Triple
T20938039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khandavaprastha |
E515637
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | Agni |
—
|
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: Agni | Statement: [Khandavaprastha, associatedWith, Agni]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Agni Context triple: [Khandavaprastha, associatedWith, Agni]
-
A.
Agni
chosen
Agni is the Vedic god of fire, revered as a central deity of sacrifice and a divine messenger between humans and the gods in ancient Indian religion.
-
B.
Anyin Agni
Anyin Agni is a dialect of the Anyin language spoken by Agni communities, primarily in parts of Côte d’Ivoire and neighboring regions.
-
C.
Indra-Agni
Indra-Agni is a dual Vedic deity combining the powers of Indra, the storm and war god, and Agni, the fire god, often invoked together in early Hindu rituals and hymns.
-
D.
Rudra
Rudra is a fierce and storm-associated Vedic deity later identified with the Hindu god Shiva, known for his destructive and healing powers.
-
E.
Vritra
Vritra is a powerful serpent or dragon-like demon in Hindu mythology, best known as the adversary slain by the god Indra to release the waters and restore cosmic order.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4fc13408190b06868df03c5c29b |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6f9534cd48190a86665fb1df6b077 |
completed | April 21, 2026, 4:13 a.m. |
Created at: April 16, 2026, 12:50 p.m.