Triple

T15905179
Position Surface form Disambiguated ID Type / Status
Subject Mary-Kate Olsen E385693 entity
Predicate sibling P363 FINISHED
Object Jake Olsen E768399 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: Jake Olsen | Statement: [Mary-Kate Olsen, sibling, Jake Olsen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jake Olsen
Context triple: [Mary-Kate Olsen, sibling, Jake Olsen]
  • A. Jake Olsen chosen
    Jake Olsen is a lesser-known member of the Olsen family, recognized primarily as the brother of actress Elizabeth Olsen and the Olsen twins, Mary-Kate and Ashley.
  • B. Ryan Olson
    Ryan Olson is an American musician and producer best known as the creative force behind the indie supergroup Gayngs and for his work in the Minneapolis music scene.
  • C. Chris Ohlson
    Chris Ohlson is a film producer known for his work on independent features, including the acclaimed drama "Kumiko, the Treasure Hunter."
  • D. Blake Olson
    Blake Olson is the protagonist of "The Matchmaker’s Playbook," a contemporary romance story centered on his involvement in a professional matchmaking scheme that complicates his personal life and relationships.
  • E. Eben Oleson
    Eben Oleson is a small-town Alaskan sheriff who becomes the reluctant hero leading the fight for survival against vampires in the horror story "30 Days of Night."
  • 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_69d86da686e4819097cbf3b1fc2d881d completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1565956588190ba4726a2879b677d completed April 16, 2026, 9:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb5a39a348190a4ef6784c54649c2 completed May 9, 2026, 10:30 p.m.
Created at: April 10, 2026, 4:52 a.m.