Triple
T22260847
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tarakasura |
E550218
|
entity |
| Predicate | reasonForKartikeyaBirth |
P5256
|
FINISHED |
| Object | boon that only Shiva’s son could kill him |
—
|
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: boon that only Shiva’s son could kill him | Statement: [Tarakasura, reasonForKartikeyaBirth, boon that only Shiva’s son could kill him]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reasonForKartikeyaBirth Context triple: [Tarakasura, reasonForKartikeyaBirth, boon that only Shiva’s son could kill him]
-
A.
sonWithIndra
Indicates a parent–child relationship where the child is a son associated with or born to Indra.
-
B.
reasonForCreation
chosen
Indicates that one entity was created for the purpose, cause, or motivation specified by another entity.
-
C.
reactionToKaikeyisBoons
Indicates a character’s emotional or behavioral response to the granting of Kaikeyi’s boons.
-
D.
reasonForName
Indicates the explanation or cause behind why an entity has a particular name.
-
E.
sonWithSurya
Indicates a parent-child relationship where the entity is a son in relation to Surya.
- 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_69e11e42adb8819087714772ea606709 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f141b703b081909a2b432463a8e2df |
completed | April 28, 2026, 11:24 p.m. |
| PD | Predicate disambiguation | batch_69e72fe1e0cc8190bd13cff2a0846225 |
completed | April 21, 2026, 8:05 a.m. |
Created at: April 16, 2026, 8:39 p.m.