Triple

T8742258
Position Surface form Disambiguated ID Type / Status
Subject F for Fake E207531 entity
Predicate featuresPerson P2308 FINISHED
Object Oja Kodar E754462 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: Oja Kodar | Statement: [F for Fake, featuresPerson, Oja Kodar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oja Kodar
Context triple: [F for Fake, featuresPerson, Oja Kodar]
  • A. Oja Kodar chosen
    Oja Kodar is a Croatian actress, screenwriter, and longtime collaborator and partner of filmmaker Orson Welles, known for her work on several of his later projects.
  • B. Katia Mann
    Katia Mann was a German intellectual and the wife and close confidante of Nobel Prize–winning author Thomas Mann, known for her significant influence on his life and work.
  • C. Renata Kallosh
    Renata Kallosh is a theoretical physicist known for her influential work in supergravity, string theory, and cosmology.
  • D. Ilona Kovács
    Ilona Kovács was the wife of renowned Hungarian-American film director Michael Curtiz.
  • E. Julie Kroitor
    Julie Kroitor is a child of Canadian filmmaker and IMAX co-founder Roman Kroitor.
  • 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_69ca835a03a081909d4d4cd01a18c9fb completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5d6fd5dc8190906b7147f27c5d46 completed March 31, 2026, 11:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf518750948190a42ad8fc352ac851 completed April 3, 2026, 5:35 a.m.
Created at: March 30, 2026, 6:38 p.m.