Triple

T17088902
Position Surface form Disambiguated ID Type / Status
Subject Heinz Behrens E414671 entity
Predicate employer P7 FINISHED
Object DEFA E355974 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: DEFA | Statement: [Heinz Behrens, employer, DEFA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: DEFA
Context triple: [Heinz Behrens, employer, DEFA]
  • A. DEFA chosen
    DEFA was the state-owned film studio of East Germany, known for producing feature films, documentaries, and animated works during the socialist era.
  • B. Neue Deutsche Filmgesellschaft
    Neue Deutsche Filmgesellschaft is a German film production and distribution company known for its role in the post-war German cinema industry.
  • C. Lenfilm
    Lenfilm is one of Russia’s oldest and most prominent film studios, based in Saint Petersburg and known for producing many classic Soviet-era movies.
  • D. DEFA 555
    DEFA 555 is a later 30 mm aircraft cannon variant developed from the French DEFA cannon family, featuring improved performance and reliability for modern fighter and attack aircraft.
  • E. Zeta Film
    Zeta Film is a film production company known for collaborating with other studios such as Central Films on various cinematic projects.
  • 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_69d886cfc8e88190b05ba466edd35591 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dbe9dc808190ab20537100e7ddee completed April 18, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a012ee81fd08190a7e1f5958fbe3b97 completed May 11, 2026, 1:20 a.m.
Created at: April 10, 2026, 5:35 a.m.