Triple

T2804021
Position Surface form Disambiguated ID Type / Status
Subject Wicker Park E54009 entity
Predicate starring P1507 FINISHED
Object Diane Kruger E31747 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: Diane Kruger | Statement: [Wicker Park, starring, Diane Kruger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Diane Kruger
Context triple: [Wicker Park, starring, Diane Kruger]
  • A. Diane Kruger chosen
    Diane Kruger is a German-born actress and former fashion model best known for her roles in films such as "Troy," "Inglourious Basterds," and "National Treasure."
  • B. Franka Potente
    Franka Potente is a German actress best known internationally for her breakout role in "Run Lola Run" and her appearances in the Bourne film series.
  • C. Juliette Binoche
    Juliette Binoche is an acclaimed French actress known for her nuanced performances in international cinema and her Academy Award-winning role in "The English Patient."
  • D. Bérénice Marlohe
    Bérénice Marlohe is a French actress best known internationally for her role as Sévérine in the James Bond film "Skyfall."
  • E. Virginie Ledoyen
    Virginie Ledoyen is a French actress known for her work in both French cinema and international films, including prominent roles in dramas and thrillers.
  • 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_69ab49dcee188190b5c6eca9ae9e3469 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abde1409148190a06a401185a26b64 completed March 7, 2026, 8:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69afc674217c81908177b088cc824e7b completed March 10, 2026, 7:21 a.m.
Created at: March 6, 2026, 9:59 p.m.