Triple

T12423479
Position Surface form Disambiguated ID Type / Status
Subject Somebody Up There Likes Me E296837 entity
Predicate editedBy P1954 FINISHED
Object Albert Akst E211226 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: Albert Akst | Statement: [Somebody Up There Likes Me, editedBy, Albert Akst]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Albert Akst
Context triple: [Somebody Up There Likes Me, editedBy, Albert Akst]
  • A. Albert Akst chosen
    Albert Akst was an American film editor known for his work on numerous Hollywood productions, particularly musicals, during the mid-20th century.
  • B. Paul Kohner
    Paul Kohner was a prominent Hollywood talent agent and film producer who represented major European and American stars during the mid-20th century.
  • C. Paul Graetz
    Paul Graetz was a French film producer active in the mid-20th century, known for backing a range of notable European films.
  • D. Arthur Kober
    Arthur Kober was an American humorist, playwright, and screenwriter known for his witty short stories and work in Hollywood during the mid-20th century.
  • E. Arthur Seid
    Arthur Seid is a film editor known for his work on the classic 1948 crime drama "Force of Evil."
  • 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_69d6ada0640c81908c061d7fb3d47786 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94d7b6bd08190b30beba393a5b1e7 completed April 10, 2026, 7:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6349552fc81909fe73dea082e3a25 completed May 2, 2026, 5:29 p.m.
Created at: April 8, 2026, 9:55 p.m.