Triple
T13041988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Lysiak |
E327215
|
entity |
| Predicate | penaltyForIncident |
P1841
|
FINISHED |
| Object | 20-game suspension |
—
|
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: 20-game suspension | Statement: [Tom Lysiak, penaltyForIncident, 20-game suspension]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: penaltyForIncident Context triple: [Tom Lysiak, penaltyForIncident, 20-game suspension]
-
A.
defaultPenalty
Indicates that a standard or automatically applied penalty is imposed in the absence of a specific or overridden penalty.
-
B.
penaltyProvision
chosen
Indicates that a rule, contract, or law includes a clause specifying a punishment or sanction for non-compliance or violation.
-
C.
penaltiesAdjustedBy
Indicates that one entity’s penalties are modified, recalculated, or otherwise changed as a result of another entity’s influence or action.
-
D.
punitiveDamagesAwarded
Indicates that a court has granted punitive damages against a party, typically to punish wrongful conduct and deter similar future behavior.
-
E.
penaltySaveBy
Indicates that a penalty kick was successfully saved by a particular goalkeeper.
- 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_69d8076e64308190904fb5c93517c901 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d98a9829b48190b23624b6b3df4600 |
completed | April 10, 2026, 11:41 p.m. |
| PD | Predicate disambiguation | batch_69d9803aca4c8190b1015cd159cc47a9 |
completed | April 10, 2026, 10:56 p.m. |
Created at: April 9, 2026, 8:56 p.m.