Triple

T17704388
Position Surface form Disambiguated ID Type / Status
Subject In Custody E441391 entity
Predicate mainCharacter P1183 FINISHED
Object Deven Sharma
Deven Sharma is a fictional protagonist featured in the crime drama film "In Custody."
E1283800 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: Deven Sharma | Statement: [In Custody, mainCharacter, Deven Sharma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Deven Sharma
Context triple: [In Custody, mainCharacter, Deven Sharma]
  • A. Deven Bhojani
    Deven Bhojani is an Indian actor and director best known for his work in Hindi television comedies and character roles in films.
  • B. Shaan Hathiramani
    Shaan Hathiramani is an entrepreneur best known as a co-founder of the mobile video-sharing app Socialcam.
  • C. Manish Dayal
    Manish Dayal is an American actor best known for his leading role in the film "The Hundred-Foot Journey" and for his work in television series such as "The Resident."
  • D. Deepak Nayyar
    Deepak Nayyar is an Indian economist and academic known for his work on development economics and his leadership roles in major universities and international economic institutions.
  • E. Ashvin Desai
    Ashvin Desai is known primarily as the husband of acclaimed Indian novelist Anita Desai.
  • 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: Deven Sharma
Triple: [In Custody, mainCharacter, Deven Sharma]
Generated description
Deven Sharma is a fictional protagonist featured in the crime drama film "In Custody."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Deven Sharma
Target entity description: Deven Sharma is a fictional protagonist featured in the crime drama film "In Custody."
  • A. Deven Bhojani
    Deven Bhojani is an Indian actor and director best known for his work in Hindi television comedies and character roles in films.
  • B. Shaan Hathiramani
    Shaan Hathiramani is an entrepreneur best known as a co-founder of the mobile video-sharing app Socialcam.
  • C. Manish Dayal
    Manish Dayal is an American actor best known for his leading role in the film "The Hundred-Foot Journey" and for his work in television series such as "The Resident."
  • D. Deepak Nayyar
    Deepak Nayyar is an Indian economist and academic known for his work on development economics and his leadership roles in major universities and international economic institutions.
  • E. Ashvin Desai
    Ashvin Desai is known primarily as the husband of acclaimed Indian novelist Anita Desai.
  • 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_69d8b9ea20b48190ace88bb46b01e6a9 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e47296770c8190b6b172fb647da564 completed April 19, 2026, 6:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a023022e50881908a617d2f80e00956 completed May 11, 2026, 7:38 p.m.
NEDg Description generation batch_6a0231b6005c8190a1d7aa10a61fa7b9 completed May 11, 2026, 7:44 p.m.
NED2 Entity disambiguation (via description) batch_6a023228e064819095b1d73d0fd2c3c2 completed May 11, 2026, 7:46 p.m.
Created at: April 10, 2026, 10:05 a.m.