Triple

T14146396
Position Surface form Disambiguated ID Type / Status
Subject Behind the Sun E350560 entity
Predicate producer P490 FINISHED
Object Arthur Cohn E685283 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: Arthur Cohn | Statement: [Behind the Sun, producer, Arthur Cohn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arthur Cohn
Context triple: [Behind the Sun, producer, Arthur Cohn]
  • A. Arthur Cohn chosen
    Arthur Cohn is a Swiss film producer renowned for his multiple Academy Award–winning independent and international films.
  • B. Alfred A. Cohn
    Alfred A. Cohn was an American screenwriter and title writer of the silent and early sound film era, best known for his work on influential films such as The Jazz Singer.
  • C. George Corson
    George Corson was a 19th-century British architect known for his significant contributions to the architectural landscape of Leeds, England.
  • D. Alvin Marks
    Alvin Marks was an American inventor known for his work on advanced energy technologies and high-efficiency lighting concepts.
  • E. Arthur Dorman
    Arthur Dorman was a British industrialist best known as a co-founder of the major steel and engineering firm Dorman Long and Co Ltd, which played a significant role in bridge building and heavy industry.
  • 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_69d827865f608190b311820428ae027b completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de612266248190a8591b646fe30ae6 completed April 14, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd8aa0e98c81908f6b55a04cd72871 completed May 8, 2026, 7:02 a.m.
Created at: April 10, 2026, 12:54 a.m.