Triple

T22075522
Position Surface form Disambiguated ID Type / Status
Subject Mahal (1949 film) E545511 entity
Predicate starring P1507 FINISHED
Object Kanu Roy
Kanu Roy was an Indian actor and music director known for his work in Hindi cinema, particularly in mid-20th-century films.
 E1516819 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: Kanu Roy | Statement: [Mahal (1949 film), starring, Kanu Roy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kanu Roy
Context triple: [Mahal (1949 film), starring, Kanu Roy]
  • A. Kanu Banerjee
    Kanu Banerjee was an Indian actor best known for playing Apu’s father, Harihar Ray, in Satyajit Ray’s acclaimed Apu Trilogy.
  • B. Parag Das
    Parag Das is a former Indian cricketer best known for representing Assam as a top-order batsman in domestic cricket.
  • C. Mukul Dey
    Mukul Dey was an Indian artist and pioneering printmaker associated with the Bengal School of Art, known especially for popularizing drypoint etching in India.
  • D. Liton Das
    Liton Das is a Bangladeshi international cricketer known primarily as a top-order wicketkeeper-batsman in limited-overs formats.
  • E. Niranjan Roy
    Niranjan Roy is an Indian actor known for his role in the classic Bengali film "Meghe Dhaka Tara" directed by Ritwik Ghatak.
  • 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: Kanu Roy
Triple: [Mahal (1949 film), starring, Kanu Roy]
Generated description
Kanu Roy was an Indian actor and music director known for his work in Hindi cinema, particularly in mid-20th-century films.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kanu Roy
Target entity description: Kanu Roy was an Indian actor and music director known for his work in Hindi cinema, particularly in mid-20th-century films.
  • A. Kanu Banerjee
    Kanu Banerjee was an Indian actor best known for playing Apu’s father, Harihar Ray, in Satyajit Ray’s acclaimed Apu Trilogy.
  • B. Parag Das
    Parag Das is a former Indian cricketer best known for representing Assam as a top-order batsman in domestic cricket.
  • C. Mukul Dey
    Mukul Dey was an Indian artist and pioneering printmaker associated with the Bengal School of Art, known especially for popularizing drypoint etching in India.
  • D. Liton Das
    Liton Das is a Bangladeshi international cricketer known primarily as a top-order wicketkeeper-batsman in limited-overs formats.
  • E. Niranjan Roy
    Niranjan Roy is an Indian actor known for his role in the classic Bengali film "Meghe Dhaka Tara" directed by Ritwik Ghatak.
  • 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_69e11e344dfc81909b1d88a7221329c7 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128b1904881909a1769ce8be39e05 completed April 28, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a80b7a98c8190909b31034aa04039 completed May 18, 2026, 3 a.m.
NEDg Description generation batch_6a0a81f51dbc8190a49506d7536d165b completed May 18, 2026, 3:05 a.m.
NED2 Entity disambiguation (via description) batch_6a0a82c10ce48190806498221cb55e7b completed May 18, 2026, 3:08 a.m.
Created at: April 16, 2026, 8:28 p.m.