Triple

T19030814
Position Surface form Disambiguated ID Type / Status
Subject Sam Robards E465730 entity
Predicate familyName P18 FINISHED
Object Robards NE NERFINISHED

How this triple was built (2 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: Robards | Statement: [Sam Robards, familyName, Robards]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robards
Context triple: [Sam Robards, familyName, Robards]
  • A. Robards chosen
    Robards is a surname most prominently associated with the American stage and film actor Jason Robards.
  • B. Reeser
    Reeser is a surname most notably associated with American actress Autumn Reeser, known for her roles in television and film.
  • C. Roone
    Roone is a masculine given name most notably associated with pioneering American television sports and news executive Roone Arledge.
  • D. Roker
    Roker is a coastal suburb of Sunderland in North East England, known for its sandy beach, seafront promenade, and historic lighthouse.
  • E. Red Rodney
    Red Rodney was an American jazz trumpeter best known for his work in the bebop era, particularly with Charlie Parker.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8dd0359648190bc2a9202c5cf29d2 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d7404d748190bcb51692fb822fd4 completed April 20, 2026, 7:35 a.m.
Created at: April 10, 2026, 12:02 p.m.