Triple
T2185378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marriage Office |
E49140
|
entity |
| Predicate | appliesDoctrine |
P4473
|
FINISHED |
| Object | Catholic doctrine on marriage |
—
|
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: Catholic doctrine on marriage | Statement: [Marriage Office, appliesDoctrine, Catholic doctrine on marriage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliesDoctrine Context triple: [Marriage Office, appliesDoctrine, Catholic doctrine on marriage]
-
A.
appliedDoctrine
Indicates that a particular doctrine, principle, or rule has been put into practice or used in interpreting or deciding a specific case, situation, or context.
-
B.
usesDoctrine
chosen
Indicates that one entity applies, follows, or relies on a particular doctrine in its actions or reasoning.
-
C.
containsDoctrine
Indicates that one entity includes, embodies, or incorporates the doctrine, principles, or teachings represented by another entity.
-
D.
createdDoctrine
Indicates that an entity originated, formulated, or established a particular doctrine, theory, or set of principles.
-
E.
developedDoctrine
Indicates that one entity created, formulated, or significantly advanced a particular doctrine or set of principles.
- 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_69a88aa72d348190a9544bb5b8a4e71d |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abbf9e99f08190892d34485c8f2f25 |
completed | March 7, 2026, 6:03 a.m. |
| PD | Predicate disambiguation | batch_69abbda32d1881909d1fd83a751fb21c |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:45 p.m.