Triple
T34864217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | relics of Mary Magdalene |
E1004966
|
entity |
| Predicate | linkedToTitleOfMaryMagdalene |
P43509
|
FINISHED |
| Object | disciple of Jesus |
—
|
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: disciple of Jesus | Statement: [relics of Mary Magdalene, linkedToTitleOfMaryMagdalene, disciple of Jesus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linkedToTitleOfMaryMagdalene Context triple: [relics of Mary Magdalene, linkedToTitleOfMaryMagdalene, disciple of Jesus]
-
A.
reportedTitleOfMary
Indicates that the specified title is one that has been reported or recorded as belonging to Mary.
-
B.
linkedToSaint
chosen
Indicates that one entity has a direct association or connection with a saint.
-
C.
messianicFigureAssociated
Indicates a relationship in which a person, symbol, or concept is linked or connected to a messianic figure, role, or expectation.
-
D.
linkedToGospel
Indicates a relationship where something is connected or related to the gospel, typically in content, origin, or thematic focus.
-
E.
venerationOfMary
Indicates a relationship in which an entity shows reverence, honor, or devotional respect toward Mary.
- 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_69f76dbb678081909a247b9b5e1a73ac |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fe6fea4a288190bf8615c5d6bf41b4 |
completed | May 8, 2026, 11:21 p.m. |
| PD | Predicate disambiguation | batch_69fe6f774de08190975a2393b9a1fd22 |
completed | May 8, 2026, 11:19 p.m. |
Created at: May 3, 2026, 4 p.m.