Triple
T2410545
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Michael |
E50376
|
entity |
| Predicate | inIslamicTradition |
P23614
|
FINISHED |
| Object | angel of mercy |
—
|
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: angel of mercy | Statement: [Saint Michael, inIslamicTradition, angel of mercy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inIslamicTradition Context triple: [Saint Michael, inIslamicTradition, angel of mercy]
-
A.
positionInIslam
Indicates the specific religious role, rank, or status an entity holds within the context of Islam.
-
B.
statusInIslamicTradition
Indicates the recognized standing, role, or level of esteem an entity holds within Islamic religious, cultural, or scholarly tradition.
-
C.
ethnicReligion
Indicates that a religion is closely associated with a particular ethnic group, often tied to that group’s culture, ancestry, or identity.
-
D.
partOfReligiousTradition
chosen
Indicates that one entity belongs to, is included within, or is practiced as a component of a particular religious tradition.
-
E.
isAbrahamicTradition
Indicates that a religious tradition belongs to the family of faiths historically derived from the beliefs and practices of Abraham.
- 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_69a88b0339a88190a1207333cd271cc9 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abceab9ce881909ae0a2f34515c11e |
completed | March 7, 2026, 7:07 a.m. |
| PD | Predicate disambiguation | batch_69abc5a530e8819094105aa92dfaf6b3 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:58 p.m.