Triple
T19206345
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Thornton |
E480242
|
entity |
| Predicate | wagersOn |
P27042
|
FINISHED |
| Object | Buck’s ability to pull a 1,000-pound sled |
—
|
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: Buck’s ability to pull a 1,000-pound sled | Statement: [John Thornton, wagersOn, Buck’s ability to pull a 1,000-pound sled]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wagersOn Context triple: [John Thornton, wagersOn, Buck’s ability to pull a 1,000-pound sled]
-
A.
wagerAmount
Indicates the specific sum of money or value that is staked or risked in a bet or wager between parties.
-
B.
outcomeOfWager
Indicates that one entity is the result or consequence of a wager or bet made by another entity.
-
C.
wagerGoal
Indicates that an entity sets or specifies a target outcome or objective for a wager or bet.
-
D.
betting
chosen
Indicates engaging in a wager where one party risks something of value on the outcome of an uncertain event involving another entity.
-
E.
typeOfStake
Indicates the specific kind or category of stake or ownership interest that one entity holds in another.
- 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_69d8e8cb8c348190b52075823911c869 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5f99d8ad0819098ebd4ee007149f1 |
completed | April 20, 2026, 10:02 a.m. |
| PD | Predicate disambiguation | batch_69e4dcf22b3c8190bee02e3af946e114 |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:19 p.m.