Triple

T13965660
Position Surface form Disambiguated ID Type / Status
Subject Roman Bohnen E335914 entity
Predicate spouse P13 FINISHED
Object Herta Schwarz
Herta Schwarz was the wife of American actor Roman Bohnen, known primarily in relation to his personal life.
E1090029 NE FINISHED

How this triple was built (4 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: Herta Schwarz | Statement: [Roman Bohnen, spouse, Herta Schwarz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Herta Schwarz
Context triple: [Roman Bohnen, spouse, Herta Schwarz]
  • A. Herta Haas
    Herta Haas was a Slovenian communist and partisan who became known as the second wife of Yugoslav leader Josip Broz Tito.
  • B. Gertrud Heinrici
    Gertrud Heinrici was the wife of German Wehrmacht Colonel General Gotthard Heinrici and a member of the German aristocracy during the first half of the 20th century.
  • C. Margarete Gebhardt
    Margarete Gebhardt was the wife of Austrian zoologist and Nobel Prize–winning ethologist Konrad Lorenz.
  • D. Hilde Schwab
    Hilde Schwab is a Swiss philanthropist and co-founder of the Schwab Foundation for Social Entrepreneurship, known for her work promoting social innovation and supporting the World Economic Forum’s initiatives.
  • E. Herta Ehlert
    Herta Ehlert was a German SS overseer at Nazi concentration camps who was later prosecuted for war crimes after World War II.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Herta Schwarz
Triple: [Roman Bohnen, spouse, Herta Schwarz]
Generated description
Herta Schwarz was the wife of American actor Roman Bohnen, known primarily in relation to his personal life.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Herta Schwarz
Target entity description: Herta Schwarz was the wife of American actor Roman Bohnen, known primarily in relation to his personal life.
  • A. Herta Haas
    Herta Haas was a Slovenian communist and partisan who became known as the second wife of Yugoslav leader Josip Broz Tito.
  • B. Gertrud Heinrici
    Gertrud Heinrici was the wife of German Wehrmacht Colonel General Gotthard Heinrici and a member of the German aristocracy during the first half of the 20th century.
  • C. Margarete Gebhardt
    Margarete Gebhardt was the wife of Austrian zoologist and Nobel Prize–winning ethologist Konrad Lorenz.
  • D. Hilde Schwab
    Hilde Schwab is a Swiss philanthropist and co-founder of the Schwab Foundation for Social Entrepreneurship, known for her work promoting social innovation and supporting the World Economic Forum’s initiatives.
  • E. Herta Ehlert
    Herta Ehlert was a German SS overseer at Nazi concentration camps who was later prosecuted for war crimes after World War II.
  • F. None of above. chosen

Provenance (5 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_69d81c61f3508190aaf2ca0dc0002c59 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2e7e24f08190ba939a8044860033 completed April 14, 2026, 12:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd323e89948190bb280e93e2058c0a completed May 8, 2026, 12:45 a.m.
NEDg Description generation batch_69fd33d981408190b017164a04676f4c completed May 8, 2026, 12:52 a.m.
NED2 Entity disambiguation (via description) batch_69fd3437f90081908c325f0a36993f57 completed May 8, 2026, 12:54 a.m.
Created at: April 9, 2026, 10:18 p.m.