Triple
T34482939
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 박근혜 |
E885237
|
entity |
| Predicate | 형사재판관련 |
P11477
|
FINISHED |
| Object | 국정농단 사건으로 유죄 판결 |
—
|
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: 국정농단 사건으로 유죄 판결 | Statement: [박근혜, 형사재판관련, 국정농단 사건으로 유죄 판결]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 형사재판관련 Context triple: [박근혜, 형사재판관련, 국정농단 사건으로 유죄 판결]
-
A.
isRelatedCriminalMatterOf
Indicates that one legal case or issue is connected to, arises from, or is otherwise associated with another in a criminal context.
-
B.
haveCriminalLaw
Indicates that an entity possesses, applies, or is governed by a system or body of criminal law.
-
C.
hasCriminalProcedureBasedOn
Indicates that one legal system’s criminal procedure is derived from, modeled on, or fundamentally influenced by another specified source or framework.
-
D.
crimeType
Indicates the specific category or nature of the crime associated with an event or entity.
-
E.
subjectOfProsecution
chosen
Indicates that an entity is the target or focus of a legal prosecution or criminal proceeding initiated by an authority.
- 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_69f349c947fc81909d30b53c194d6ea1 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71fb1ab3881908e2f7c0e6f23db49 |
completed | May 3, 2026, 10:13 a.m. |
| PD | Predicate disambiguation | batch_69f71cc6397881909aaad37a9daa8a7e |
completed | May 3, 2026, 10 a.m. |
Created at: May 1, 2026, 2:01 a.m.