Triple

T21282044
Position Surface form Disambiguated ID Type / Status
Subject Frances Gumm E524549 entity
Predicate spouse P13 FINISHED
Object Mickey Deans NE NERFINISHED

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: Mickey Deans | Statement: [Frances Gumm, spouse, Mickey Deans]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mickey Deans
Context triple: [Frances Gumm, spouse, Mickey Deans]
  • A. Mickey Deans chosen
    Mickey Deans was an American discotheque manager and musician best known as the fifth and final husband of legendary entertainer Judy Garland.
  • B. Mickey Rivers
    Mickey Rivers is a former Major League Baseball center fielder best known for his speed, leadoff hitting, and key role on the New York Yankees’ late-1970s championship teams.
  • C. Jack Dean
    Jack Dean was an early 20th-century American silent film actor best known for his leading roles in melodramas such as "The Cheat."
  • D. Mickey Rogers
    Mickey Rogers is an alternative spelling or nickname form of the name Michael Rogers, typically referring to the same individual.
  • E. Mickey Fisher
    Mickey Fisher is an American television writer and producer best known for creating the science fiction drama series "Extant."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b5171f6c8190a5d57201ede73811 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e736d249fc8190b0b310467ddeac3c completed April 21, 2026, 8:35 a.m.
Created at: April 16, 2026, 4:02 p.m.