Triple
T21944994
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andhadhun |
E541911
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object |
Manav Vij
Manav Vij is an Indian film and television actor known for his supporting roles in Hindi cinema, including notable performances in critically acclaimed thrillers and dramas.
|
E1527207
|
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: Manav Vij | Statement: [Andhadhun, castMember, Manav Vij]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Manav Vij Context triple: [Andhadhun, castMember, Manav Vij]
-
A.
Bhavesh Mandalia
Bhavesh Mandalia is an Indian screenwriter and filmmaker known for his work on acclaimed Hindi films and socially relevant comedies.
-
B.
Varun Singh
Varun Singh is an individual known primarily as the father of Ram Singh.
-
C.
Sachit Mehra
Sachit Mehra is a Canadian political figure who serves in a top leadership role within the Liberal Party of Canada.
-
D.
Rajat Monga
Rajat Monga is a computer scientist and engineer best known as a co-creator and early lead of TensorFlow at Google Brain.
-
E.
Manava Naik
Manava Naik is an Indian actress known for her work in Hindi and Marathi films and television.
- 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: Manav Vij Triple: [Andhadhun, castMember, Manav Vij]
Generated description
Manav Vij is an Indian film and television actor known for his supporting roles in Hindi cinema, including notable performances in critically acclaimed thrillers and dramas.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Manav Vij Target entity description: Manav Vij is an Indian film and television actor known for his supporting roles in Hindi cinema, including notable performances in critically acclaimed thrillers and dramas.
-
A.
Bhavesh Mandalia
Bhavesh Mandalia is an Indian screenwriter and filmmaker known for his work on acclaimed Hindi films and socially relevant comedies.
-
B.
Varun Singh
Varun Singh is an individual known primarily as the father of Ram Singh.
-
C.
Sachit Mehra
Sachit Mehra is a Canadian political figure who serves in a top leadership role within the Liberal Party of Canada.
-
D.
Rajat Monga
Rajat Monga is a computer scientist and engineer best known as a co-creator and early lead of TensorFlow at Google Brain.
-
E.
Manava Naik
Manava Naik is an Indian actress known for her work in Hindi and Marathi films and television.
- 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_6a0ab640f7788190baa1305f47cd4ca2 |
completed | May 18, 2026, 6:48 a.m. |
| NEDg | Description generation | batch_6a0ab6fd3a6881908ea1e8f85eb9d969 |
completed | May 18, 2026, 6:51 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0ab791bd6c819098b3de570bd08815 |
completed | May 18, 2026, 6:54 a.m. |
Created at: April 16, 2026, 7:56 p.m.