Triple
T10567576
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Louis |
E249388
|
entity |
| Predicate | canonLawContribution |
P94695
|
FINISHED |
| Object | support for ecclesiastical courts |
—
|
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: support for ecclesiastical courts | Statement: [Saint Louis, canonLawContribution, support for ecclesiastical courts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canonLawContribution Context triple: [Saint Louis, canonLawContribution, support for ecclesiastical courts]
-
A.
canonLawSubject
Indicates that an entity is the subject or topic governed, regulated, or addressed by a particular canon law or set of canonical legal norms.
-
B.
canonLawTraining
Indicates that one entity has provided or received training or education in canon law in relation to another entity.
-
C.
canonLawAction
Indicates an action, decision, or procedure carried out under or in accordance with canon law.
-
D.
canonLawContext
Indicates that something occurs within, is governed by, or is interpreted according to the norms and framework of canon law.
-
E.
religiousCanon
Indicates that something is formally recognized as part of an established body of authoritative religious texts or doctrine.
- 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_69d381c8bd708190acf3d275c908251e |
completed | April 6, 2026, 9:50 a.m. |
| NER | Named-entity recognition | batch_69d5272ef5848190b76d671ea2d26314 |
completed | April 7, 2026, 3:47 p.m. |
| PD | Predicate disambiguation | batch_69d51901ff6c819095e7b528170a69dc |
completed | April 7, 2026, 2:47 p.m. |
| PDg | Predicate description generation | batch_69d5270eca0481908573b698390c5b08 |
completed | April 7, 2026, 3:47 p.m. |
Created at: April 6, 2026, 12:36 p.m.