Triple

T22433244
Position Surface form Disambiguated ID Type / Status
Subject Lootera E554548 entity
Predicate editor P1954 FINISHED
Object Dipika Kalra
Dipika Kalra is an Indian film editor known for her work on acclaimed Hindi films, including the period romance drama "Lootera."
E1536428 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: Dipika Kalra | Statement: [Lootera, editor, Dipika Kalra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dipika Kalra
Context triple: [Lootera, editor, Dipika Kalra]
  • A. Sandhini Agarwal
    Sandhini Agarwal is an AI researcher known for her work at OpenAI on safety, policy, and the development and deployment of large-scale models such as CLIP.
  • B. Bhavna Limbachia
    Bhavna Limbachia is a British actress best known for her comedic and dramatic roles on UK television, including prominent parts in series such as Citizen Khan and Coronation Street.
  • C. Vaishali Kasaravalli
    Vaishali Kasaravalli was an Indian actress and costume designer known for her work in Kannada cinema and television.
  • D. Aditi Yadav
    Aditi Yadav is the daughter of Indian politician and former Uttar Pradesh Chief Minister Akhilesh Yadav.
  • E. Surekha Sikri
    Surekha Sikri was a renowned Indian theatre, film, and television actress celebrated for her powerful character roles and multiple National Film Awards.
  • 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: Dipika Kalra
Triple: [Lootera, editor, Dipika Kalra]
Generated description
Dipika Kalra is an Indian film editor known for her work on acclaimed Hindi films, including the period romance drama "Lootera."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Dipika Kalra
Target entity description: Dipika Kalra is an Indian film editor known for her work on acclaimed Hindi films, including the period romance drama "Lootera."
  • A. Sandhini Agarwal
    Sandhini Agarwal is an AI researcher known for her work at OpenAI on safety, policy, and the development and deployment of large-scale models such as CLIP.
  • B. Bhavna Limbachia
    Bhavna Limbachia is a British actress best known for her comedic and dramatic roles on UK television, including prominent parts in series such as Citizen Khan and Coronation Street.
  • C. Vaishali Kasaravalli
    Vaishali Kasaravalli was an Indian actress and costume designer known for her work in Kannada cinema and television.
  • D. Aditi Yadav
    Aditi Yadav is the daughter of Indian politician and former Uttar Pradesh Chief Minister Akhilesh Yadav.
  • E. Surekha Sikri
    Surekha Sikri was a renowned Indian theatre, film, and television actress celebrated for her powerful character roles and multiple National Film Awards.
  • 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_69e11e5010e48190ae1e9c9db9697637 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15a3320448190ae3931062599116e completed April 29, 2026, 1:09 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0af0f90f5881908f0011690cb0f1e4 completed May 18, 2026, 10:59 a.m.
NEDg Description generation batch_6a0af268db2881908706641ad1e41f79 completed May 18, 2026, 11:05 a.m.
NED2 Entity disambiguation (via description) batch_6a0b08e411048190a368214c57c35d5e completed May 18, 2026, 12:41 p.m.
Created at: April 16, 2026, 8:47 p.m.