Triple
T6427455
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrew Fastow |
E128093
|
entity |
| Predicate | afterPrisonActivity |
P25423
|
FINISHED |
| Object | corporate ethics speaker |
—
|
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: corporate ethics speaker | Statement: [Andrew Fastow, afterPrisonActivity, corporate ethics speaker]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: afterPrisonActivity Context triple: [Andrew Fastow, afterPrisonActivity, corporate ethics speaker]
-
A.
postPrisonOccupation
chosen
Indicates the type of work or occupation a person engages in after being released from prison.
-
B.
restrictionAfterPardon
Indicates that a restriction or limitation is imposed on an entity following the granting of a pardon.
-
C.
laterActivity
Indicates that one activity occurs after another in time, establishing a temporal ordering between them.
-
D.
servedPrisonTime
Indicates that an entity has spent a period of time incarcerated in prison as a consequence of a legal sentence.
-
E.
endedActivityAfterDeathOf
Indicates that an activity was terminated following, and as a consequence of, the death of a specified 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_69c00838de888190af2eec0b80495efa |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c06920cef48190a884df8f12987a0d |
completed | March 22, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69c060f780b08190aa650b4d1fc51f21 |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:44 p.m.