Triple
T25920584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Serapion |
E653156
|
entity |
| Predicate | subjectReligiousOrder |
P20285
|
FINISHED |
| Object | Order of Mercy |
—
|
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: Order of Mercy | Statement: [Saint Serapion, subjectReligiousOrder, Order of Mercy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subjectReligiousOrder Context triple: [Saint Serapion, subjectReligiousOrder, Order of Mercy]
-
A.
religiousOrderOrRole
Indicates that an entity has a specific religious affiliation, order, or role within a religious tradition.
-
B.
religiousOrderBranchOf
Indicates that one religious order or congregation is an official subdivision, branch, or offshoot of another religious order.
-
C.
religiousOrderName
Indicates the specific name of the religious order with which an entity is affiliated or associated.
-
D.
religiousOrderAssociation
chosen
Indicates that an entity is formally connected to, affiliated with, or a member of a particular 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_69e7ab3e025c819086771607157f0015 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6562fd3488190be1acd8c526a28d2 |
completed | May 2, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69f651a731508190bb0c8c2462eba224 |
completed | May 2, 2026, 7:33 p.m. |
Created at: April 22, 2026, 8:32 a.m.