Triple
T25307882
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hot Spot |
E634529
|
entity |
| Predicate | hasOdds |
P93133
|
FINISHED |
| Object | odds vary by number of picks and matches |
—
|
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: odds vary by number of picks and matches | Statement: [Hot Spot, hasOdds, odds vary by number of picks and matches]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOdds Context triple: [Hot Spot, hasOdds, odds vary by number of picks and matches]
-
A.
bettingOdds
chosen
Indicates the likelihood or probability of a particular outcome in a bet, typically expressed as numerical odds set for wagering.
-
B.
hasSportsbook
Indicates that an entity operates, offers, or is associated with a sportsbook service for placing sports bets.
-
C.
hasBettingStructure
Indicates that there is a specific set of rules or format governing how bets are placed and progressed in a game or wagering context.
-
D.
hasToteBetting
Indicates that an entity offers or is associated with pari-mutuel (tote) betting services or facilities.
-
E.
wageringAvailable
Indicates that it is possible to place bets or wagers on the associated event or entity.
- 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_69e75a972c6481909bc11710e8d30a6c |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f4939c49a48190b9fdc2555273915e |
completed | May 1, 2026, 11:50 a.m. |
| PD | Predicate disambiguation | batch_69f45d06d0388190b36ecde92013624a |
completed | May 1, 2026, 7:57 a.m. |
Created at: April 21, 2026, 1:25 p.m.