Triple
T18344479
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UAE Derby |
E439498
|
entity |
| Predicate | raceSurfaceChange |
P129040
|
FINISHED |
| Object | switched to dirt at Meydan in 2015 |
—
|
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: switched to dirt at Meydan in 2015 | Statement: [UAE Derby, raceSurfaceChange, switched to dirt at Meydan in 2015]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: raceSurfaceChange Context triple: [UAE Derby, raceSurfaceChange, switched to dirt at Meydan in 2015]
-
A.
raceSurfaceHistory
chosen
Indicates the type of surface on which an entity has raced in the past, capturing its historical race-surface conditions.
-
B.
racecourseFeature
Indicates that one entity is a physical or functional feature or component of a racecourse associated with the other entity.
-
C.
raceTrack
Indicates that one entity serves as a race track or racing course used by another entity for racing activities.
-
D.
hasRaceSurface
Indicates that an event or activity takes place on, or is associated with, a specific type of race surface.
-
E.
raceAdded
Indicates that a race event or race-related record has been newly created or incorporated into a system or dataset.
- 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_69d8b9175fec8190af865699b4e64d8c |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e514f2c8ec8190b045482846a68204 |
completed | April 19, 2026, 5:46 p.m. |
| PD | Predicate disambiguation | batch_69e44fe91bc08190906518e1b120fcf0 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:37 a.m.