Triple

T12295113
Position Surface form Disambiguated ID Type / Status
Subject Roshan Seth E293063 entity
Predicate givenName P17 FINISHED
Object Roshan
Roshan is the given name of Roshan Seth, an Indian-born British actor known for his roles in films such as "Gandhi" and "Indiana Jones and the Temple of Doom."
E975308 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: Roshan | Statement: [Roshan Seth, givenName, Roshan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roshan
Context triple: [Roshan Seth, givenName, Roshan]
  • A. Roshn
    Roshn is a Saudi Arabian real estate developer backed by the Public Investment Fund, known for building large-scale residential communities across the kingdom.
  • B. Rohana
    Rohana is a historical region in southern Sri Lanka that formed the core territory of the ancient Kingdom of Ruhuna.
  • C. Shalin
    Shalin is a Malaysian ten-pin bowler renowned for her numerous international titles and status as one of Asia’s most successful female bowlers.
  • D. Gulani
    Gulani is a local government area in northeastern Nigeria known for its rural communities within Yobe State.
  • E. Udayan
    Udayan is a central figure in Jhumpa Lahiri’s novel "The Lowland," whose radical political involvement and complex family relationships drive much of the story’s emotional and moral conflict.
  • 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: Roshan
Triple: [Roshan Seth, givenName, Roshan]
Generated description
Roshan is the given name of Roshan Seth, an Indian-born British actor known for his roles in films such as "Gandhi" and "Indiana Jones and the Temple of Doom."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Roshan
Target entity description: Roshan is the given name of Roshan Seth, an Indian-born British actor known for his roles in films such as "Gandhi" and "Indiana Jones and the Temple of Doom."
  • A. Roshn
    Roshn is a Saudi Arabian real estate developer backed by the Public Investment Fund, known for building large-scale residential communities across the kingdom.
  • B. Rohana
    Rohana is a historical region in southern Sri Lanka that formed the core territory of the ancient Kingdom of Ruhuna.
  • C. Shalin
    Shalin is a Malaysian ten-pin bowler renowned for her numerous international titles and status as one of Asia’s most successful female bowlers.
  • D. Gulani
    Gulani is a local government area in northeastern Nigeria known for its rural communities within Yobe State.
  • E. Udayan
    Udayan is a central figure in Jhumpa Lahiri’s novel "The Lowland," whose radical political involvement and complex family relationships drive much of the story’s emotional and moral conflict.
  • 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_69d6ab690ad081908c0ed3870ec82d53 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d93ed7251c8190b94d7cd75ad49b9c completed April 10, 2026, 6:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69f61e79bf548190bf7f314222ed1ed1 completed May 2, 2026, 3:55 p.m.
NEDg Description generation batch_69f62260d6708190808e52935a27e2c1 completed May 2, 2026, 4:12 p.m.
NED2 Entity disambiguation (via description) batch_69f6230f4c8081908a759efa43b4800b completed May 2, 2026, 4:15 p.m.
Created at: April 8, 2026, 9:52 p.m.