Triple
T15535352
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yoshi Circuit |
E370325
|
entity |
| Predicate | courseClass |
P119066
|
FINISHED |
| Object | Flower Cup |
E1154597
|
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: Flower Cup | Statement: [Yoshi Circuit, courseClass, Flower Cup]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Flower Cup Context triple: [Yoshi Circuit, courseClass, Flower Cup]
-
A.
Flower Cup
chosen
Flower Cup is a racing tournament cup in the Mario Kart series, typically featuring beginner-friendly tracks with bright, colorful themes.
-
B.
Flower Piece
Flower Piece is the English title of Robert Schumann’s short piano work "Blumenstück in D-flat major, Op. 19," a lyrical Romantic character piece.
-
C.
Flower Lady
Flower Lady is a song featured on Phil Ochs’s 1967 album "Pleasures of the Harbor."
-
D.
Crossing Cup
Crossing Cup is a downloadable content Grand Prix cup in Mario Kart 8 featuring tracks inspired by the Animal Crossing series and other themed courses.
-
E.
Maiden Cup
The Maiden Cup is a prestigious annual horse racing event held in Mauritius, attracting top thoroughbreds and significant public attention.
- 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_69d85cc521a08190921fb50319dddc34 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e0442e327c8190b4b879c8a3cd38e3 |
completed | April 16, 2026, 2:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff3d605b908190a18c63142c8bb854 |
completed | May 9, 2026, 1:57 p.m. |
Created at: April 10, 2026, 4:06 a.m.