Triple
T19429289
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Keshi |
E486066
|
entity |
| Predicate | category |
P87
|
FINISHED |
| Object | Asuras |
—
|
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: Asuras | Statement: [Keshi, category, Asuras]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Asuras Context triple: [Keshi, category, Asuras]
-
A.
Asura
chosen
Asura is a class of powerful, often antagonistic supernatural beings in Indian religions, particularly Hinduism and Buddhism, frequently depicted as rivals of the gods (Devas).
-
B.
Rakshasas
Rakshasas are powerful, shape-shifting demon beings from Hindu mythology, often portrayed as malevolent antagonists in epics like the Ramayana.
-
C.
Daityas
Daityas are a race of powerful and often antagonistic beings in Hindu mythology, typically portrayed as formidable opponents of the gods.
-
D.
Devas
The Devas are celestial gods in Hindu mythology who play pivotal roles in the cosmic order and divine interventions depicted throughout the Ramayana.
-
E.
Yazatas
Yazatas are divine beings or angels in Zoroastrian and Iranian mythology who personify natural and moral forces and are worthy of worship.
- 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_69d8e8d688f881909c85104a62e09d8a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6321b78d08190b86cef7c60cbb61c |
completed | April 20, 2026, 2:03 p.m. |
Created at: April 10, 2026, 1:37 p.m.