Triple
T22111553
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Buniyaad |
E546429
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Jyoti Sarup |
—
|
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: Jyoti Sarup | Statement: [Buniyaad, director, Jyoti Sarup]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jyoti Sarup Context triple: [Buniyaad, director, Jyoti Sarup]
-
A.
Jyoti Sarup
chosen
Jyoti Sarup is an Indian television and film director best known for his work on the landmark TV series "Buniyaad."
-
B.
Kusum Misra
Kusum Misra is known as the wife of Indian civil servant and former Principal Secretary to the Prime Minister, Nripendra Misra.
-
C.
Upasna Singh
Upasna Singh is an Indian television and film actress best known for her comic roles in Hindi cinema and popular TV shows like "Comedy Nights with Kapil."
-
D.
Manju Kumari Sinha
Manju Kumari Sinha was the wife of Nitish Kumar, a prominent Indian politician and long-serving Chief Minister of Bihar.
-
E.
Bhawani Das
Bhawani Das was an 18th-century Indian artist renowned for his detailed natural history paintings created for British patrons in colonial India.
- 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_69e11e38b3848190ac3a4fa97d56e65a |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12949cc7881908898ca7dc130f57f |
completed | April 28, 2026, 9:40 p.m. |
Created at: April 16, 2026, 8:31 p.m.