Triple

T15971502
Position Surface form Disambiguated ID Type / Status
Subject Jens Grede E387333 entity
Predicate spouse P13 FINISHED
Object Emma Grede E387331 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: Emma Grede | Statement: [Jens Grede, spouse, Emma Grede]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Emma Grede
Context triple: [Jens Grede, spouse, Emma Grede]
  • A. Emma Grede chosen
    Emma Grede is a British entrepreneur and fashion executive best known as the co-founder and CEO of Good American and a founding partner of Kim Kardashian’s shapewear brand SKIMS.
  • B. Nina Kristensen
    Nina Kristensen is a video game developer and co-founder of the British studio Ninja Theory, known for cinematic action titles like Heavenly Sword and Hellblade: Senua’s Sacrifice.
  • C. Camilla Christensen
    Camilla Christensen is a Danish fashion model known for her work with major international brands and appearances in prominent magazines and runway shows.
  • D. Christianne Jensen
    Christianne Jensen is a vocalist known for her guest appearance on Jon Bellion’s album "Glory Sound Prep."
  • E. Karoline Pettersen
    Karoline Pettersen is known as the former spouse of Norwegian actor and director Aksel Hennie.
  • 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_69d86da94ccc819083d187f5dc6a123e completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e15729d73c8190a4140a0e55ee2566 completed April 16, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffcf1893388190800f013fab415ae7 completed May 10, 2026, 12:19 a.m.
Created at: April 10, 2026, 4:54 a.m.