Triple
T22260839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tarakasura |
E550218
|
entity |
| Predicate | boonDescription |
P59011
|
FINISHED |
| Object | could be killed only by a son of Shiva |
—
|
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: could be killed only by a son of Shiva | Statement: [Tarakasura, boonDescription, could be killed only by a son of Shiva]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: boonDescription Context triple: [Tarakasura, boonDescription, could be killed only by a son of Shiva]
-
A.
boonDetails
chosen
Indicates the specific terms, conditions, or characteristics associated with a granted benefit or favor within the relationship or action.
-
B.
boastsOf
Indicates that one entity proudly talks about or shows off another entity as a source of pride or achievement.
-
C.
usedBoonsFrom
Indicates that one entity has utilized or expended beneficial effects, powers, or advantages that originated from another entity.
-
D.
boonCircumvention
Indicates that an advantage, benefit, or protective measure is being bypassed, undermined, or avoided rather than used as intended.
-
E.
obtainedBoonsFrom
Indicates that one entity has received or gained benefits, favors, or blessings from another entity.
- 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.