Triple
T4936538
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kalki |
E110824
|
entity |
| Predicate | positionInDashavatara |
P27705
|
FINISHED |
| Object | tenth avatar of Vishnu |
—
|
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: tenth avatar of Vishnu | Statement: [Kalki, positionInDashavatara, tenth avatar of Vishnu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInDashavatara Context triple: [Kalki, positionInDashavatara, tenth avatar of Vishnu]
-
A.
hasPositionInMahabharata
Indicates that one entity holds or is assigned a specific role, rank, or position within the context of the Mahabharata narrative.
-
B.
positionInCosmogony
Indicates the role or place an entity occupies within a culture’s creation or origin narrative of the universe.
-
C.
positionInPantheon
chosen
Indicates the rank, role, or hierarchical standing that a deity or figure holds within a specific pantheon or religious hierarchy.
-
D.
positionInTemple
Indicates the specific location or role an entity occupies within a temple.
-
E.
lastTirthankara
Indicates that the subject is the final or most recent Tirthankara in a recognized sequence of Tirthankaras.
- 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_69bd4415eee08190bdce70276e56a5b4 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd7085b1dc819099408f6503f0210f |
completed | March 20, 2026, 4:06 p.m. |
| PD | Predicate disambiguation | batch_69bd6c389b9881908ad7fb1c5393c1b1 |
completed | March 20, 2026, 3:48 p.m. |
Created at: March 20, 2026, 1:30 p.m.