Triple

T21282047
Position Surface form Disambiguated ID Type / Status
Subject Frances Gumm E524549 entity
Predicate child P120 FINISHED
Object Joey Luft 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: Joey Luft | Statement: [Frances Gumm, child, Joey Luft]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joey Luft
Context triple: [Frances Gumm, child, Joey Luft]
  • A. Joey Luft chosen
    Joey Luft is an American television producer and occasional actor best known as the son of legendary entertainer Judy Garland and producer Sidney Luft.
  • B. Joey Wright
    Joey Wright is an American-Australian basketball coach best known for his successful tenure in Australia’s National Basketball League, where he earned multiple Coach of the Year awards and led several teams to deep playoff runs.
  • C. Joey Kern
    Joey Kern is an American actor known for his roles in films like "Cabin Fever" and "Super Troopers," as well as various television appearances.
  • D. Joey Zimmerman
    Joey Zimmerman is an American actor best known for playing Dylan Piper in Disney Channel’s "Halloweentown" film series.
  • E. Joey Matthews
    Joey Matthews is a central character in the 1954 mystery thriller film "Gorilla at Large," around whom much of the circus-themed suspense and intrigue revolves.
  • 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.