Triple

T1720507
Position Surface form Disambiguated ID Type / Status
Subject Mitchell Leisen E37378 entity
Predicate name P16 FINISHED
Object Mitchell Leisen E37378 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: Mitchell Leisen | Statement: [Mitchell Leisen, name, Mitchell Leisen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mitchell Leisen
Context triple: [Mitchell Leisen, name, Mitchell Leisen]
  • A. Mitchell Leisen chosen
    Mitchell Leisen was an American film director, art director, and costume designer known for his stylish Hollywood productions from the 1930s and 1940s.
  • B. Andrew Miano
    Andrew Miano is an American film producer known for his work on independent and critically acclaimed movies, often collaborating with director Tom Ford and others.
  • C. Kevin Yagher
    Kevin Yagher is an American special effects and makeup artist and director best known for his work on horror and fantasy films and for creating iconic genre characters.
  • D. Evan Schiff
    Evan Schiff is a film editor known for his work on high-profile action movies, including entries in the John Wick franchise.
  • E. Doug Mitchell
    Doug Mitchell is an Australian film producer best known for his longtime collaboration with director George Miller on projects including the Mad Max franchise.
  • 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_69a8861912dc8190931af43b4b9158a7 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa63558d7c8190830cb8ee2e4a8932 completed March 6, 2026, 5:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69adf3b9a2f4819082ca2e9f838f7b9e completed March 8, 2026, 10:10 p.m.
Created at: March 4, 2026, 7:30 p.m.