Triple

T29486282
Position Surface form Disambiguated ID Type / Status
Subject Fritz Kahn E747931 entity
Predicate usedVisualMetaphor P82532 FINISHED
Object factory as metaphor for the human body LITERAL 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: factory as metaphor for the human body | Statement: [Fritz Kahn, usedVisualMetaphor, factory as metaphor for the human body]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: usedVisualMetaphor
Context triple: [Fritz Kahn, usedVisualMetaphor, factory as metaphor for the human body]
  • A. visualMetaphor chosen
    Indicates a relationship where one entity conceptually represents or explains another through a visual analogy or symbolic imagery.
  • B. primaryMetaphor
    Indicates a fundamental conceptual mapping where one domain (often concrete or physical) is systematically understood in terms of another (often abstract), forming a basic metaphorical relationship between them.
  • C. usesScientificMetaphor
    Indicates that one entity employs scientific concepts or terminology metaphorically to describe or explain another entity or situation.
  • D. visualElements
    Indicates that one entity contains, uses, or is characterized by specific visual components or graphical features associated with another entity.
  • E. visuallyDefines
    Indicates that one entity establishes or clarifies the appearance, form, or visual characteristics of another entity.
  • F. None of above.

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_69f0bd43ba30819095eb1cfc3adf525c completed April 28, 2026, 1:59 p.m.
NER Named-entity recognition batch_69f66c06bbc48190b97efd782ebc81e6 completed May 2, 2026, 9:26 p.m.
PD Predicate disambiguation batch_69f6633ac8a88190ab0cda62bbfcf9b0 completed May 2, 2026, 8:48 p.m.
Created at: April 28, 2026, 4:08 p.m.