Triple
T275612
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Supreme Judicial Court |
E5241
|
entity |
| Predicate | typeOfReview |
P3850
|
FINISHED |
| Object | appellate review |
—
|
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: appellate review | Statement: [Supreme Judicial Court, typeOfReview, appellate review]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfReview Context triple: [Supreme Judicial Court, typeOfReview, appellate review]
-
A.
reviewedBy
Indicates that an item, work, or action has been examined and evaluated by a specific agent or reviewer.
-
B.
peerReview
Indicates that one entity evaluates, critiques, or validates the work or performance of another entity, typically as an equal in expertise or status.
-
C.
standardOfReview
chosen
Indicates the level and type of scrutiny an authority (such as a court or reviewer) applies when evaluating a prior decision, action, or finding.
-
D.
typeOfSupport
Indicates the kind or category of assistance, help, or backing provided in a given context.
-
E.
opinionBy
Indicates that a particular opinion, viewpoint, or judgment is expressed or held by a specific 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_69a257e6c8788190987dfe705ca2912a |
completed | Feb. 28, 2026, 2:50 a.m. |
| NER | Named-entity recognition | batch_69a25dd1cdf881909c2c9b77b7f88684 |
completed | Feb. 28, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_69a25b7480e881909399beccfc7ffb81 |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 2:59 a.m.