Triple
T32596503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jean-Marie Bastien-Thiry |
E833223
|
entity |
| Predicate | pardonRequestedBy |
P113203
|
FINISHED |
| Object | various public figures and clergy |
—
|
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: various public figures and clergy | Statement: [Jean-Marie Bastien-Thiry, pardonRequestedBy, various public figures and clergy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pardonRequestedBy Context triple: [Jean-Marie Bastien-Thiry, pardonRequestedBy, various public figures and clergy]
-
A.
pardonStatus
Indicates whether an entity has been officially forgiven or exempted from penalties for a prior offense or violation.
-
B.
pardonReason
Indicates the reason or justification for which a pardon is granted.
-
C.
pardonReceivedFrom
Indicates that one entity has been officially forgiven or had penalties removed by another authority or individual.
-
D.
pardonDate
Indicates the date on which an official pardon for an offense is granted or takes effect.
-
E.
soughtPardonFor
chosen
Indicates that one entity requested or attempted to obtain a formal pardon or forgiveness for another entity or for a specific action.
- 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_69f3492ab63c8190aec24d5003b47c29 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c695d31c8190bbd496755c70c81a |
completed | May 3, 2026, 3:52 a.m. |
| PD | Predicate disambiguation | batch_69f6bd2c138481908afa3ee3e91f8900 |
completed | May 3, 2026, 3:12 a.m. |
Created at: May 1, 2026, 1:05 a.m.