Triple

T13990618
Position Surface form Disambiguated ID Type / Status
Subject Kung Fu E336562 entity
Predicate creator P184 FINISHED
Object Herman Miller E994634 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: Herman Miller | Statement: [Kung Fu, creator, Herman Miller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Herman Miller
Context triple: [Kung Fu, creator, Herman Miller]
  • A. Herman Miller
    Herman Miller is an American furniture company renowned for its innovative, modern office and home furnishings, including iconic ergonomic chairs and mid-century designs.
  • B. Herman Miller chosen
    Herman Miller was an American screenwriter best known for his work in film and television during the mid-20th century.
  • C. Knoll
    Knoll is an American design firm renowned for its modernist furniture and collaborations with iconic designers such as Eero Saarinen and Ludwig Mies van der Rohe.
  • D. Eames
    Eames is a charismatic and skilled forger in the film "Inception," known for his ability to impersonate others within shared dreamscapes.
  • E. Stanley Works
    Stanley Works is a historic American tool and hardware manufacturing company best known as a predecessor to Stanley Black & Decker.
  • 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_69d81c639e808190a0e4b4f3d31c6a59 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2eb22e388190904fc87765176c91 completed April 14, 2026, 12:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbac98ca448190b585ef69a4e4bfca completed May 6, 2026, 9:03 p.m.
Created at: April 9, 2026, 10:18 p.m.