Triple
T36243994
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Second Zurich Disputation |
E891602
|
entity |
| Predicate | hasConfessionalAlignment |
P43087
|
FINISHED |
| Object | Reformed |
—
|
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: Reformed | Statement: [Second Zurich Disputation, hasConfessionalAlignment, Reformed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasConfessionalAlignment Context triple: [Second Zurich Disputation, hasConfessionalAlignment, Reformed]
-
A.
confessionalAlignment
chosen
Indicates the degree to which an entity’s beliefs, practices, or identity conform to or align with a particular religious confession or doctrinal standard.
-
B.
hasConfessional
Indicates that an entity possesses, contains, or is associated with a confessional space or facility.
-
C.
hasConfessionalDocument
Indicates that an entity possesses, is associated with, or is documented by a formal confessional document (such as a statement of faith, creed, or confession).
-
D.
usesConfessions
Indicates that one entity employs or relies on another entity’s confessions as a basis for some action, decision, or outcome.
-
E.
hasConfessionals
Indicates that an entity includes or is associated with one or more confessional segments or statements.
- 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_69f76e44993481908fa75e4c48d0aab3 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0a54cc8190868c1bfa1590d1a6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:09 p.m.