Triple
T4906631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Devas |
E109926
|
entity |
| Predicate | inRamayana |
P59363
|
FINISHED |
| Object | support Rama |
—
|
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: support Rama | Statement: [Devas, inRamayana, support Rama]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inRamayana Context triple: [Devas, inRamayana, support Rama]
-
A.
hasPositionInMahabharata
Indicates that one entity holds or is assigned a specific role, rank, or position within the context of the Mahabharata narrative.
-
B.
isDivyaDesam
Indicates that a location is one of the 108 sacred Vishnu temples (Divya Desams) revered in the Tamil Vaishnavite tradition.
-
C.
isPancharangaKshetram
Indicates that a temple or sacred site is recognized as one of the Pancharanga Kshetrams, the five traditional holy shrines dedicated to Lord Ranganatha (Vishnu) along the Kaveri river.
-
D.
VajranabhaIs
Indicates that something or someone is identified as or characterized by being Vajranabha.
-
E.
दोषसिद्धि
Indicates a judicial relationship where an authority formally establishes and declares a person’s guilt for an alleged offense.
- F. None of above. chosen
Provenance (4 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_69bd441180708190ba42ffb44fea533a |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6e72ed5c819081104c99a398e0af |
completed | March 20, 2026, 3:57 p.m. |
| PD | Predicate disambiguation | batch_69bd6c325e188190823836d79934e9bc |
completed | March 20, 2026, 3:48 p.m. |
| PDg | Predicate description generation | batch_69bd6cc228088190849f23b7bd4cf549 |
completed | March 20, 2026, 3:50 p.m. |
Created at: March 20, 2026, 1:29 p.m.