Triple

T10340952
Position Surface form Disambiguated ID Type / Status
Subject Fritz Haber E243125 entity
Predicate spouse P13 FINISHED
Object Clara Immerwahr E638104 NE FINISHED

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: Clara Immerwahr | Statement: [Fritz Haber, spouse, Clara Immerwahr]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Clara Immerwahr
Context triple: [Fritz Haber, spouse, Clara Immerwahr]
  • A. Clara Immerwahr chosen
    Clara Immerwahr was a German chemist and early female PhD holder who became known for her outspoken ethical opposition to chemical warfare during World War I.
  • B. Lucie Mannheim
    Lucie Mannheim was a German-born actress known for her work in early 20th-century cinema and theatre, particularly in British films after fleeing Nazi Germany.
  • C. Rosa Fröhlich
    Rosa Fröhlich is a central fictional character in Heinrich Mann’s novel "Professor Unrat," known as the cabaret singer whose relationship with the strict schoolteacher leads to his social and moral downfall.
  • D. Felicitas Radke
    Felicitas Radke was the wife of renowned German actor Conrad Veidt, known for her marriage to this prominent figure of early 20th-century cinema.
  • E. Rose Stradner
    Rose Stradner was an Austrian-American actress known for her work in Hollywood films of the 1930s and 1940s.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d381af787481908bc401325c760a88 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e0a645348190af91450360a9abed completed April 7, 2026, 10:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69d75070c3ac8190b0d50a93d48c9bd9 completed April 9, 2026, 7:08 a.m.
Created at: April 6, 2026, 11:55 a.m.