Triple
T10260969
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Muhammad Ali vs Sonny Liston fight |
E240591
|
entity |
| Predicate | bettingOdds |
P93133
|
FINISHED |
| Object | Liston heavily favored |
—
|
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: Liston heavily favored | Statement: [Muhammad Ali vs Sonny Liston fight, bettingOdds, Liston heavily favored]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bettingOdds Context triple: [Muhammad Ali vs Sonny Liston fight, bettingOdds, Liston heavily favored]
-
A.
betting
Indicates engaging in a wager where one party risks something of value on the outcome of an uncertain event involving another entity.
-
B.
hasBookmakers
Indicates that an entity is associated with or utilizes one or more bookmakers for betting or odds-setting activities.
-
C.
usedInBettingLines
Indicates that something (such as data, statistics, or an event) is employed as a factor or component in determining betting lines or odds.
-
D.
preSeasonTitleOdds
Indicates the betting or projected probability, set before a season begins, that an entity (typically a team) will win the championship or title.
-
E.
sportsMarketFor
Indicates a market or commercial context in which a particular sport, sporting event, or sports-related product is bought, sold, traded, or otherwise economically transacted.
- F. None of above. chosen
Provenance (4 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_69d381a7e198819090280d5ab885d59e |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d2b5853081909cd0397e08a0f44d |
completed | April 7, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69d4d1edae6881909a65201b8e51ea0a |
completed | April 7, 2026, 9:44 a.m. |
| PDg | Predicate description generation | batch_69d4d2b4ae548190b4a4c671f86b82d1 |
completed | April 7, 2026, 9:47 a.m. |
Created at: April 6, 2026, 11:32 a.m.