Triple

T18289743
Position Surface form Disambiguated ID Type / Status
Subject The Man Who Came Back (1924 film) E438079 entity
Predicate stars P1956 FINISHED
Object Tom Santschi 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: Tom Santschi | Statement: [The Man Who Came Back (1924 film), stars, Tom Santschi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Santschi
Context triple: [The Man Who Came Back (1924 film), stars, Tom Santschi]
  • A. Tom Santschi chosen
    Tom Santschi was an American silent film actor best known for his rugged roles in early Westerns and adventure serials.
  • B. Tom Schaul
    Tom Schaul is a machine learning researcher known for his contributions to deep reinforcement learning, including co-developing the Dueling DQN architecture.
  • C. John Zulberti
    John Zulberti is a former standout lacrosse player best known for his collegiate career with the Syracuse University men's lacrosse program.
  • D. Michael Tuchner
    Michael Tuchner was a British film and television director known for his work on crime dramas and character-driven stories in the 1960s and 1970s.
  • E. Frank Teschemacher
    Frank Teschemacher was an influential early Chicago jazz clarinetist and saxophonist known for his role in shaping the Chicago style of the 1920s and early 1930s.
  • 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_69d8b914530c8190b4474d862a2b2a1b completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e500fd65888190afdbb29dc60066af completed April 19, 2026, 4:21 p.m.
Created at: April 10, 2026, 10:35 a.m.