Triple
T31676184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frederick, Archbishop of Mainz |
E808404
|
entity |
| Predicate | canonLaw |
P11460
|
FINISHED |
| Object | Latin Church canon law |
—
|
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: Latin Church canon law | Statement: [Frederick, Archbishop of Mainz, canonLaw, Latin Church canon law]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canonLaw Context triple: [Frederick, Archbishop of Mainz, canonLaw, Latin Church canon law]
-
A.
canonLawSubject
chosen
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.
canonLawContext
Indicates that something occurs within, is governed by, or is interpreted according to the norms and framework of canon law.
-
C.
canonLawTraining
Indicates that one entity has provided or received training or education in canon law in relation to another entity.
-
D.
canonLawContribution
Indicates a contribution an entity makes to the development, interpretation, or application of canon law.
-
E.
canonLawAction
Indicates an action, decision, or procedure carried out under or in accordance with canon law.
- 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_69f348dcf5d48190ac25b1365ae717a8 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6aaf50be08190a2b62a6d881f8aee |
completed | May 3, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69f6aa20a1588190a53533fc9764efb2 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 30, 2026, 11:03 p.m.