Triple
T20085727
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Babruvahana |
E500122
|
entity |
| Predicate | causeOfArjunaDeath |
P138664
|
FINISHED |
| Object | defeated Arjuna during Ashwamedha campaign |
—
|
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: defeated Arjuna during Ashwamedha campaign | Statement: [Babruvahana, causeOfArjunaDeath, defeated Arjuna during Ashwamedha campaign]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: causeOfArjunaDeath Context triple: [Babruvahana, causeOfArjunaDeath, defeated Arjuna during Ashwamedha campaign]
-
A.
RaniDurgavatiDeath
Indicates the event or relationship of Rani Durgavati’s death, linking her as the person who died to the time, place, or circumstances of that death.
-
B.
deifiedPersonDeathCause
Indicates the cause or manner of death of the person who is venerated or treated as a deity.
-
C.
diesInArmsOf
Indicates that one entity dies while being physically held or embraced by another entity.
-
D.
causeOfHusbandDeath
Indicates that the subject is the cause or reason for the husband’s death.
-
E.
diedFor
Indicates that one entity’s death occurred as a sacrifice or in order to benefit, save, or serve another entity.
- F. None of above. chosen
Provenance (4 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_69da627770948190997f486f9a2e370f |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6655ae9ec8190bde2f17452639de8 |
completed | April 20, 2026, 5:41 p.m. |
| PD | Predicate disambiguation | batch_69e54cf369b88190931532420517dac7 |
completed | April 19, 2026, 9:45 p.m. |
| PDg | Predicate description generation | batch_69e54fc20888819083c9118a09d0d2dc |
completed | April 19, 2026, 9:57 p.m. |
Created at: April 11, 2026, 3:41 p.m.