Triple

T357344
Position Surface form Disambiguated ID Type / Status
Subject EPCOT E7572 entity
Predicate hasAttraction P105 FINISHED
Object Spaceship Earth E45270 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: Spaceship Earth | Statement: [EPCOT, hasAttraction, Spaceship Earth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Spaceship Earth
Context triple: [EPCOT, hasAttraction, Spaceship Earth]
  • A. Spaceship Earth chosen
    Spaceship Earth is a geodesic sphere–shaped dark ride at EPCOT in Walt Disney World that takes guests on a narrated journey through the history and evolution of human communication.
  • B. Sunsphere
    The Sunsphere is a 266-foot-tall, gold-glass observation tower built as the symbol of the 1982 World's Fair in Knoxville, Tennessee.
  • C. Centennial Wheel
    The Centennial Wheel is a large, modern Ferris wheel at Chicago’s Navy Pier that offers panoramic views of the city skyline and Lake Michigan.
  • D. Tempozan Giant Ferris Wheel
    Tempozan Giant Ferris Wheel is a large, popular observation wheel in Osaka, Japan, offering panoramic views of the city and Osaka Bay.
  • E. SkyPod observation deck
    The SkyPod observation deck is one of the highest public viewing platforms in the world, offering panoramic views from near the top of Toronto’s CN Tower.
  • 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_69a2e7e696948190bebc966535995e45 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ebaf0c9881909313f98818e7fa58 completed Feb. 28, 2026, 1:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3e86175588190a893cb2266f06170 completed March 1, 2026, 7:18 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.