Triple
T3176606
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Epiphanius of Pavia |
E66478
|
entity |
| Predicate | typeOfSanctity |
P18301
|
FINISHED |
| Object | confessor |
—
|
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: confessor | Statement: [Saint Epiphanius of Pavia, typeOfSanctity, confessor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfSanctity Context triple: [Saint Epiphanius of Pavia, typeOfSanctity, confessor]
-
A.
typeOfSaint
chosen
Indicates that one entity is classified as a specific kind or category of saint in relation to another entity.
-
B.
sacredStatus
Indicates that something holds a revered, holy, or religiously significant status within a particular belief system or tradition.
-
C.
typeOfDeity
Indicates that one entity is classified as a specific kind or category of deity in relation to another.
-
D.
venerationType
Indicates the specific manner or category of reverence or worship directed toward an entity.
-
E.
sacredTo
Indicates that one entity is regarded as holy, revered, or dedicated in honor of another entity, such as a deity, person, or concept.
- 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_69ad8586a34c8190944c63ec11a8de1a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada69b0bec8190957913b44d876079 |
completed | March 8, 2026, 4:40 p.m. |
| PD | Predicate disambiguation | batch_69ad9e02677c8190a21d93b1259b2761 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:06 p.m.