Triple
T36732327
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matthew–Luke–Mark |
E907373
|
entity |
| Predicate | proposesFirstGospel |
P186540
|
FINISHED |
| Object | Gospel of Matthew |
—
|
NE NERFINISHED |
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: Gospel of Matthew | Statement: [Matthew–Luke–Mark, proposesFirstGospel, Gospel of Matthew]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: proposesFirstGospel Context triple: [Matthew–Luke–Mark, proposesFirstGospel, Gospel of Matthew]
-
A.
positionAmongGospels
Indicates the numerical order or placement of a given gospel within the sequence of all gospels.
-
B.
chronologicalOrderOfGospels
Indicates the temporal sequence in which the Gospels are believed or asserted to have been written or occurred relative to one another.
-
C.
uniqueToGospel
Indicates that a particular element (such as a story, saying, or detail) appears only in one specific Gospel and not in any of the others.
-
D.
apostolicOrigin
Indicates that something originates from, is derived from, or is directly linked in authority or tradition to the apostles.
-
E.
nameInCanonicalGospels
Indicates that a person or entity is explicitly named in at least one of the four canonical Christian gospels (Matthew, Mark, Luke, or John).
- 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_69f76e75aa6881909b844d00a3888ee5 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fe1a1ca4819084c196f0041f0be2 |
completed | May 5, 2026, 2:26 p.m. |
| PD | Predicate disambiguation | batch_69f7cf7890008190a8bc355ff2d61c86 |
completed | May 3, 2026, 10:43 p.m. |
| PDg | Predicate description generation | batch_69f9fd66eed48190bdc26a8def328c2d |
completed | May 5, 2026, 2:23 p.m. |
Created at: May 3, 2026, 4:12 p.m.