Triple

T11769624
Position Surface form Disambiguated ID Type / Status
Subject Michael Rennie E279862 entity
Predicate portrayed P1668 FINISHED
Object Harry Lime E754469 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: Harry Lime | Statement: [Michael Rennie, portrayed, Harry Lime]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry Lime
Context triple: [Michael Rennie, portrayed, Harry Lime]
  • A. Harry Lime chosen
    Harry Lime is the charismatic yet morally ambiguous racketeer portrayed by Orson Welles in the classic film noir "The Third Man."
  • B. Martin Max
    Martin Max is a former German professional footballer and prolific striker best known for his goal-scoring exploits in the Bundesliga.
  • C. Felix Krull
    Felix Krull is the charming, quick-witted con artist and social climber who narrates Thomas Mann’s picaresque novel "The Confessions of Felix Krull."
  • D. Rosa Klebb
    Rosa Klebb is a fictional Soviet counterintelligence officer and SPECTRE operative who serves as the main antagonist in the James Bond novel and film "From Russia with Love," notorious for her ruthlessness and poison-tipped shoe blade.
  • E. Frank Gruber
    Frank Gruber was an American writer best known for his prolific work in pulp fiction, mystery and Western novels, and Hollywood screenplays.
  • 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_69d6ab01d2688190ad8ed6bda487eaa5 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a55c9f988190b203b66a28c767ae completed April 10, 2026, 7:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69f09075aba8819082434a43473025bd completed April 28, 2026, 10:48 a.m.
Created at: April 8, 2026, 9:41 p.m.