Triple

T19364258
Position Surface form Disambiguated ID Type / Status
Subject Paul Hausser E484359 entity
Predicate familyName P18 FINISHED
Object Hausser 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: Hausser | Statement: [Paul Hausser, familyName, Hausser]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hausser
Context triple: [Paul Hausser, familyName, Hausser]
  • A. Hausser chosen
    Hausser is a German surname most notably associated with Paul Hausser, a high-ranking military officer of the 20th century.
  • B. Hugo Schmeisser
    Hugo Schmeisser was a German firearms designer best known for pioneering modern assault rifle concepts and influencing small arms development in the 20th century.
  • C. 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.
  • D. Hermann Hoth
    Hermann Hoth was a German general in the Wehrmacht during World War II, known for commanding panzer armies on the Eastern Front and participating in major operations including the invasion of the Soviet Union.
  • E. Schörner
    Schörner is a German surname most notably borne by Ferdinand Schörner, a high-ranking Wehrmacht field marshal during World War II.
  • 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_69d8e8d305088190ad13571532aa454c completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e619a9ac68819082cf9deadf526156 completed April 20, 2026, 12:18 p.m.
Created at: April 10, 2026, 1:35 p.m.