Triple
T21901198
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wood Memorial Stakes |
E540811
|
entity |
| Predicate | approximateTimingRelativeToDerby |
P48368
|
FINISHED |
| Object | About four weeks before the Kentucky Derby |
—
|
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: About four weeks before the Kentucky Derby | Statement: [Wood Memorial Stakes, approximateTimingRelativeToDerby, About four weeks before the Kentucky Derby]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateTimingRelativeToDerby Context triple: [Wood Memorial Stakes, approximateTimingRelativeToDerby, About four weeks before the Kentucky Derby]
-
A.
timingMethod
Indicates the method or technique used to measure or record the timing of an event or process.
-
B.
timeStartApprox
chosen
Indicates that the associated event or state begins at an approximate, rather than exact, point in time.
-
C.
hasApproximateDuration
Indicates that one entity has a duration that is estimated or not exact, typically expressed as an approximate length of time.
-
D.
migrationTiming
Indicates the temporal characteristics or schedule of when a migration event occurs or is expected to occur.
-
E.
calculationTime
Indicates the amount of time required to perform or complete a calculation.
- 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_69e0c47b4e8c81908c8076eaa4c8e4f2 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f11fcb18748190a21071c122b7e6d5 |
completed | April 28, 2026, 8:59 p.m. |
| PD | Predicate disambiguation | batch_69e6be9ebf4c8190892df1a8e1313f88 |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 7:16 p.m.