Triple
T2456869
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Service of Light |
E54441
|
entity |
| Predicate | congregationalAction |
P21643
|
FINISHED |
| Object | holding lighted candles |
—
|
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: holding lighted candles | Statement: [Service of Light, congregationalAction, holding lighted candles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: congregationalAction Context triple: [Service of Light, congregationalAction, holding lighted candles]
-
A.
religiousActivity
chosen
Indicates participation in, performance of, or association with practices, rituals, or behaviors related to a religion or faith tradition.
-
B.
hasCongregation
Indicates that an entity is associated with or serves as the gathering place or organized group of worshippers for a religious community.
-
C.
religiousEvent
Indicates that an event is related to religious practices, observances, or ceremonies.
-
D.
convenesIn
Indicates that an entity brings together or assembles a group, meeting, or event at a specific place or venue.
-
E.
convenesAs
Indicates that an entity brings together or assembles a group, body, or session in a particular role or capacity.
- 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_69ab49dee84c819096b50a0049c347ac |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd49c5aa081909ab4f726a458b77f |
completed | March 7, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69abd0b199488190aa381b36593ae1ac |
completed | March 7, 2026, 7:16 a.m. |
Created at: March 6, 2026, 9:44 p.m.