Triple

T12436645
Position Surface form Disambiguated ID Type / Status
Subject Defiance E297159 entity
Predicate starring P1507 FINISHED
Object Iben Hjejle E828082 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: Iben Hjejle | Statement: [Defiance, starring, Iben Hjejle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Iben Hjejle
Context triple: [Defiance, starring, Iben Hjejle]
  • A. Iben Hjejle chosen
    Iben Hjejle is a Danish actress best known internationally for her role opposite John Cusack in the romantic comedy-drama film "High Fidelity."
  • B. Flemming Christensen
    Flemming Christensen is a Danish former professional footballer and coach known for his career as a forward in Danish and European clubs.
  • C. Jørn Mikkelsen
    Jørn Mikkelsen is a Danish journalist best known for leading the national newspaper Jyllands-Posten as its editor-in-chief.
  • D. Lars Mikkelsen
    Lars Mikkelsen is a Danish actor known for his roles in series such as "The Killing," "Sherlock," and "House of Cards," as well as for his work in Danish film and television.
  • E. Trine Dyrholm
    Trine Dyrholm is an acclaimed Danish actress and singer known for her powerful performances in both film and television, including prominent roles in internationally recognized Danish cinema.
  • 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_69d6ada0640c81908c061d7fb3d47786 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94d8c8fd481909b35ac504127a1b6 completed April 10, 2026, 7:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f63f06d16481909ed2eb5195ebd7e4 completed May 2, 2026, 6:14 p.m.
Created at: April 8, 2026, 9:55 p.m.