Triple
T36347918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anthony Ray Hinton |
E895115
|
entity |
| Predicate | exoneratedWithAssistanceFrom |
P185150
|
FINISHED |
| Object | Equal Justice Initiative |
—
|
NE NERFINISHED |
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: Equal Justice Initiative | Statement: [Anthony Ray Hinton, exoneratedWithAssistanceFrom, Equal Justice Initiative]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exoneratedWithAssistanceFrom Context triple: [Anthony Ray Hinton, exoneratedWithAssistanceFrom, Equal Justice Initiative]
-
A.
exoneratedIn
Indicates that an entity has been officially cleared of blame or legal responsibility in a particular case, situation, or proceeding.
-
B.
exonerationGroundsInclude
Indicates that the reasons or grounds for an exoneration include a specified factor or condition.
-
C.
wasAmnestied
Indicates that an entity was officially granted amnesty, nullifying or forgiving prior offenses or penalties.
-
D.
eventuallyParoled
Indicates that an individual who was previously incarcerated was later released from prison on parole.
-
E.
dateOfExoneration
Indicates the date on which an entity was officially cleared of blame, guilt, or conviction.
- F. None of above. chosen
Provenance (4 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_69f76e4f437c8190a1af3ea2564f41f5 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7bb3ff1b08190802b1063d55d3923 |
completed | May 3, 2026, 9:16 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a611a081908dd6aec1df3f4d7f |
completed | May 3, 2026, 9:09 p.m. |
| PDg | Predicate description generation | batch_69f7bb3f23f48190b0b9c2d667e09b52 |
completed | May 3, 2026, 9:16 p.m. |
Created at: May 3, 2026, 4:09 p.m.