Triple
T21566507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SAC Capital Advisors |
E532174
|
entity |
| Predicate | receivedPenalty |
P3012
|
FINISHED |
| Object | multi-billion dollar fine |
—
|
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: multi-billion dollar fine | Statement: [SAC Capital Advisors, receivedPenalty, multi-billion dollar fine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: receivedPenalty Context triple: [SAC Capital Advisors, receivedPenalty, multi-billion dollar fine]
-
A.
penaltyPoints
Indicates that a certain number of negative points or demerits are assigned to an entity as a consequence of a rule violation, error, or infraction.
-
B.
penaltyReducedTo
Indicates that an existing penalty has been lowered or commuted to a lesser penalty or amount.
-
C.
penaltyAppliesTo
Indicates that a specific penalty is imposed on, or is relevant to, a particular entity or situation.
-
D.
hasPunishment
chosen
Indicates that an entity is subject to a specified penalty, sanction, or adverse consequence as a result of some action, condition, or rule.
-
E.
supportsPenalty
Indicates that one entity endorses, approves of, or is in favor of a particular penalty being applied to another entity or situation.
- 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_69e0c460db088190828c64206a450273 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eee9c912a08190952bbc9217a957d9 |
completed | April 27, 2026, 4:44 a.m. |
| PD | Predicate disambiguation | batch_69e6320c8c2c81908bf031447d66a052 |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:30 p.m.