Triple

T9824882
Position Surface form Disambiguated ID Type / Status
Subject Wilm Hosenfeld E238629 entity
Predicate portrayedBy P1507 FINISHED
Object Thomas Kretschmann E21474 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: Thomas Kretschmann | Statement: [Wilm Hosenfeld, portrayedBy, Thomas Kretschmann]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas Kretschmann
Context triple: [Wilm Hosenfeld, portrayedBy, Thomas Kretschmann]
  • A. Thomas Kretschmann chosen
    Thomas Kretschmann is a German actor known for his frequent roles in war and historical films, including notable performances in "The Pianist," "Downfall," and "King Kong."
  • B. Daniel Günther
    Daniel Günther is a German politician from the Christian Democratic Union (CDU) who serves as the Minister-President of the northern federal state of Schleswig-Holstein.
  • C. Michael Müller
    Michael Müller is a German politician from the Social Democratic Party (SPD) who served as the Governing Mayor of Berlin in the 2010s.
  • D. Peter Kohl
    Peter Kohl is a German businessman and author best known as the son of former German Chancellor Helmut Kohl.
  • E. Christian Scholz
    Christian Scholz is a German computer scientist and open-source developer known for his contributions to web technologies and social software.
  • 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_69ca84e0dd1881909800765d1e21f735 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb3181c688190afea3b27ee392a30 completed April 2, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1cc810bac8190a5ff94c0717e7706 completed April 5, 2026, 2:44 a.m.
Created at: March 30, 2026, 8:31 p.m.