Triple
T488510
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dan Snyder |
E9932
|
entity |
| Predicate | penalty |
P2287
|
FINISHED |
| Object | NFL fine of 10 million USD in 2021 |
—
|
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: NFL fine of 10 million USD in 2021 | Statement: [Dan Snyder, penalty, NFL fine of 10 million USD in 2021]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: penalty Context triple: [Dan Snyder, penalty, NFL fine of 10 million USD in 2021]
-
A.
penaltyProvision
Indicates that a rule, contract, or law includes a clause specifying a punishment or sanction for non-compliance or violation.
-
B.
punishedBy
chosen
Indicates that an entity receives punishment administered by another entity.
-
C.
hasPunishment
Indicates that an entity is subject to a specified penalty, sanction, or adverse consequence as a result of some action, condition, or rule.
-
D.
plea
Indicates that a defendant formally states their response (such as guilty, not guilty, or no contest) to criminal charges in a legal proceeding.
-
E.
passes
Indicates that one entity successfully transfers, hands over, or moves something (such as an object, message, or responsibility) to another 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_69a2e802e2908190ab17c9479e0b6412 |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2f0df764481909811d9483dfbc4aa |
completed | Feb. 28, 2026, 1:42 p.m. |
| PD | Predicate disambiguation | batch_69a2edf63fbc819090ea6ca11f39116a |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.