Triple

T16183546
Position Surface form Disambiguated ID Type / Status
Subject Fanaa E392742 entity
Predicate starring P1507 FINISHED
Object Shruti Seth
Shruti Seth is an Indian television and film actress known for her roles in popular Hindi TV shows and Bollywood movies.
E1209007 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: Shruti Seth | Statement: [Fanaa, starring, Shruti Seth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shruti Seth
Context triple: [Fanaa, starring, Shruti Seth]
  • A. Shefali Chowdhury
    Shefali Chowdhury is a British actress best known for playing Parvati Patil in the Harry Potter film series.
  • B. Anvita Abbi
    Anvita Abbi is an Indian linguist renowned for her pioneering work on the endangered languages of the Andaman Islands and other lesser-known South Asian languages.
  • C. Karthika Srinivas
    Karthika Srinivas is an Indian film editor known for his work in Telugu cinema, including editing the blockbuster film "Pushpa: The Rise."
  • D. Shivani Rawat
    Shivani Rawat is an Indian-American film producer and founder of ShivHans Pictures, known for backing acclaimed independent films such as Trumbo and Captain Fantastic.
  • E. Sangita Srivastava
    Sangita Srivastava is an Indian academic and administrator who has served as the vice-chancellor of the historic University of Allahabad.
  • 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: Shruti Seth
Triple: [Fanaa, starring, Shruti Seth]
Generated description
Shruti Seth is an Indian television and film actress known for her roles in popular Hindi TV shows and Bollywood movies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Shruti Seth
Target entity description: Shruti Seth is an Indian television and film actress known for her roles in popular Hindi TV shows and Bollywood movies.
  • A. Shefali Chowdhury
    Shefali Chowdhury is a British actress best known for playing Parvati Patil in the Harry Potter film series.
  • B. Anvita Abbi
    Anvita Abbi is an Indian linguist renowned for her pioneering work on the endangered languages of the Andaman Islands and other lesser-known South Asian languages.
  • C. Karthika Srinivas
    Karthika Srinivas is an Indian film editor known for his work in Telugu cinema, including editing the blockbuster film "Pushpa: The Rise."
  • D. Shivani Rawat
    Shivani Rawat is an Indian-American film producer and founder of ShivHans Pictures, known for backing acclaimed independent films such as Trumbo and Captain Fantastic.
  • E. Sangita Srivastava
    Sangita Srivastava is an Indian academic and administrator who has served as the vice-chancellor of the historic University of Allahabad.
  • 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_69d87f1e49ac8190a311b54d32990576 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e2205ef39081908da383abdebc2ccc completed April 17, 2026, 11:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a002d9c35248190a5540a692503c989 completed May 10, 2026, 7:02 a.m.
NEDg Description generation batch_6a002ec2fd948190878af958d0b90ce6 completed May 10, 2026, 7:07 a.m.
NED2 Entity disambiguation (via description) batch_6a00312a4fc48190b6bd6ad9db71bb4d completed May 10, 2026, 7:18 a.m.
Created at: April 10, 2026, 5:02 a.m.