Triple

T13797405
Position Surface form Disambiguated ID Type / Status
Subject Real Steel E331551 entity
Predicate castMember P1668 FINISHED
Object Karl Yune E1060221 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: Karl Yune | Statement: [Real Steel, castMember, Karl Yune]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karl Yune
Context triple: [Real Steel, castMember, Karl Yune]
  • A. Karl Yune chosen
    Karl Yune is an American actor known for roles in films such as "Memoirs of a Geisha" and "Real Steel."
  • B. Ray Yoshida
    Ray Yoshida was an influential American painter and educator associated with the Chicago Imagists, known for his collage-like compositions and his long teaching career shaping generations of artists.
  • C. Takeshi Kasai
    Takeshi Kasai is a Japanese public health expert who has served in senior leadership roles at the World Health Organization, particularly in the Asia-Pacific region.
  • D. Hiro Yamamoto
    Hiro Yamamoto is an American bassist best known as a founding member of the Seattle grunge band Soundgarden.
  • E. Takao Kato
    Takao Kato is a Japanese automotive executive who has served as president and chief executive officer of Mitsubishi Motors Corporation.
  • 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_69d81c58feb08190a77bca8bf7d6d20f completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de025be1f08190aac525d72d7dc0c3 completed April 14, 2026, 9:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b086d6d48190b823ed0a4403fbc5 completed May 3, 2026, 8:31 p.m.
Created at: April 9, 2026, 10:11 p.m.