Triple
T2410542
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Michael |
E50376
|
entity |
| Predicate | positionInHeavenlyHierarchy |
P27705
|
FINISHED |
| Object | leader of the army of God |
—
|
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: leader of the army of God | Statement: [Saint Michael, positionInHeavenlyHierarchy, leader of the army of God]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInHeavenlyHierarchy Context triple: [Saint Michael, positionInHeavenlyHierarchy, leader of the army of God]
-
A.
positionInPantheon
chosen
Indicates the rank, role, or hierarchical standing that a deity or figure holds within a specific pantheon or religious hierarchy.
-
B.
positionInCosmogony
Indicates the role or place an entity occupies within a culture’s creation or origin narrative of the universe.
-
C.
ecclesiasticalRank
Indicates the hierarchical religious office or clerical status that one entity holds within a church or ecclesiastical organization.
-
D.
positionInMass
Indicates that an entity occupies a specific location or role within a larger undifferentiated group, collection, or mass.
-
E.
positionInHierarchy
Indicates that one entity occupies a specific rank or level relative to another within an ordered hierarchy.
- 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.