Triple

T23038726
Position Surface form Disambiguated ID Type / Status
Subject Legoland Florida E573677 entity
Predicate hasSection P35 FINISHED
Object Miniland USA 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: Miniland USA | Statement: [Legoland Florida, hasSection, Miniland USA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Miniland USA
Context triple: [Legoland Florida, hasSection, Miniland USA]
  • A. MINILAND chosen
    MINILAND is a detailed miniature world built from LEGO bricks, typically depicting local landmarks and cityscapes in interactive, small-scale form.
  • B. Modelland
    Modelland is a young adult fantasy novel by supermodel Tyra Banks that satirically explores the world of modeling through a magical, dystopian academy.
  • C. Miniatur Wunderland
    Miniatur Wunderland is a world-famous model railway and miniature world attraction in Hamburg, Germany, featuring intricately detailed landscapes, cities, and interactive displays.
  • D. Vikeland
    Vikeland is a small settlement located within the municipality of Kvæfjord in Troms og Finnmark county, Norway.
  • E. Small World Park
    Small World Park is a family-friendly amusement and recreation park in Pittsburg, California, featuring rides, picnic areas, and attractions geared primarily toward young children.
  • 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_69e245b911188190bc3d96326c847969 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f185121da0819095b523d7d2c923ab completed April 29, 2026, 4:12 a.m.
Created at: April 17, 2026, 3:53 p.m.