Triple
T28114522
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shiva as Pateeswarar |
E710583
|
entity |
| Predicate | hasConsortFormOf |
P46302
|
FINISHED |
| Object | Parvati |
—
|
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: Parvati | Statement: [Shiva as Pateeswarar, hasConsortFormOf, Parvati]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasConsortFormOf Context triple: [Shiva as Pateeswarar, hasConsortFormOf, Parvati]
-
A.
hasTypeOfConsort
Indicates that an entity has a consort characterized by a specific type or category of consort relationship.
-
B.
hasConsortDeityForm
chosen
Indicates that an entity has a consort specifically in their deity or divine form.
-
C.
possibleConsortOf
Indicates that one entity is a potential or likely romantic or marital partner of another, without asserting that the relationship is confirmed.
-
D.
hasConjunctForms
Indicates that an entity is associated with one or more conjunct (combined or compound) forms of itself or related elements.
-
E.
linkedToConsort
Indicates a relationship in which one entity is connected or associated to another as its consort (spouse or formal partner).
- 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_69ef9b72f63081909dfbc2c1ddae86c6 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69ff7dcedab08190a719a707d03306e2 |
completed | May 9, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69ff7d0119348190ad462554e81190fe |
completed | May 9, 2026, 6:29 p.m. |
Created at: April 27, 2026, 9:13 p.m.