Triple

T12391905
Position Surface form Disambiguated ID Type / Status
Subject Deadwood E296012 entity
Predicate leadActor P1507 FINISHED
Object William Sanderson E678346 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: William Sanderson | Statement: [Deadwood, leadActor, William Sanderson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Sanderson
Context triple: [Deadwood, leadActor, William Sanderson]
  • A. William Sanderson chosen
    William Sanderson is an American character actor known for his distinctive roles in films and television series such as Blade Runner, Newhart, and Deadwood.
  • B. John Ballantyne
    John Ballantyne is the amnesiac patient and central male protagonist in Alfred Hitchcock’s 1945 psychological thriller "Spellbound."
  • C. William Chalmers
    William Chalmers was a Swedish merchant and philanthropist whose endowment led to the creation of the Chalmers University of Technology in Gothenburg.
  • D. Thomas Rutherford
    Thomas Rutherford was an early settler and landowner in Napa Valley whose name was given to the community of Rutherford, California.
  • E. James Gillett
    James Gillett was an early 20th-century American politician who served as the 22nd governor of California from 1907 to 1911.
  • 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_69d6ad9e653c8190b1473c860ee53dae completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d93fd0bcc48190bb1a59a3aaa6bfdf completed April 10, 2026, 6:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6347c239881909a031e9e195080c9 completed May 2, 2026, 5:29 p.m.
Created at: April 8, 2026, 9:54 p.m.