Triple

T21944239
Position Surface form Disambiguated ID Type / Status
Subject Talvar E541894 entity
Predicate starredActor P5563 FINISHED
Object Sohum Shah
Sohum Shah is an Indian actor and film producer known for his performances in critically acclaimed Hindi films such as Ship of Theseus, Tumbbad, and Talvar.
E1509404 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: Sohum Shah | Statement: [Talvar, starredActor, Sohum Shah]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sohum Shah
Context triple: [Talvar, starredActor, Sohum Shah]
  • A. Ishaan Khatter
    Ishaan Khatter is an Indian film actor known for his work in Hindi cinema, including acclaimed performances in films like "Beyond the Clouds" and "Dhadak."
  • B. Zain Kapoor
    Zain Kapoor is the son of Indian Bollywood actor Shahid Kapoor and his wife Mira Rajput Kapoor.
  • C. Tusshar Kapoor
    Tusshar Kapoor is an Indian film actor and producer known for his work in Bollywood comedies such as the "Golmaal" series.
  • D. Prateik Babbar
    Prateik Babbar is an Indian film actor known for his roles in Hindi cinema, including his debut in "Jaane Tu... Ya Jaane Na."
  • E. Akash Khurana
    Akash Khurana is an Indian actor, screenwriter, and director known for his work in Hindi cinema 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: Sohum Shah
Triple: [Talvar, starredActor, Sohum Shah]
Generated description
Sohum Shah is an Indian actor and film producer known for his performances in critically acclaimed Hindi films such as Ship of Theseus, Tumbbad, and Talvar.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sohum Shah
Target entity description: Sohum Shah is an Indian actor and film producer known for his performances in critically acclaimed Hindi films such as Ship of Theseus, Tumbbad, and Talvar.
  • A. Ishaan Khatter
    Ishaan Khatter is an Indian film actor known for his work in Hindi cinema, including acclaimed performances in films like "Beyond the Clouds" and "Dhadak."
  • B. Zain Kapoor
    Zain Kapoor is the son of Indian Bollywood actor Shahid Kapoor and his wife Mira Rajput Kapoor.
  • C. Tusshar Kapoor
    Tusshar Kapoor is an Indian film actor and producer known for his work in Bollywood comedies such as the "Golmaal" series.
  • D. Prateik Babbar
    Prateik Babbar is an Indian film actor known for his roles in Hindi cinema, including his debut in "Jaane Tu... Ya Jaane Na."
  • E. Akash Khurana
    Akash Khurana is an Indian actor, screenwriter, and director known for his work in Hindi cinema 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_6a0a60f1f49c81909f6c17dad3bd0219 completed May 18, 2026, 12:44 a.m.
NEDg Description generation batch_6a0a6200fb1c81909a4ab05fd368dafc completed May 18, 2026, 12:49 a.m.
NED2 Entity disambiguation (via description) batch_6a0a626731d8819097b209ae1375ae25 completed May 18, 2026, 12:50 a.m.
Created at: April 16, 2026, 7:56 p.m.