Triple
T21944839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Astitva |
E541908
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Mahesh Manjrekar |
—
|
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: Mahesh Manjrekar | Statement: [Astitva, producer, Mahesh Manjrekar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mahesh Manjrekar Context triple: [Astitva, producer, Mahesh Manjrekar]
-
A.
Mahesh Manjrekar
chosen
Mahesh Manjrekar is an Indian filmmaker and actor known for his influential work in Marathi and Hindi cinema, including directing acclaimed films like "Vaastav."
-
B.
Kamal Shirwadkar
Kamal Shirwadkar was the wife of renowned Marathi poet and writer Vishnu Vaman Shirwadkar, popularly known as Kusumagraj.
-
C.
Dilip Mehta
Dilip Mehta is an Indian-born photojournalist and filmmaker known for his documentary and feature film work, often intersecting with the socially conscious cinema of his sister, director Deepa Mehta.
-
D.
Roopesh Parekh
Roopesh Parekh is a television and film producer known for his work on the adaptation of Agatha Christie's "Ordeal by Innocence."
-
E.
Vikramaditya Motwane
Vikramaditya Motwane is an Indian filmmaker and screenwriter known for directing acclaimed films like "Udaan," "Lootera," and the Netflix series "Sacred Games."
- 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1242688988190a7b8f033c49368de |
completed | April 28, 2026, 9:18 p.m. |
Created at: April 16, 2026, 7:56 p.m.