Triple
T14071814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | J. Parnell Thomas |
E338625
|
entity |
| Predicate | charged with |
P77292
|
FINISHED |
| Object | conspiracy to defraud the United States |
—
|
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: conspiracy to defraud the United States | Statement: [J. Parnell Thomas, charged with, conspiracy to defraud the United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: charged with Context triple: [J. Parnell Thomas, charged with, conspiracy to defraud the United States]
-
A.
accusedOf
Indicates that one entity has formally alleged or claimed that another entity committed a specific wrongdoing or offense.
-
B.
accusedIn
Indicates that a person or entity is formally charged with wrongdoing in a particular case, proceeding, or context.
-
C.
guiltyOf
Indicates that an entity has been judged or determined to have committed a particular offense, crime, or wrongful act.
-
D.
crimeCharged
chosen
Indicates that legal authorities have formally accused an entity of committing a specific crime.
-
E.
prosecuted
Indicates that legal authorities have formally brought criminal charges against an entity and pursued a case against them in a court of law.
- 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_69d81c67ba6c819091935650dfb3b895 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5c5aa828819098ef55a70a0decbc |
completed | April 14, 2026, 3:25 p.m. |
| PD | Predicate disambiguation | batch_69de05adef888190b023ab42ef5076b6 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:21 p.m.