Triple

T22079884
Position Surface form Disambiguated ID Type / Status
Subject Outdoor Systems E545621 entity
Predicate foundedBy P104 FINISHED
Object Karl Eller NE NERFINISHED

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: Karl Eller | Statement: [Outdoor Systems, foundedBy, Karl Eller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karl Eller
Context triple: [Outdoor Systems, foundedBy, Karl Eller]
  • A. Karl Eller chosen
    Karl Eller was an influential American businessman and media executive known for building major advertising and communications companies and for his significant philanthropic support of business education.
  • B. Karl Klingler
    Karl Klingler was a German violinist, violist, and chamber musician best known as the founder and leader of the renowned Klingler Quartet.
  • C. Karl Weschke
    Karl Weschke was a German-born British painter known for his expressive, often somber figurative and landscape works and his association with the post-war St Ives art scene in Cornwall.
  • D. Frank Klingebiel
    Frank Klingebiel is a German local politician who serves as the long-time mayor of the city of Salzgitter in Lower Saxony.
  • E. Arthur Hoerl
    Arthur Hoerl was an American screenwriter active during the early to mid-20th century, known for his work on numerous low-budget and genre films.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e3523488190badd54b5d580c00d completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128b56d5c8190aa825fe02e3ad917 completed April 28, 2026, 9:37 p.m.
Created at: April 16, 2026, 8:28 p.m.