Triple
T3657657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UCI Road World Championships road race |
E77571
|
entity |
| Predicate | jerseyDesign |
P48156
|
FINISHED |
| Object | white jersey with rainbow bands |
—
|
LITERAL 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: white jersey with rainbow bands | Statement: [UCI Road World Championships road race, jerseyDesign, white jersey with rainbow bands]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: jerseyDesign Context triple: [UCI Road World Championships road race, jerseyDesign, white jersey with rainbow bands]
-
A.
jersey
Indicates that one entity is the jersey (sports uniform top) associated with, worn by, or representing another entity.
-
B.
primaryJerseyDesign
chosen
Indicates the main visual design or pattern used on an entity’s primary jersey or uniform.
-
C.
designsFor
Indicates that one entity creates or plans something specifically intended to serve, suit, or be used by another entity.
-
D.
jerseyHonor
Indicates that an entity has been honored by having its jersey formally recognized, typically through retirement or special commemoration.
-
E.
jerseySignificance
Indicates the importance, meaning, or symbolic value associated with a particular jersey in a given context.
- F. None of above.
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_69ad85def5cc8190863dccf55a18bebb |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc3d36c1c8190920397a75de4c47d |
completed | March 8, 2026, 6:45 p.m. |
| PD | Predicate disambiguation | batch_69adb84650148190bf79231105e58d7f |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:24 p.m.