Triple

T4708982
Position Surface form Disambiguated ID Type / Status
Subject Harry Cohn E104461 entity
Predicate sibling P363 FINISHED
Object Jack Cohn E213509 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: Jack Cohn | Statement: [Harry Cohn, sibling, Jack Cohn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jack Cohn
Context triple: [Harry Cohn, sibling, Jack Cohn]
  • A. Jack Cohn chosen
    Jack Cohn was an American film executive and producer who co-founded Columbia Pictures and helped shape the early Hollywood studio system.
  • B. Charles Klein
    Charles Klein was a prominent early 20th-century American playwright best known for his successful Broadway dramas and melodramas.
  • C. Albert Bloch
    Albert Bloch was an American modernist painter best known for his association with the German Expressionist movement and his participation in the Der Blaue Reiter group.
  • D. Dashiell Weinstein
    Dashiell Weinstein is one of the children of disgraced film producer Harvey Weinstein.
  • E. Ralph Berkowitz
    Ralph Berkowitz was an American pianist, accompanist, and arts administrator known for his influential work in classical music performance and education.
  • 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_69bd43eac3c08190af7e4020c6c3704c completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd63ed2ed081908cd52570ba085806 completed March 20, 2026, 3:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69be43a16d1c819081e9e20f015c7f90 completed March 21, 2026, 7:07 a.m.
Created at: March 20, 2026, 1:17 p.m.