Triple
T10401721
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Guardians |
E245162
|
entity |
| Predicate | centralCase |
P58780
|
FINISHED |
| Object | exoneration of a wrongfully convicted man |
—
|
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: exoneration of a wrongfully convicted man | Statement: [The Guardians, centralCase, exoneration of a wrongfully convicted man]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: centralCase Context triple: [The Guardians, centralCase, exoneration of a wrongfully convicted man]
-
A.
centralToCase
chosen
Indicates that something plays a pivotal or essential role in determining the outcome or understanding of a particular case.
-
B.
centralAppeal
Indicates that something serves as the main attraction, focus, or compelling feature that draws interest or attention.
-
C.
centralIn
Indicates that one entity occupies a central or most important position within another entity, context, or structure.
-
D.
courtCenterOf
Indicates that one entity is the central or primary location (e.g., main venue or focal point) for court-related activities of another entity.
-
E.
centralTest
Indicates that an entity serves as the primary or core test within a set of tests or an evaluation 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_69d381b5116081908d85227bab6d3c0c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9e42da08190a5383df3df6d3c18 |
completed | April 7, 2026, 11:26 a.m. |
| PD | Predicate disambiguation | batch_69d4dfb438c481908dff87c47de2f069 |
completed | April 7, 2026, 10:43 a.m. |
Created at: April 6, 2026, 12:07 p.m.