Triple
T21944856
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Astitva |
E541908
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object |
Sunil Barve
Sunil Barve is an Indian actor and producer known for his work in Marathi theatre, television, and films.
|
E1522572
|
NE FINISHED |
How this triple was built (4 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: Sunil Barve | Statement: [Astitva, stars, Sunil Barve]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sunil Barve Context triple: [Astitva, stars, Sunil Barve]
-
A.
Sunil Sukthankar
Sunil Sukthankar is an acclaimed Indian filmmaker known for his influential work in contemporary Marathi cinema, often focusing on socially relevant and realistic themes.
-
B.
Vinod Bhanushali
Vinod Bhanushali is an Indian film producer and music industry executive known for his long association with T-Series and involvement in numerous Bollywood projects.
-
C.
Achyut Potdar
Achyut Potdar is an Indian character actor known for his numerous supporting roles in Hindi films and television.
-
D.
Ramesh Tawadkar
Ramesh Tawadkar is an Indian politician from Goa who serves as the Speaker of the Goa Legislative Assembly and is associated with the Bharatiya Janata Party (BJP).
-
E.
Mohan Agashe
Mohan Agashe is an Indian actor and psychiatrist known for his acclaimed performances in parallel cinema and mainstream Hindi and Marathi films.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Sunil Barve Triple: [Astitva, stars, Sunil Barve]
Generated description
Sunil Barve is an Indian actor and producer known for his work in Marathi theatre, television, and films.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sunil Barve Target entity description: Sunil Barve is an Indian actor and producer known for his work in Marathi theatre, television, and films.
-
A.
Sunil Sukthankar
Sunil Sukthankar is an acclaimed Indian filmmaker known for his influential work in contemporary Marathi cinema, often focusing on socially relevant and realistic themes.
-
B.
Vinod Bhanushali
Vinod Bhanushali is an Indian film producer and music industry executive known for his long association with T-Series and involvement in numerous Bollywood projects.
-
C.
Achyut Potdar
Achyut Potdar is an Indian character actor known for his numerous supporting roles in Hindi films and television.
-
D.
Ramesh Tawadkar
Ramesh Tawadkar is an Indian politician from Goa who serves as the Speaker of the Goa Legislative Assembly and is associated with the Bharatiya Janata Party (BJP).
-
E.
Mohan Agashe
Mohan Agashe is an Indian actor and psychiatrist known for his acclaimed performances in parallel cinema and mainstream Hindi and Marathi films.
- F. None of above. chosen
Provenance (5 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. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a9eaa53cc8190bfc006245a63f9e5 |
completed | May 18, 2026, 5:07 a.m. |
| NEDg | Description generation | batch_6a0aa0066d0481909872d8e1dbbe2fcf |
completed | May 18, 2026, 5:13 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0aa07acd5c8190bc73cc1d8897fa01 |
completed | May 18, 2026, 5:15 a.m. |
Created at: April 16, 2026, 7:56 p.m.