Triple

T12928555
Position Surface form Disambiguated ID Type / Status
Subject Flame Princess E309308 entity
Predicate affiliation P10 FINISHED
Object Fire Kingdom E1010052 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: Fire Kingdom | Statement: [Flame Princess, affiliation, Fire Kingdom]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fire Kingdom
Context triple: [Flame Princess, affiliation, Fire Kingdom]
  • A. Fire Kingdom chosen
    The Fire Kingdom is a blazing, lava-filled realm ruled by fire elementals in the post-apocalyptic Land of Ooo from the animated series "Adventure Time."
  • B. Forbidden Kingdom
    Forbidden Kingdom is an ancient-Egypt-themed area within Chessington World of Adventures featuring rides, attractions, and immersive theming.
  • C. The Kingdom
    The Kingdom is a Danish supernatural horror television series created by Lars von Trier that blends hospital drama with dark humor and occult phenomena.
  • D. The Kingdom
    The Kingdom is a 2020 studio album by British rock band Bush that showcases a heavier, more modern hard-rock sound.
  • E. The Kingdom
    The Kingdom is an oratorio by English composer Edward Elgar that continues the religious and musical themes of his earlier work The Apostles.
  • 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_69d7bdfa933c8190b5a27aa4a08a19b7 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d971ec72a48190aceef10630603d2c completed April 10, 2026, 9:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8d58a0c8190b96252f04fdf1256 completed May 3, 2026, 2:54 a.m.
Created at: April 9, 2026, 5:42 p.m.