Triple

T21395159
Position Surface form Disambiguated ID Type / Status
Subject Lillian Randolph E527759 entity
Predicate appearedIn P795 FINISHED
Object Judge Priest 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: Judge Priest | Statement: [Lillian Randolph, appearedIn, Judge Priest]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Judge Priest
Context triple: [Lillian Randolph, appearedIn, Judge Priest]
  • A. Judge Priest chosen
    Judge Priest is a 1934 American comedy film directed by John Ford, featuring Will Rogers as a folksy Southern judge and including an early notable performance by Hattie McDaniel.
  • B. Justice Stone
    Justice Stone was a prominent U.S. Supreme Court justice known for his influential opinions in tax and constitutional law during the early 20th century.
  • C. Judge Mathis
    Judge Mathis is a long-running American arbitration-based reality court show featuring former Michigan judge Greg Mathis presiding over small-claims disputes.
  • D. Johnny Castle
    Johnny Castle is the charismatic dance instructor and romantic lead portrayed by Patrick Swayze in the 1987 film "Dirty Dancing."
  • E. Old Judge Priest
    Old Judge Priest is a series of humorous short stories by Irvin S. Cobb centered on a folksy, benevolent judge in a small Kentucky town in the American South.
  • 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_69e0b51ff3748190935c0a513c62a12b completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8b117d8c881908b823c1212b5b919 completed April 22, 2026, 11:29 a.m.
Created at: April 16, 2026, 5:13 p.m.