Triple

T16584946
Position Surface form Disambiguated ID Type / Status
Subject István Szabó E402929 entity
Predicate notableWork P4 FINISHED
Object Hanussen E803974 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: Hanussen | Statement: [István Szabó, notableWork, Hanussen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hanussen
Context triple: [István Szabó, notableWork, Hanussen]
  • A. Hanussen chosen
    Hanussen is a 1988 Austrian-German biographical drama film about the clairvoyant performer Erik Jan Hanussen, starring Klaus Maria Brandauer.
  • B. Friedrich Jeckeln
    Friedrich Jeckeln was a high-ranking Nazi SS and police leader responsible for organizing and overseeing some of the largest mass shootings of Jews and civilians on the Eastern Front during World War II.
  • C. Julius Schreck
    Julius Schreck was an early member of the Nazi Party and the first commander of Adolf Hitler’s SS bodyguard unit, playing a key role in the formation of the Schutzstaffel.
  • D. Wolf Lieser
    Wolf Lieser is a German gallerist and curator best known for founding the Digital Art Museum (DAM) and promoting digital and computer-based art.
  • E. Günther
    Günther is a German masculine given name traditionally associated with figures of Germanic origin and culture.
  • 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_69d88387363c8190a97a0c942130de97 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3599b057881909fcb8bbb156633a8 completed April 18, 2026, 10:14 a.m.
NED1 Entity disambiguation (via context triple) batch_6a006ef2d6048190954144ab848760ec completed May 10, 2026, 11:41 a.m.
Created at: April 10, 2026, 5:16 a.m.