Triple

T10917505
Position Surface form Disambiguated ID Type / Status
Subject Riff-Raff E257862 entity
Predicate starring P1507 FINISHED
Object George Moss
George Moss is an actor known for his role in the film "Riff-Raff."
 E894440 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: George Moss | Statement: [Riff-Raff, starring, George Moss]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: George Moss
Context triple: [Riff-Raff, starring, George Moss]
  • A. Adam Moss
    Adam Moss is an American magazine editor best known for transforming New York Magazine into an influential, award-winning publication during his long tenure as editor-in-chief.
  • B. Kallum Watkins
    Kallum Watkins is an English professional rugby league footballer best known for his successful career as a centre for Leeds Rhinos and the England national team.
  • C. Dominic Lewis
    Dominic Lewis is a British-born film and television composer known for scoring a variety of Hollywood projects across action, animation, and comedy.
  • D. Nathan Kingsbury
    Nathan Kingsbury was an American telecommunications executive for AT&T in the early 20th century, known for his role in shaping U.S. telephone regulation and policy.
  • E. Lee Adams
    Lee Adams is an American lyricist best known for his long-running Broadway songwriting partnership with composer Charles Strouse, creating shows such as Bye Bye Birdie and Applause.
  • 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: George Moss
Triple: [Riff-Raff, starring, George Moss]
Generated description
George Moss is an actor known for his role in the film "Riff-Raff."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: George Moss
Target entity description: George Moss is an actor known for his role in the film "Riff-Raff."
  • A. Adam Moss
    Adam Moss is an American magazine editor best known for transforming New York Magazine into an influential, award-winning publication during his long tenure as editor-in-chief.
  • B. Kallum Watkins
    Kallum Watkins is an English professional rugby league footballer best known for his successful career as a centre for Leeds Rhinos and the England national team.
  • C. Dominic Lewis
    Dominic Lewis is a British-born film and television composer known for scoring a variety of Hollywood projects across action, animation, and comedy.
  • D. Nathan Kingsbury
    Nathan Kingsbury was an American telecommunications executive for AT&T in the early 20th century, known for his role in shaping U.S. telephone regulation and policy.
  • E. Lee Adams
    Lee Adams is an American lyricist best known for his long-running Broadway songwriting partnership with composer Charles Strouse, creating shows such as Bye Bye Birdie and Applause.
  • 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_69d6aa864ed88190818280ab6791d065 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7707ebdcc8190b42cafe21c667c82 completed April 9, 2026, 9:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69e2170bb97c81908e8d209ddb630601 completed April 17, 2026, 11:18 a.m.
NEDg Description generation batch_69e21d8952c881908a952de83754e049 completed April 17, 2026, 11:46 a.m.
NED2 Entity disambiguation (via description) batch_69e2247fbd348190bb0d221923dac892 completed April 17, 2026, 12:16 p.m.
Created at: April 8, 2026, 9:22 p.m.