Triple

T8564973
Position Surface form Disambiguated ID Type / Status
Subject Jyothika E202780 entity
Predicate notableWork P4 FINISHED
Object Raatchasi
Raatchasi is a 2019 Tamil-language social drama film in which Jyothika plays a strict yet compassionate government school headmistress working to reform a failing rural institution.
 E742928 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: Raatchasi | Statement: [Jyothika, notableWork, Raatchasi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Raatchasi
Context triple: [Jyothika, notableWork, Raatchasi]
  • A. Rani
    Rani is an honorific title used in South Asia for a queen or a female royal consort.
  • B. Rajani
    Rajani is a Bengali novel by renowned 19th-century writer Bankim Chandra Chattopadhyay, noted for its exploration of social and emotional themes in colonial India.
  • C. Vasusena
    Vasusena is the original birth name of Karna, a central warrior figure in the Indian epic Mahabharata.
  • D. Arunachalam
    Arunachalam is a 1997 Tamil-language comedy-drama film starring Rajinikanth, known for its blend of humor, social themes, and mass entertainment.
  • E. Rajasbai
    Rajasbai was a queen consort of the Maratha Empire, known primarily as one of the wives of Chhatrapati Rajaram I.
  • 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: Raatchasi
Triple: [Jyothika, notableWork, Raatchasi]
Generated description
Raatchasi is a 2019 Tamil-language social drama film in which Jyothika plays a strict yet compassionate government school headmistress working to reform a failing rural institution.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Raatchasi
Target entity description: Raatchasi is a 2019 Tamil-language social drama film in which Jyothika plays a strict yet compassionate government school headmistress working to reform a failing rural institution.
  • A. Rani
    Rani is an honorific title used in South Asia for a queen or a female royal consort.
  • B. Rajani
    Rajani is a Bengali novel by renowned 19th-century writer Bankim Chandra Chattopadhyay, noted for its exploration of social and emotional themes in colonial India.
  • C. Vasusena
    Vasusena is the original birth name of Karna, a central warrior figure in the Indian epic Mahabharata.
  • D. Arunachalam
    Arunachalam is a 1997 Tamil-language comedy-drama film starring Rajinikanth, known for its blend of humor, social themes, and mass entertainment.
  • E. Rajasbai
    Rajasbai was a queen consort of the Maratha Empire, known primarily as one of the wives of Chhatrapati Rajaram I.
  • 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_69ca8327b0a881908606ff860713964d completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe9d2331881909d92ddde90f580e9 completed March 31, 2026, 3:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce89677888819091dfda14ce6baef3 completed April 2, 2026, 3:21 p.m.
NEDg Description generation batch_69ce8c10d774819086437ffeeb1ef25d completed April 2, 2026, 3:32 p.m.
NED2 Entity disambiguation (via description) batch_69ce8d0064fc819095058293e4229f25 completed April 2, 2026, 3:36 p.m.
Created at: March 30, 2026, 6:20 p.m.