Triple
T32581437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madison Stakes |
E832798
|
entity |
| Predicate | raceCondition |
P116956
|
FINISHED |
| Object | stakes |
—
|
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: stakes | Statement: [Madison Stakes, raceCondition, stakes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: raceCondition Context triple: [Madison Stakes, raceCondition, stakes]
-
A.
requiresConcurrenceWith
Indicates that one action, decision, or condition must be agreed upon or approved by another specified party or entity before it can proceed or be valid.
-
B.
raceContext
chosen
Indicates the situational or environmental circumstances under which a race or competitive event takes place.
-
C.
captureCondition
Indicates the specific circumstances or criteria under which a capture event or action is triggered or considered valid.
-
D.
raceRegion
Indicates that an instance of a race takes place within, or is associated with, a specific geographic region.
-
E.
concurrencyControl
Indicates that multiple operations or transactions are coordinated so they can occur at the same time without interfering with each other or corrupting shared data.
- 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_69f349289adc81909f4374a58ec35a39 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c669d6408190bc26dbf21f59e237 |
completed | May 3, 2026, 3:52 a.m. |
| PD | Predicate disambiguation | batch_69f6bd2c138481908afa3ee3e91f8900 |
completed | May 3, 2026, 3:12 a.m. |
Created at: May 1, 2026, 1:04 a.m.