Triple

T13550388
Position Surface form Disambiguated ID Type / Status
Subject Rose Ross E323628 entity
Predicate associatedWithCharacter P1481 FINISHED
Object Silas Selleck E323627 NE FINISHED

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: Silas Selleck | Statement: [Rose Ross, associatedWithCharacter, Silas Selleck]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Silas Selleck
Context triple: [Rose Ross, associatedWithCharacter, Silas Selleck]
  • A. Silas Selleck chosen
    Silas Selleck is the taciturn, morally ambiguous frontiersman who serves as the central protagonist in the 2015 Western film "Slow West."
  • B. John Reilly
    John Reilly is a musician known for being a member of the Irish-American Celtic rock band O'Malley's March.
  • C. Nolan Richardson
    Nolan Richardson is an American college basketball coach best known for leading the University of Arkansas to the 1994 NCAA championship with his up-tempo "40 Minutes of Hell" style.
  • D. Dustin Weaver
    Dustin Weaver is an American comic book artist known for his detailed, dynamic work on major Marvel titles and creator-owned projects.
  • E. James Woods
    James Woods is an American actor known for his intense performances in film and television, including acclaimed roles in movies such as "Salvador," "Videodrome," and "Casino."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d8076776248190bdf0d4fa1f85a5fc completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbaff0a6548190b8cde5084cef0061 completed April 12, 2026, 2:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f76bb0195c8190b62e7aad4d78f899 completed May 3, 2026, 3:37 p.m.
Created at: April 9, 2026, 9:46 p.m.