Triple
T10205326
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Germain of Paris |
E242176
|
entity |
| Predicate | typeOfCanonization |
P92709
|
FINISHED |
| Object | local cult recognized by tradition |
—
|
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: local cult recognized by tradition | Statement: [Germain of Paris, typeOfCanonization, local cult recognized by tradition]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfCanonization Context triple: [Germain of Paris, typeOfCanonization, local cult recognized by tradition]
-
A.
hasCanonization
Indicates that an entity has undergone or been granted formal canonization, typically recognizing it as officially sainted or sanctified.
-
B.
typeOfCanonry
Indicates that one canonry is classified as a specific kind or category of canonry in relation to another.
-
C.
hasPartInCanonization
Indicates that an entity participated in or contributed to the process of canonization of another entity.
-
D.
isCanonicalFormOf
Indicates that one entity is the standard or officially accepted form or representation of another, often more variant, entity.
-
E.
canonizedAs
Indicates that an authority, typically a religious institution, has formally declared someone to be a saint or holy figure.
- 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_69d381ae26c48190985abd0e25ee5d04 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d3aa22071c819095febd18dd607978 |
completed | April 6, 2026, 12:42 p.m. |
| PD | Predicate disambiguation | batch_69d39559e5ac8190b88eca75956b7e6a |
completed | April 6, 2026, 11:13 a.m. |
| PDg | Predicate description generation | batch_69d3aa208c248190a0fb186b106389f3 |
completed | April 6, 2026, 12:42 p.m. |
Created at: April 6, 2026, 10:44 a.m.