Triple
T32696976
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Juror 2 |
E836035
|
entity |
| Predicate | laterSupportsVerdict |
P146791
|
FINISHED |
| Object | not guilty |
—
|
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: not guilty | Statement: [Juror 2, laterSupportsVerdict, not guilty]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterSupportsVerdict Context triple: [Juror 2, laterSupportsVerdict, not guilty]
-
A.
laterSupportsClaimOf
Indicates that one statement or piece of evidence, appearing later in time or sequence, provides support for the validity or truth of an earlier claim.
-
B.
supportsDecisionOf
chosen
Indicates that one entity endorses, backs, or agrees with the decision made by another entity.
-
C.
supportsDecisionAPI
Indicates that one entity provides or enables a decision-making API service for another entity.
-
D.
supportsSince
Indicates that one entity has been providing support to another entity starting from a specific point in time and continuing thereafter.
-
E.
laterVersionsCapability
Indicates that one entity has the capability to support, handle, or be compatible with later versions of another entity.
- 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_69f3493323288190a4e88251035fe96e |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69ffa9677be08190852c8ef6c2545fed |
completed | May 9, 2026, 9:38 p.m. |
| PD | Predicate disambiguation | batch_69ffa6570e2c8190a9d7b37f12b91d9a |
completed | May 9, 2026, 9:25 p.m. |
Created at: May 1, 2026, 1:10 a.m.