Triple
T9324918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | High Council of the Judiciary |
E224361
|
entity |
| Predicate | appointmentPowerOver |
P87523
|
FINISHED |
| Object | ordinary 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: ordinary judges | Statement: [High Council of the Judiciary, appointmentPowerOver, ordinary judges]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appointmentPowerOver Context triple: [High Council of the Judiciary, appointmentPowerOver, ordinary judges]
-
A.
appointmentTerm
Indicates the duration or specific period for which an appointment, position, or role is held.
-
B.
appointmentBy
Indicates that one entity is appointed or designated to a role, position, or task by another entity.
-
C.
appointmentBody
Indicates that one entity serves as the main content or body text associated with a particular appointment.
-
D.
officeEnded
Indicates that a person’s term in an office or position has concluded at a specified time or under certain conditions.
-
E.
afterOfficeActivity
Indicates that one entity engages in an activity that takes place after regular office or work hours.
- 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_69ca8426d48481909596360f7791c7dd |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd36f77c808190aa5489c4305fd67d |
completed | April 1, 2026, 3:17 p.m. |
| PD | Predicate disambiguation | batch_69cc7a643924819097f01144734901cf |
completed | April 1, 2026, 1:52 a.m. |
| PDg | Predicate description generation | batch_69cc94b796788190816b71b1e9996288 |
completed | April 1, 2026, 3:44 a.m. |
Created at: March 30, 2026, 7:38 p.m.