that the subject is the initial or starting node in an ordered sequence, structure, or path.
- 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_69a2527757ec819090b8becb2cf1a862 |
completed | Feb. 28, 2026, 2:27 a.m. |
| NER | Named-entity recognition | batch_69a2583169a0819081b658882e5bc452 |
completed | Feb. 28, 2026, 2:51 a.m. |
| PD | Predicate disambiguation | batch_69a2565f30848190a2a71fdb7dc140b5 |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a257101060819094db0f3a3a72f312 |
completed | Feb. 28, 2026, 2:46 a.m. |
Created at: Feb. 28, 2026, 2:31 a.m.