Triple
T36079397
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rivkele |
E1043596
|
entity |
| Predicate | typeOfDeityRelation |
P60881
|
FINISHED |
| Object | servant of the God of Vengeance |
—
|
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: servant of the God of Vengeance | Statement: [Rivkele, typeOfDeityRelation, servant of the God of Vengeance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfDeityRelation Context triple: [Rivkele, typeOfDeityRelation, servant of the God of Vengeance]
-
A.
typeOfDeity
Indicates that one entity is classified as a specific kind or category of deity in relation to another.
-
B.
relationshipToDeities
chosen
Indicates how an entity is connected or related to one or more deities, such as through worship, lineage, role, or status.
-
C.
sharesDeityTypesWith
Indicates that two entities are associated with at least one of the same types or categories of deities.
-
D.
roleOfReferencedDeity
Indicates that one entity specifies the function, status, or position held by a deity that is referenced in relation to another entity or context.
-
E.
deityIdentification
Indicates that one entity is identified, recognized, or designated as a deity in relation to another entity or context.
- 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_69f76e3154908190a6f702671c2bea08 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a022c5269888190944314074aedfe73 |
completed | May 11, 2026, 7:21 p.m. |
| PD | Predicate disambiguation | batch_6a02286020308190b238183f7ba2065f |
completed | May 11, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:08 p.m.