Triple
T14589318
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Recorder (judge) |
E342401
|
entity |
| Predicate | maySitOn |
P65248
|
FINISHED |
| Object | appeals from magistrates’ courts (in the Crown Court) |
—
|
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: appeals from magistrates’ courts (in the Crown Court) | Statement: [Recorder (judge), maySitOn, appeals from magistrates’ courts (in the Crown Court)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maySitOn Context triple: [Recorder (judge), maySitOn, appeals from magistrates’ courts (in the Crown Court)]
-
A.
maySit
chosen
Indicates that one entity is permitted or allowed to sit on or in another entity.
-
B.
maySitWith
Indicates that one entity is permitted or allowed to sit together with another entity.
-
C.
maySitAs
Indicates that one entity is permitted or authorized to serve or participate in an official capacity within another entity (such as a body, panel, or role).
-
D.
canSitIn
Indicates that one entity is able or permitted to sit inside or occupy the seating space of another entity.
-
E.
maySitByRight
Indicates that an entity has the right or permission to sit next to 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_69d822ddc0f081909cd8163c7de298cd |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb4237d88819097f3f9a40f5be152 |
completed | April 14, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69de656a953481909a4645b004c40de7 |
completed | April 14, 2026, 4:03 p.m. |
Created at: April 10, 2026, 1:24 a.m.