Triple

T4033467
Position Surface form Disambiguated ID Type / Status
Subject Slattery’s Hurricane E83768 entity
Predicate director P255 FINISHED
Object André De Toth E162921 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: André De Toth | Statement: [Slattery’s Hurricane, director, André De Toth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: André De Toth
Context triple: [Slattery’s Hurricane, director, André De Toth]
  • A. André De Toth chosen
    André De Toth was a Hungarian-American film director best known for his work in film noir and 3D horror, including the classic "House of Wax" (1953).
  • B. Jacob Kershner
    Jacob Kershner was the first husband of anarchist activist and writer Emma Goldman, known primarily through his brief and troubled marriage to her in the late 19th century.
  • C. Monte Hellman
    Monte Hellman was an American film director and producer best known for his influential low-budget cult classics, including the road movie "Two-Lane Blacktop."
  • D. Robert Siodmak
    Robert Siodmak was a German-born film director best known for his influential work in Hollywood film noir during the 1940s.
  • E. Tom Benedek
    Tom Benedek is an American screenwriter best known for co-writing the science fiction film "Cocoon."
  • 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_69aed92e29ac819080f7a98b594fec05 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefb108fc0819080c8f41da2e558e0 completed March 9, 2026, 4:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5629748d88190984cce08eef05e9c completed March 14, 2026, 1:28 p.m.
Created at: March 9, 2026, 3:36 p.m.