Triple
T26222151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | High Court judge of England and Wales |
E655791
|
entity |
| Predicate | securityOfTenure |
P165028
|
FINISHED |
| Object | holds office during good behaviour |
—
|
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: holds office during good behaviour | Statement: [High Court judge of England and Wales, securityOfTenure, holds office during good behaviour]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: securityOfTenure Context triple: [High Court judge of England and Wales, securityOfTenure, holds office during good behaviour]
-
A.
landTenure
Indicates the type, conditions, or rights under which land is held, used, or owned by an entity.
-
B.
seaTenureSystem
Indicates a system governing rights, access, and control over the use and management of marine or sea areas.
-
C.
propertyHeld
Indicates that a particular property is possessed, owned, or controlled by a specified entity.
-
D.
estateTitleOf
Indicates that one entity holds or is associated with the legal title or ownership interest in a particular estate or property of another entity.
-
E.
estateLinkedToTitle
Indicates that a particular estate is legally or formally associated with a specific title.
- 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_69ee5b4a77e08190bfcb5f8ecdc55abd |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f65705a3048190a3728b695ba2ae65 |
completed | May 2, 2026, 7:56 p.m. |
| PD | Predicate disambiguation | batch_69f651a731508190bb0c8c2462eba224 |
completed | May 2, 2026, 7:33 p.m. |
| PDg | Predicate description generation | batch_69f6562ef4e4819082ce6abd41b74dc5 |
completed | May 2, 2026, 7:53 p.m. |
Created at: April 26, 2026, 8:56 p.m.