Triple

T12436772
Position Surface form Disambiguated ID Type / Status
Subject How I Live Now E297162 entity
Predicate cinematographyBy P1953 FINISHED
Object Franz Lustig
Franz Lustig is a German cinematographer known for his visually distinctive work on films such as "How I Live Now."
E1198889 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: Franz Lustig | Statement: [How I Live Now, cinematographyBy, Franz Lustig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Franz Lustig
Context triple: [How I Live Now, cinematographyBy, Franz Lustig]
  • A. Oskar Fischer
    Oskar Fischer was a German neurologist and psychiatrist known for his early research on dementia and the pathological changes associated with Alzheimer’s disease.
  • B. Franz Seldte
    Franz Seldte was a German nationalist politician and co-founder of the Stahlhelm veterans' organization who became a prominent minister in Nazi Germany.
  • C. Fritz Loerzer
    Fritz Loerzer was a German military officer and World War II Luftwaffe general.
  • D. Franz Roth
    Franz Roth is a former German midfielder best known for scoring decisive goals for Bayern Munich in multiple European Cup finals during the 1970s.
  • E. Raoul Hausmann
    Raoul Hausmann was an Austrian-born artist and writer best known as a leading figure of the Berlin Dada movement, pioneering photomontage and experimental sound poetry.
  • 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: Franz Lustig
Triple: [How I Live Now, cinematographyBy, Franz Lustig]
Generated description
Franz Lustig is a German cinematographer known for his visually distinctive work on films such as "How I Live Now."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Franz Lustig
Target entity description: Franz Lustig is a German cinematographer known for his visually distinctive work on films such as "How I Live Now."
  • A. Oskar Fischer
    Oskar Fischer was a German neurologist and psychiatrist known for his early research on dementia and the pathological changes associated with Alzheimer’s disease.
  • B. Franz Seldte
    Franz Seldte was a German nationalist politician and co-founder of the Stahlhelm veterans' organization who became a prominent minister in Nazi Germany.
  • C. Fritz Loerzer
    Fritz Loerzer was a German military officer and World War II Luftwaffe general.
  • D. Franz Roth
    Franz Roth is a former German midfielder best known for scoring decisive goals for Bayern Munich in multiple European Cup finals during the 1970s.
  • E. Raoul Hausmann
    Raoul Hausmann was an Austrian-born artist and writer best known as a leading figure of the Berlin Dada movement, pioneering photomontage and experimental sound poetry.
  • 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_69d6ada0640c81908c061d7fb3d47786 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94d8c8fd481909b35ac504127a1b6 completed April 10, 2026, 7:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69fffee0ff948190911c02f6e50ea2bc completed May 10, 2026, 3:43 a.m.
NEDg Description generation batch_6a00007647a08190bff12da75c4a3c02 completed May 10, 2026, 3:50 a.m.
NED2 Entity disambiguation (via description) batch_6a0000e385bc819080e63ced564fe77b completed May 10, 2026, 3:52 a.m.
Created at: April 8, 2026, 9:55 p.m.