Triple

T14219032
Position Surface form Disambiguated ID Type / Status
Subject Karlheinz Böhm E352436 entity
Predicate notableWork P4 FINISHED
Object Sissi E964654 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: Sissi | Statement: [Karlheinz Böhm, notableWork, Sissi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sissi
Context triple: [Karlheinz Böhm, notableWork, Sissi]
  • A. Sissi
    Sissi is a Brazilian former footballer renowned as one of the standout forwards of women’s soccer in the 1990s.
  • B. Sissi
    Sissi is the affectionate nickname of Empress Elisabeth of Austria, a 19th-century Habsburg empress famed for her beauty, independent spirit, and tragic life.
  • C. Sissi (1955 film) chosen
    Sissi (1955 film) is a popular Austrian historical romance movie that dramatizes the early life and love story of Empress Elisabeth of Austria.
  • D. Kaiservilla
    Kaiservilla is a former imperial summer residence in Bad Ischl, Austria, best known as the retreat of Emperor Franz Joseph I and Empress Elisabeth of Austria.
  • E. Duchess in Bavaria
    Duchess in Bavaria was a noble title borne by members of the Wittelsbach family, a cadet branch of the Bavarian royal house.
  • 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_69d8278a06e481908b5d6af0a8afe737 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de621258d4819085f358cd2cf109e4 completed April 14, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd28121a288190975d5852f9a503d4 completed May 8, 2026, 12:02 a.m.
Created at: April 10, 2026, 1:06 a.m.