Triple
T32489422
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DeSales University |
E830338
|
entity |
| Predicate | religiousOrderSponsor |
P20285
|
FINISHED |
| Object | Oblates of St. Francis de Sales |
—
|
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: Oblates of St. Francis de Sales | Statement: [DeSales University, religiousOrderSponsor, Oblates of St. Francis de Sales]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: religiousOrderSponsor Context triple: [DeSales University, religiousOrderSponsor, Oblates of St. Francis de Sales]
-
A.
religiousOrderAssociation
chosen
Indicates that an entity is formally connected to, affiliated with, or a member of a particular religious order.
-
B.
religiousOrderSupported
Indicates that one entity provides support—such as resources, endorsement, or maintenance—to a particular religious order.
-
C.
religiousOrderName
Indicates the specific name of the religious order with which an entity is affiliated or associated.
-
D.
religiousOrderBranchOf
Indicates that one religious order or congregation is an official subdivision, branch, or offshoot of another religious order.
-
E.
religiousOrderCode
Indicates the specific religious order or denomination with which an entity is affiliated, represented by a standardized code.
- 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_69f34920aa4081908d8fb0277414b911 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fef8c3f2388190b995ec173512945a |
completed | May 9, 2026, 9:05 a.m. |
| PD | Predicate disambiguation | batch_69fef65975608190960b78d27e806d4f |
completed | May 9, 2026, 8:54 a.m. |
Created at: May 1, 2026, 12:59 a.m.