Triple
T22107111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Remsen Stakes |
E546313
|
entity |
| Predicate | approximatePurseRange |
P131010
|
FINISHED |
| Object | hundreds of thousands of US dollars |
—
|
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: hundreds of thousands of US dollars | Statement: [Remsen Stakes, approximatePurseRange, hundreds of thousands of US dollars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximatePurseRange Context triple: [Remsen Stakes, approximatePurseRange, hundreds of thousands of US dollars]
-
A.
approximatePurse
Indicates that one entity estimates or comes close to determining the value, amount, or contents of another entity’s purse or collection of resources.
-
B.
typicalPurseRangeUSD
chosen
Indicates the usual monetary range in U.S. dollars for the prize purse or total payout associated with an event or activity.
-
C.
totalPurse
Indicates the total amount of prize money or winnings available in a given competitive event or context.
-
D.
categoryRange
Indicates that a category or classification spans from a defined lower bound to an upper bound within a specified range.
-
E.
rangeCityApprox
Indicates that an entity is located within an approximate geographic range of a specified city, rather than at an exact or strictly defined boundary.
- 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_69e11e378dc08190896d6a51597afd5a |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12919dd388190b8ca08e2464cb0b8 |
completed | April 28, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69e71b2ed7348190b6fa2e52f54393fb |
completed | April 21, 2026, 6:37 a.m. |
Created at: April 16, 2026, 8:30 p.m.