Triple

T19127935
Position Surface form Disambiguated ID Type / Status
Subject Heathers E468235 entity
Predicate director P255 FINISHED
Object Michael Lehmann 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: Michael Lehmann | Statement: [Heathers, director, Michael Lehmann]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Lehmann
Context triple: [Heathers, director, Michael Lehmann]
  • A. Michael Lehmann chosen
    Michael Lehmann is an American film and television director best known for the dark comedy "Heathers" and various other Hollywood comedies.
  • B. Michael Hecht
    Michael Hecht is the birth name of Michael Howard, a British Conservative politician who served as Leader of the Opposition and Home Secretary.
  • C. Michael Hecht
    Michael Hecht is a scientist best known for leading NASA’s MOXIE experiment on the Perseverance rover, which demonstrates in-situ oxygen production on Mars.
  • D. Michael Hertzberg
    Michael Hertzberg is an American film producer best known for his work on several Mel Brooks comedies, including "Blazing Saddles" and "Silent Movie."
  • E. Michael Ehrlich
    Michael Ehrlich is a relatively obscure individual whose primary public mention appears to be as a namesake associated with the surname Ehrlich.
  • 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_69d8dd0796a48190b34ce4cd9d3f3be5 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e3ceb5808190b3b53d9e8df3605a completed April 20, 2026, 8:29 a.m.
Created at: April 10, 2026, 12:05 p.m.