Triple

T6184152
Position Surface form Disambiguated ID Type / Status
Subject The Clock E138013 entity
Predicate costumeDesigner P184 FINISHED
Object Irene Sharaff E224489 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: Irene Sharaff | Statement: [The Clock, costumeDesigner, Irene Sharaff]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Irene Sharaff
Context triple: [The Clock, costumeDesigner, Irene Sharaff]
  • A. Irene Sharaff chosen
    Irene Sharaff was an acclaimed American costume designer known for her influential work in Broadway theatre and Hollywood films, earning multiple Academy Awards for her distinctive visual style.
  • B. Miriam Henreid
    Miriam Henreid is known as one of the daughters of Austrian-born actor and director Paul Henreid.
  • C. Lilyan Tashman
    Lilyan Tashman was an American stage and film actress of the silent and early sound eras, known for her sophisticated, often vampish roles and stylish screen presence in the 1920s and early 1930s.
  • D. Hilde Benjamin
    Hilde Benjamin was a prominent East German jurist and politician, notorious as a hardline judge and later Minister of Justice in the German Democratic Republic.
  • E. Lisa Fruchtman
    Lisa Fruchtman is an American film editor known for her work on major films such as "Apocalypse Now" and for winning an Academy Award for Best Film Editing.
  • 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_69c008a8fd408190b7ec6e42934974a6 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c061020d148190ae2edf2b363f1e24 completed March 22, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69c243d333e48190b1cb9ffd769f5473 completed March 24, 2026, 7:57 a.m.
Created at: March 22, 2026, 4:19 p.m.