Triple

T10738622
Position Surface form Disambiguated ID Type / Status
Subject Männerpension E253260 entity
Predicate hasCastMember P2308 FINISHED
Object Götz Otto E882379 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: Götz Otto | Statement: [Männerpension, hasCastMember, Götz Otto]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Götz Otto
Context triple: [Männerpension, hasCastMember, Götz Otto]
  • A. Götz Otto chosen
    Götz Otto is a German actor best known internationally for playing the henchman Stamper in the James Bond film "Tomorrow Never Dies."
  • B. Oskar Werner
    Oskar Werner was an acclaimed Austrian actor known for his intense, introspective performances in European and Hollywood films of the mid-20th century.
  • C. Oskar Hergt
    Oskar Hergt was a conservative German politician of the Weimar Republic who served as a leading figure and early chairman of the German National People’s Party (DNVP).
  • D. Heinz Conrads
    Heinz Conrads was an Austrian actor, radio and television presenter, and entertainer, best known for his popular postwar Viennese radio and TV shows.
  • E. Hans Goerke
    Hans Goerke was the original owner and namesake of the historic Goerke 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_69d6aa5e51e8819095f06881cecf152e completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d710424d8c81908ee9b59d622f2af5 completed April 9, 2026, 2:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69deb0a03a1481908edb933b1613a027 completed April 14, 2026, 9:24 p.m.
Created at: April 8, 2026, 9:14 p.m.