Triple

T22366700
Position Surface form Disambiguated ID Type / Status
Subject Elser – Er hätte die Welt verändert E552922 entity
Predicate editedBy P1954 FINISHED
Object Alexander Dittner NE NERFINISHED

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: Alexander Dittner | Statement: [Elser – Er hätte die Welt verändert, editedBy, Alexander Dittner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alexander Dittner
Context triple: [Elser – Er hätte die Welt verändert, editedBy, Alexander Dittner]
  • A. Alexander Dittner chosen
    Alexander Dittner is a film editor best known for his work on the 2013 animated film "Tarzan."
  • B. Daniel P. Livermore
    Daniel P. Livermore was the husband of prominent American abolitionist and women's rights advocate Mary Livermore.
  • C. Eric L. Zinterhofer
    Eric L. Zinterhofer is an American private equity investor and media executive known for his leadership roles in the telecommunications and cable industry.
  • D. Michael Wimer
    Michael Wimer is a film and television producer best known for his work on genre projects such as the science fiction series "Outsiders."
  • E. Daniel W. Herzog
    Daniel W. Herzog is an American Anglican bishop best known for serving as the Bishop of the Episcopal Diocese of Albany in New York.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e4affcc8190ba7c27d29062558d completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1580074dc819091305ac7017000d3 completed April 29, 2026, 12:59 a.m.
Created at: April 16, 2026, 8:44 p.m.