Triple

T16133912
Position Surface form Disambiguated ID Type / Status
Subject Werner Herzog E391470 entity
Predicate directed P7373 FINISHED
Object My Best Fiend E1195440 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: My Best Fiend | Statement: [Werner Herzog, directed, My Best Fiend]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: My Best Fiend
Context triple: [Werner Herzog, directed, My Best Fiend]
  • A. My Best Fiend chosen
    My Best Fiend is a 1999 documentary film by Werner Herzog that explores his intense, tumultuous relationship and collaborations with actor Klaus Kinski.
  • B. Dearest Enemy
    Dearest Enemy is a 1925 Broadway musical comedy with music by Richard Rodgers and lyrics by Lorenz Hart, set during the American Revolutionary War.
  • C. Worst Enemy
    "Worst Enemy" is a track by American rapper Raekwon from his 2015 studio album *Fly International Luxurious Art*.
  • D. My Mortal Enemy
    "My Mortal Enemy" is a 1926 novel by Willa Cather that explores themes of love, sacrifice, and disillusionment through the story of a woman who abandons wealth and security for a romantic marriage that later unravels.
  • E. My Own Worst Enemy
    My Own Worst Enemy is an American television drama series created by Jason Smilovic that blends espionage, psychological thriller, and dual-identity themes.
  • 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_69d87f1bb0988190b490d273dbf3fd03 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21a039f0c8190a679e16a27f2dbe3 completed April 17, 2026, 11:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff7a304348190bf471f2b9279b806 completed May 10, 2026, 3:12 a.m.
Created at: April 10, 2026, 5:01 a.m.