Triple

T21102059
Position Surface form Disambiguated ID Type / Status
Subject Addie Pray E519929 entity
Predicate mainCharacter P1183 FINISHED
Object Moses Pray 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: Moses Pray | Statement: [Addie Pray, mainCharacter, Moses Pray]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Moses Pray
Context triple: [Addie Pray, mainCharacter, Moses Pray]
  • A. Moses Pray chosen
    Moses Pray is a charmingly roguish Bible salesman and con man who becomes the reluctant guardian and partner-in-crime of a young girl in the film and novel "Paper Moon."
  • B. Moses Blah
    Moses Blah was a Liberian politician and former vice president who briefly served as Liberia’s president in 2003 during the turbulent final phase of the Second Liberian Civil War.
  • C. Moses Liddell
    Moses Liddell is a notable individual who bears the surname Liddell, recognized as a distinguished representative of that family name.
  • D. Moses King
    Moses King was an American publisher and editor best known for producing popular guidebooks and illustrated reference works in the late 19th and early 20th centuries.
  • E. Moses Hightower
    Moses Hightower is a towering, soft-spoken police recruit known for his immense strength and gentle demeanor in the "Police Academy" film series.
  • 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_69e0b508d8dc81909be940dafe36c8f7 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e71b5e16cc81908257ccf8c9a59117 completed April 21, 2026, 6:38 a.m.
Created at: April 16, 2026, 2:53 p.m.