Triple

T22103044
Position Surface form Disambiguated ID Type / Status
Subject Special 26 E546216 entity
Predicate producer P490 FINISHED
Object Shital Bhatia
Shital Bhatia is an Indian film producer known for backing acclaimed Hindi movies, including the heist thriller "Special 26."
E1561323 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: Shital Bhatia | Statement: [Special 26, producer, Shital Bhatia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shital Bhatia
Context triple: [Special 26, producer, Shital Bhatia]
  • A. Deepa Bhatia
    Deepa Bhatia is an Indian film editor known for her acclaimed work on several Hindi films, including the critically celebrated drama "Taare Zameen Par."
  • B. Persis Khambatta
    Persis Khambatta was an Indian model and actress best known internationally for her role as Lieutenant Ilia in "Star Trek: The Motion Picture."
  • C. Tarika Bansal
    Tarika Bansal is the ambitious daughter of the protagonist in the Hindi film "Angrezi Medium," whose dream of studying abroad drives the emotional core of the story.
  • D. Bhavani Choudhry
    Bhavani Choudhry is a fictional character from the 1994 Hindi action drama film "Vijaypath."
  • E. Sharan Narang
    Sharan Narang is a machine learning researcher known for his work on large-scale natural language processing models, including contributions to the development of the T5 transformer architecture.
  • 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: Shital Bhatia
Triple: [Special 26, producer, Shital Bhatia]
Generated description
Shital Bhatia is an Indian film producer known for backing acclaimed Hindi movies, including the heist thriller "Special 26."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Shital Bhatia
Target entity description: Shital Bhatia is an Indian film producer known for backing acclaimed Hindi movies, including the heist thriller "Special 26."
  • A. Deepa Bhatia
    Deepa Bhatia is an Indian film editor known for her acclaimed work on several Hindi films, including the critically celebrated drama "Taare Zameen Par."
  • B. Persis Khambatta
    Persis Khambatta was an Indian model and actress best known internationally for her role as Lieutenant Ilia in "Star Trek: The Motion Picture."
  • C. Tarika Bansal
    Tarika Bansal is the ambitious daughter of the protagonist in the Hindi film "Angrezi Medium," whose dream of studying abroad drives the emotional core of the story.
  • D. Bhavani Choudhry
    Bhavani Choudhry is a fictional character from the 1994 Hindi action drama film "Vijaypath."
  • E. Sharan Narang
    Sharan Narang is a machine learning researcher known for his work on large-scale natural language processing models, including contributions to the development of the T5 transformer architecture.
  • 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_69e11e378dc08190896d6a51597afd5a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f129175a7881909549883f23c53dca completed April 28, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0bc22afa788190a93dc2beeeeedcc3 completed May 19, 2026, 1:51 a.m.
NEDg Description generation batch_6a0bc31b94f481909c437296742cfed8 completed May 19, 2026, 1:55 a.m.
NED2 Entity disambiguation (via description) batch_6a0bc38cf34c8190aaca05bbf32d28de completed May 19, 2026, 1:57 a.m.
Created at: April 16, 2026, 8:30 p.m.