Triple
T1068378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark Felt |
E23266
|
entity |
| Predicate | chargeOrConviction |
P1779
|
FINISHED |
| Object | unauthorized disclosure of FBI information |
—
|
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: unauthorized disclosure of FBI information | Statement: [Mark Felt, chargeOrConviction, unauthorized disclosure of FBI information]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chargeOrConviction Context triple: [Mark Felt, chargeOrConviction, unauthorized disclosure of FBI information]
-
A.
convictedOf
Indicates that a person or entity has been found guilty of committing a specified offense or crime through a formal legal process.
-
B.
legalCharge
chosen
Indicates that an authority has formally accused an entity of committing a specific legal offense or violation.
-
C.
numberOfConvictions
Indicates the count of times an entity has been formally found guilty of an offense.
-
D.
accusedOf
Indicates that one entity has formally alleged or claimed that another entity committed a specific wrongdoing or offense.
-
E.
charge
Indicates that one entity formally accuses another of an offense or imposes a financial cost or obligation on them.
- 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_69a493ee1f908190992b5f0d1b04459b |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b9e1047481909af1cf8df2a01fff |
completed | March 1, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69a4b736f1e881909bace735b38c0ade |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:42 p.m.