Triple

T6860196
Position Surface form Disambiguated ID Type / Status
Subject "Doctor Zhivago" (1965 film) E158256 entity
Predicate editor P1954 FINISHED
Object Norman Savage E158256 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: Norman Savage | Statement: ["Doctor Zhivago" (1965 film), editor, Norman Savage]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Norman Savage
Context triple: ["Doctor Zhivago" (1965 film), editor, Norman Savage]
  • A. Norman Savage chosen
    Norman Savage is an editor known for his work on the classic novel "Doctor Zhivago."
  • B. Orlando Murden
    Orlando Murden was an American songwriter best known for co-writing the classic soul ballad "For Once in My Life."
  • C. Eugene Sawyer
    Eugene Sawyer was an American politician who briefly served as mayor of Chicago in the late 1980s following the death of Harold Washington.
  • D. Roland Culver
    Roland Culver was a British actor known for his polished, often aristocratic screen presence in mid-20th-century film, television, and theatre.
  • E. Lyman Ward
    Lyman Ward is a Canadian-American actor best known for playing Ferris Bueller’s father in the 1986 film "Ferris Bueller’s Day Off."
  • 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_69c68830cdbc8190a8301c7a9d9f651a completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d8737fac81909fc546ca2bf6a278 completed March 27, 2026, 7:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69c72fe79af081909baacbfd4d5e8f24 completed March 28, 2026, 1:33 a.m.
Created at: March 27, 2026, 2:21 p.m.