Triple

T6080490
Position Surface form Disambiguated ID Type / Status
Subject Fred Schepisi E135509 entity
Predicate directed P7373 FINISHED
Object Words and Pictures E566010 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: Words and Pictures | Statement: [Fred Schepisi, directed, Words and Pictures]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Words and Pictures
Context triple: [Fred Schepisi, directed, Words and Pictures]
  • A. Words and Pictures chosen
    Words and Pictures is a 2013 romantic drama film about the rivalry and relationship between an art teacher and an English teacher at a prep school, directed by Fred Schepisi.
  • B. Stories and Pictures
    Stories and Pictures is a celebrated collection of Yiddish short stories by I. L. Peretz that helped define modern Jewish literature.
  • C. The Book with No Pictures
    The Book with No Pictures is a bestselling children's picture book by comedian and writer B. J. Novak that uses only text and playful typography to create a humorous, read-aloud experience without any illustrations.
  • D. The Ink Factory
    The Ink Factory is a British production company best known for adapting John le Carré’s works for film and television.
  • E. Of Words
    "Of Words" is a chapter in Book III that examines the nature, use, and significance of language and terminology.
  • 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_69c0087ad31c8190ab936e0ff28614b6 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c057735b6081908b82757505fa7d5d completed March 22, 2026, 8:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1252a178c81909a3d689ad748fb5e completed March 23, 2026, 11:34 a.m.
Created at: March 22, 2026, 4:11 p.m.