Triple
T22225501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sergeant Gerry Boyle |
E549326
|
entity |
| Predicate | alignmentWithLaw |
P147359
|
FINISHED |
| Object | bends rules but pursues justice |
—
|
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: bends rules but pursues justice | Statement: [Sergeant Gerry Boyle, alignmentWithLaw, bends rules but pursues justice]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alignmentWithLaw Context triple: [Sergeant Gerry Boyle, alignmentWithLaw, bends rules but pursues justice]
-
A.
alignedAgainst
Indicates that two or more entities are united in opposition to a common target, side, or objective.
-
B.
alignedWithPrinciple
Indicates that an entity’s behavior, decision, or state is consistent with and adheres to a specified principle or set of principles.
-
C.
linkedLaw
Indicates that there is a connection or reference between an entity and a specific law or legal provision.
-
D.
positionOnLaw
Indicates a stance, opinion, or interpretation that an entity holds regarding a specific law or legal provision.
-
E.
policyAlignment
Indicates the degree to which one entity’s policies are consistent with, supportive of, or in agreement with those of another entity.
- 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_69e11e403d6481909a94d0aaf157f6ef |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12bee8de8819091ec5d14ea057f9e |
completed | April 28, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69e71b4dcc408190a30429fb08fcf39e |
completed | April 21, 2026, 6:38 a.m. |
| PDg | Predicate description generation | batch_69e723f65c5c8190a0ee3c539e5d0767 |
completed | April 21, 2026, 7:15 a.m. |
Created at: April 16, 2026, 8:37 p.m.