Triple

T10811043
Position Surface form Disambiguated ID Type / Status
Subject Mihály Kertész E255098 entity
Predicate child P120 FINISHED
Object Kati Curtiz E48302 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: Kati Curtiz | Statement: [Mihály Kertész, child, Kati Curtiz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kati Curtiz
Context triple: [Mihály Kertész, child, Kati Curtiz]
  • A. Michael Curtiz chosen
    Michael Curtiz was a Hungarian-American film director best known for helming classic Hollywood films such as "Casablanca."
  • B. Rudolph Maté
    Rudolph Maté was a Polish-born cinematographer and film director renowned for his visually striking work in classic Hollywood cinema, including films like "The Passion of Joan of Arc" and "D.O.A."
  • C. Florence Vidor
    Florence Vidor was a prominent American silent film actress of the 1920s, known for her sophisticated screen presence and roles in dramas and comedies.
  • D. Walter Reisch
    Walter Reisch was an Austrian-born screenwriter and film director best known for his work in Hollywood during the 1930s and 1940s, contributing to notable films such as "Gaslight."
  • E. Joseph L. Mankiewicz
    Joseph L. Mankiewicz was an acclaimed American screenwriter, producer, and director known for his sophisticated, dialogue-driven films and multiple Academy Awards, including those for writing and directing.
  • 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_69d6aa61c15c8190a1839550c56e75e1 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d733b7bfac8190b6ae34144376d6ad completed April 9, 2026, 5:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69e3c7d11cf081908f714686f582c081 completed April 18, 2026, 6:05 p.m.
Created at: April 8, 2026, 9:18 p.m.