Triple

T20218228
Position Surface form Disambiguated ID Type / Status
Subject The Legend of Zelda (1986 video game) E495181 entity
Predicate setting P1957 FINISHED
Object Hyrule NE NERFINISHED

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: Hyrule | Statement: [The Legend of Zelda (1986 video game), setting, Hyrule]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hyrule
Context triple: [The Legend of Zelda (1986 video game), setting, Hyrule]
  • A. Hyrule chosen
    Hyrule is a recurring fictional kingdom in Nintendo’s The Legend of Zelda series, known for its fantasy landscapes, ancient legends, and central role in the adventures of Link and Princess Zelda.
  • B. Mushroom Kingdom
    Mushroom Kingdom is a whimsical, colorful fantasy realm in the Super Mario franchise, home to characters like Princess Peach, Toads, and various iconic enemies.
  • C. Ylisse
    Ylisse is a central kingdom and setting in the game Fire Emblem Awakening, ruled by the royal family to which Lucina belongs.
  • D. Eternia
    Eternia is a character known for being part of the Justus League, a group of heroes in the relevant fictional universe.
  • E. Eternia
    Eternia is the fictional, magic-infused homeworld of He-Man and other characters in the Masters of the Universe franchise.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da626cff80819097b530718a7c98b6 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66edaeeb08190bb74bd4a10aceca2 completed April 20, 2026, 6:22 p.m.
Created at: April 11, 2026, 11:39 p.m.