Triple
T19821513
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mahishasura |
E476205
|
entity |
| Predicate | parent |
P120
|
FINISHED |
| Object | Rambha |
—
|
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: Rambha | Statement: [Mahishasura, parent, Rambha]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rambha Context triple: [Mahishasura, parent, Rambha]
-
A.
Rambha
chosen
Rambha is a celebrated celestial nymph in Hindu mythology, renowned for her extraordinary beauty and role as a divine courtesan in the court of the gods.
-
B.
Randhava
Randhava is a Punjabi surname and clan name commonly found among Jat communities in northern India and Pakistan.
-
C.
Sharmishta
Sharmishta is the full given name of Shami Chakrabarti, a prominent British barrister and human rights advocate.
-
D.
Bhairavi
Bhairavi is a fierce and transformative Hindu goddess associated with destruction, time, and spiritual awakening, revered as one of the ten Mahavidyas in Shakta tradition.
-
E.
Madhavi
Madhavi is a celebrated courtesan and pivotal literary figure in ancient Tamil epic tradition, prominently featured in the Sangam-era works Silappatikaram and its sequel Manimekalai.
- 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_69d8e51c7c188190b926f3a2a7b5f881 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e654fee3e48190ae728e49748ad268 |
completed | April 20, 2026, 4:31 p.m. |
Created at: April 10, 2026, 1:50 p.m.