Triple
T27658640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Magistrate Division |
E697058
|
entity |
| Predicate | reviewOfDecisions |
P13083
|
FINISHED |
| Object | subject to appeal to Regular Division judges |
—
|
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: subject to appeal to Regular Division judges | Statement: [Magistrate Division, reviewOfDecisions, subject to appeal to Regular Division judges]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reviewOfDecisions Context triple: [Magistrate Division, reviewOfDecisions, subject to appeal to Regular Division judges]
-
A.
reviewsDecisionsFrom
chosen
Indicates that one entity examines and evaluates the decisions made by another entity.
-
B.
reportsDecisionsOf
Indicates that one entity communicates or provides information about the decisions made by another entity.
-
C.
decisionTypeReviewed
Indicates that a particular decision has been examined or evaluated, typically as part of a review or oversight process.
-
D.
decisionsAre
Indicates that certain choices, judgments, or resolutions possess a specified quality, status, or classification.
-
E.
documentsDecisionsOn
Indicates that one entity records, details, or formally captures the decisions made about 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_69ef590b85a4819083ec7c12bd3c9c10 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f6359e3d3c81909814e2f0a7fb0ea9 |
completed | May 2, 2026, 5:34 p.m. |
| PD | Predicate disambiguation | batch_69f631871c888190bf29466fe4254e51 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 27, 2026, 2:35 p.m.