Triple

T20467383
Position Surface form Disambiguated ID Type / Status
Subject Wilm Hosenfeld E502087 entity
Predicate familyName P18 FINISHED
Object Hosenfeld 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: Hosenfeld | Statement: [Wilm Hosenfeld, familyName, Hosenfeld]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hosenfeld
Context triple: [Wilm Hosenfeld, familyName, Hosenfeld]
  • A. Hosenfeld chosen
    Hosenfeld is a German surname most notably associated with Wilm Hosenfeld, a Wehrmacht officer known for helping to save Jews during World War II.
  • B. Fahrenkopf
    Fahrenkopf is a surname most prominently associated with Frank J. Fahrenkopf Jr., an American lawyer, lobbyist, and former chairman of the Republican National Committee.
  • C. Hauerz
    Hauerz is a village and district of the spa town Bad Wurzach in the Ravensburg district of Baden-Württemberg, Germany.
  • D. Marloffstein
    Marloffstein is a small municipality in the Erlangen-Höchstadt district of Bavaria, Germany, known for its rural character and proximity to the city of Erlangen.
  • E. Grosbard
    Grosbard is a surname most notably associated with Ulu Grosbard, a Belgian-born American film and theater director.
  • 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_69e0b4ae5f1081908768b0c9a3a0bf38 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6995d9d1c81909ee223a35a0850ba completed April 20, 2026, 9:23 p.m.
Created at: April 16, 2026, 11:33 a.m.