Triple

T17026794
Position Surface form Disambiguated ID Type / Status
Subject Heidi (1937 film) E413084 entity
Predicate screenwriter P2831 FINISHED
Object Julien Josephson E333709 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: Julien Josephson | Statement: [Heidi (1937 film), screenwriter, Julien Josephson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Julien Josephson
Context triple: [Heidi (1937 film), screenwriter, Julien Josephson]
  • A. Julien Josephson chosen
    Julien Josephson was an American screenwriter active in early Hollywood, known for adapting literary works and contributing to several notable studio films.
  • B. Julian Franklin
    Julian Franklin is a relatively obscure individual whose primary notability appears to stem from sharing the surname Franklin rather than from widely recognized public achievements.
  • C. Jules Fisher
    Jules Fisher is a renowned American theatrical lighting designer celebrated for his work on numerous Broadway productions and multiple Tony Award wins.
  • D. Nicholas Wittman
    Nicholas Wittman is an actor best known for his role in the television series "Mars."
  • E. Julian Reid
    Julian Reid is a relatively obscure individual whose specific public notability is not clearly established from the available information.
  • 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d5d5ed388190871aa738cac04b65 completed April 18, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_6a011b53306081908972a0a5db474b6c completed May 10, 2026, 11:57 p.m.
Created at: April 10, 2026, 5:33 a.m.