Triple

T19162834
Position Surface form Disambiguated ID Type / Status
Subject Oskar von Hindenburg E469100 entity
Predicate familyName P18 FINISHED
Object von Hindenburg — 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: von Hindenburg | Statement: [Oskar von Hindenburg, familyName, von Hindenburg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: von Hindenburg
Context triple: [Oskar von Hindenburg, familyName, von Hindenburg]
  • A. von Hindenburg chosen
    Von Hindenburg is a German noble family name most famously associated with Paul von Hindenburg, the World War I field marshal and later President of Germany.
  • B. von Zeppelin
    Von Zeppelin is a German noble family name most famously associated with Ferdinand von Zeppelin, the aviation pioneer who developed rigid airships known as Zeppelins.
  • C. Zimmermann
    Zimmermann was a zoologist who formally described the Indian muntjac, a small deer species native to South and Southeast Asia.
  • D. Zimmermann
    Zimmermann is a German surname commonly associated with the occupation of a carpenter or builder.
  • E. LZ 127 Graf Zeppelin
    LZ 127 Graf Zeppelin was a pioneering German rigid airship that became famous for its long-distance passenger flights and record-setting global journeys in the late 1920s and early 1930s.
  • 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_69d8dd084ff48190ac0f8c46ee722629 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5eebe03ac8190bbe0b34ebf0d90c6 completed April 20, 2026, 9:15 a.m.
Created at: April 10, 2026, 12:06 p.m.