Triple

T10212991
Position Surface form Disambiguated ID Type / Status
Subject Taal E242375 entity
Predicate starring P1507 FINISHED
Object Sushma Seth
Sushma Seth is an Indian film, television, and theatre actress known for her character roles, especially as a mother or grandmother, in numerous Hindi movies and TV serials.
E854440 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: Sushma Seth | Statement: [Taal, starring, Sushma Seth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sushma Seth
Context triple: [Taal, starring, Sushma Seth]
  • A. Anu Khosla
    Anu Khosla is one of the children of Indian-American billionaire venture capitalist and Sun Microsystems co-founder Vinod Khosla.
  • B. Sushma Kharakwal
    Sushma Kharakwal is an Indian politician who has served as the mayor of Lucknow, the capital city of Uttar Pradesh.
  • C. Seema Kapoor
    Seema Kapoor is an Indian television and film actress and director, known for her work in Hindi entertainment and her marriage to the late actor Om Puri.
  • D. Nandita Puri
    Nandita Puri is an Indian journalist and author best known for her biography of her late husband, acclaimed actor Om Puri.
  • E. Neeru Khosla
    Neeru Khosla is an Indian-American education advocate and co-founder of the nonprofit digital learning platform CK-12 Foundation.
  • 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: Sushma Seth
Triple: [Taal, starring, Sushma Seth]
Generated description
Sushma Seth is an Indian film, television, and theatre actress known for her character roles, especially as a mother or grandmother, in numerous Hindi movies and TV serials.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sushma Seth
Target entity description: Sushma Seth is an Indian film, television, and theatre actress known for her character roles, especially as a mother or grandmother, in numerous Hindi movies and TV serials.
  • A. Anu Khosla
    Anu Khosla is one of the children of Indian-American billionaire venture capitalist and Sun Microsystems co-founder Vinod Khosla.
  • B. Sushma Kharakwal
    Sushma Kharakwal is an Indian politician who has served as the mayor of Lucknow, the capital city of Uttar Pradesh.
  • C. Seema Kapoor
    Seema Kapoor is an Indian television and film actress and director, known for her work in Hindi entertainment and her marriage to the late actor Om Puri.
  • D. Nandita Puri
    Nandita Puri is an Indian journalist and author best known for her biography of her late husband, acclaimed actor Om Puri.
  • E. Neeru Khosla
    Neeru Khosla is an Indian-American education advocate and co-founder of the nonprofit digital learning platform CK-12 Foundation.
  • 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_69d381ae26c48190985abd0e25ee5d04 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d3aa23bce881909b5deac612ec22cb completed April 6, 2026, 12:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69d71c77f65c8190862fde1c2fae045b completed April 9, 2026, 3:26 a.m.
NEDg Description generation batch_69d71f76e3cc8190b21a5fe8825caa2b completed April 9, 2026, 3:39 a.m.
NED2 Entity disambiguation (via description) batch_69d7319938ec8190a4a1a5f09832e3e3 completed April 9, 2026, 4:56 a.m.
Created at: April 6, 2026, 11:03 a.m.