Triple

T14630919
Position Surface form Disambiguated ID Type / Status
Subject Grosse Pointe Blank E343474 entity
Predicate editedBy P1954 FINISHED
Object Brian Berdan E323818 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: Brian Berdan | Statement: [Grosse Pointe Blank, editedBy, Brian Berdan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brian Berdan
Context triple: [Grosse Pointe Blank, editedBy, Brian Berdan]
  • A. Brian Berdan chosen
    Brian Berdan is a film editor known for his work on action-packed movies such as "Crank: High Voltage."
  • B. Daniel Krumitz
    Daniel Krumitz is a brilliant but socially awkward FBI cyber forensics expert featured as a central character in the television series CSI: Cyber.
  • C. Charles Heerey
    Charles Heerey was a Catholic prelate and missionary bishop who played a significant role in the hierarchy of the Church in Nigeria.
  • D. Wilson Benge
    Wilson Benge was a British character actor, often cast as butlers or servants, who appeared in numerous Hollywood films during the early 20th century.
  • E. Charles Horvath
    Charles Horvath was an American actor and stuntman known for his rugged roles in Westerns and action films.
  • 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_69d822dffc3c8190aa173b90761bffda completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb4a912248190a3df7f821395c776 completed April 14, 2026, 9:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdfb7ab30c8190af49268b6f93aeb1 completed May 8, 2026, 3:04 p.m.
Created at: April 10, 2026, 1:26 a.m.