Triple

T14527676
Position Surface form Disambiguated ID Type / Status
Subject Pat Morita E340821 entity
Predicate name P16 FINISHED
Object Pat Morita E340821 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: Pat Morita | Statement: [Pat Morita, name, Pat Morita]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pat Morita
Context triple: [Pat Morita, name, Pat Morita]
  • A. Pat Morita chosen
    Pat Morita was a Japanese-American actor and comedian best known for his role as Mr. Miyagi in "The Karate Kid" film series.
  • B. Tokujin Yoshioka
    Tokujin Yoshioka is a renowned Japanese designer and artist celebrated for his innovative use of light, transparent materials, and poetic minimalism in furniture, interiors, and installations.
  • C. Dan Inosanto
    Dan Inosanto is a Filipino-American martial arts instructor and Jeet Kune Do expert best known as Bruce Lee’s close student and collaborator, as well as a key figure in popularizing Filipino martial arts worldwide.
  • D. Takeshi Katō
    Takeshi Katō was a Japanese actor known for his supporting roles in numerous postwar films and television dramas.
  • E. Osamu Shimomura
    Osamu Shimomura was a Japanese organic chemist and marine biologist best known for discovering and isolating the green fluorescent protein (GFP), a breakthrough that revolutionized biological imaging.
  • 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_69d822dac79c8190a84a073f3cbaced5 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dea051bc608190ad4d516c5e7bca43 completed April 14, 2026, 8:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd7a52260881909a0d85603666107d completed May 8, 2026, 5:53 a.m.
Created at: April 10, 2026, 1:22 a.m.