Triple
T21110632
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sadashiv Amrapurkar |
E520161
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Sadashiv Amrapurkar |
—
|
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: Sadashiv Amrapurkar | Statement: [Sadashiv Amrapurkar, name, Sadashiv Amrapurkar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sadashiv Amrapurkar Context triple: [Sadashiv Amrapurkar, name, Sadashiv Amrapurkar]
-
A.
Sadashiv Amrapurkar
chosen
Sadashiv Amrapurkar was an acclaimed Indian actor best known for his powerful character and villainous roles in Hindi and Marathi cinema.
-
B.
Vaman Bendre
Vaman Bendre is the son of renowned Kannada poet and Jnanpith awardee Da. Ra. Bendre.
-
C.
Bhalchandra Vaman Apte
Bhalchandra Vaman Apte was a renowned Indian Sanskrit scholar and lexicographer, best known for his widely used Sanskrit-English dictionaries and educational works.
-
D.
D. R. Bendre
D. R. Bendre was a renowned Indian Kannada poet and one of the most influential figures in modern Kannada literature.
-
E.
Bhanumati Annasaheb Rajopadhye
Bhanumati Annasaheb Rajopadhye, better known as Bhanu Athaiya, was an acclaimed Indian costume designer and the first Indian to win an Academy Award.
- 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_69e0b509a318819092fbbcb21d1fe603 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e72101f7308190beb202a052ff04d2 |
completed | April 21, 2026, 7:02 a.m. |
Created at: April 16, 2026, 2:54 p.m.