Triple

T18320754
Position Surface form Disambiguated ID Type / Status
Subject Karl Wolff E438871 entity
Predicate name P16 FINISHED
Object Karl Wolff 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: Karl Wolff | Statement: [Karl Wolff, name, Karl Wolff]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karl Wolff
Context triple: [Karl Wolff, name, Karl Wolff]
  • A. Karl Wolff chosen
    Karl Wolff was a high-ranking Nazi official who served as Heinrich Himmler’s chief of staff and later played a key role in negotiating the German surrender in Italy during World War II.
  • B. Lutz Bornmann
    Lutz Bornmann is a German scientometrics and bibliometrics researcher known for his influential work on research evaluation, citation analysis, and science indicators.
  • C. Viktor Lutze
    Viktor Lutze was a high-ranking Nazi official who led the Sturmabteilung (SA) after Ernst Röhm’s purge and helped consolidate Adolf Hitler’s control over the paramilitary organization.
  • D. Erich Dietl
    Erich Dietl was a German Wehrmacht general during World War II, noted for his leadership of mountain troops on the Eastern Front and in Norway.
  • E. Oscar Werwath
    Oscar Werwath was a German-born American engineer and educator best known as the founder and first leader of the Milwaukee School of Engineering.
  • 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_69d8b916a2d081909e249e4902f6aad9 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e50aa5a3508190a3025e71c11d79e2 completed April 19, 2026, 5:02 p.m.
Created at: April 10, 2026, 10:36 a.m.