Triple
T14997436
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Dismas |
E373993
|
entity |
| Predicate | scripturalPassage |
P3661
|
FINISHED |
| Object | Luke 23:39–43 |
—
|
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: Luke 23:39–43 | Statement: [Saint Dismas, scripturalPassage, Luke 23:39–43]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scripturalPassage Context triple: [Saint Dismas, scripturalPassage, Luke 23:39–43]
-
A.
scriptureFor
Indicates that one entity serves as a scriptural or authoritative religious text for another entity (such as a person, group, or belief system).
-
B.
scripturalReference
chosen
Indicates that one entity cites, alludes to, or is based on a specific passage or portion of a scriptural text found in another entity.
-
C.
scriptureFocus
Indicates that something centers on, emphasizes, or is primarily concerned with religious scripture or sacred texts.
-
D.
scriptureRead
Indicates that an entity reads, studies, or engages with a religious or sacred text.
-
E.
scripturalSection
Indicates a relationship where one text or passage is a specific section or subdivision within a larger scriptural work.
- 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_69d85ccc84388190aa151e5173370c8d |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded718e4288190b5e144f82299a194 |
completed | April 15, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69de9a6169b48190a679609febd2d0e3 |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:54 a.m.