Triple

T4609502
Position Surface form Disambiguated ID Type / Status
Subject Phillip Crosby E100519 entity
Predicate relative P37 FINISHED
Object Joe E. Brown E147461 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: Joe E. Brown | Statement: [Phillip Crosby, relative, Joe E. Brown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joe E. Brown
Context triple: [Phillip Crosby, relative, Joe E. Brown]
  • A. Joe E. Brown chosen
    Joe E. Brown was a popular American comedian and film actor of the 1930s and 1940s, known for his wide-mouthed grin and roles in numerous Hollywood comedies.
  • B. William Witney
    William Witney was an American film director best known for his prolific work on action-packed B-movies and serials, particularly Westerns, during Hollywood’s mid-20th-century studio era.
  • C. Fred Gwynne
    Fred Gwynne was an American actor and illustrator best known for his comedic television roles, particularly as Herman Munster on the 1960s sitcom "The Munsters."
  • D. Bud Cort
    Bud Cort is an American actor and director best known for his iconic role as the young Harold in the cult classic film "Harold and Maude."
  • E. Errol
    Errol is a masculine given name of English origin, often used as a first name in various English-speaking countries.
  • 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_69bd43cce1e08190a07d53af6a9b6c24 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd599f08d88190ad4bed8bafb592cd completed March 20, 2026, 2:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfa7e918881908743818e0645da46 completed March 21, 2026, 1:55 a.m.
Created at: March 20, 2026, 1:12 p.m.