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.