Triple
T26775957
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gary Duncan |
E670119
|
entity |
| Predicate | wasConvictedIn |
P90191
|
FINISHED |
| Object | Louisiana state court |
—
|
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: Louisiana state court | Statement: [Gary Duncan, wasConvictedIn, Louisiana state court]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasConvictedIn Context triple: [Gary Duncan, wasConvictedIn, Louisiana state court]
-
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.
convictedBy
Indicates that an authority, typically a court or judge, has formally found an entity guilty of a crime or offense.
-
C.
hasHadCriminalConviction
chosen
Indicates that an entity has previously been found guilty of a criminal offense through a legal process.
-
D.
convictedIndividual
Indicates that an individual has been found guilty of a crime or offense through a formal legal process and has received a conviction.
-
E.
someMembersConvictedOf
Indicates that within a group or organization, at least one member has been found guilty of a crime or offense through a formal legal or disciplinary process.
- 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_69eeb31c925881909b597f6e40056d28 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f6193294948190adeecbad17283103 |
completed | May 2, 2026, 3:33 p.m. |
| PD | Predicate disambiguation | batch_69f611ad2eb48190ac1ed0090f13f7a9 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 4:04 a.m.