Triple
T23485906
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 안창호 |
E570531
|
entity |
| Predicate | 평가 |
P8710
|
FINISHED |
| Object | 대한민국 건국 이념 형성에 기여한 인물 |
—
|
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: 대한민국 건국 이념 형성에 기여한 인물 | Statement: [안창호, 평가, 대한민국 건국 이념 형성에 기여한 인물]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 평가 Context triple: [안창호, 평가, 대한민국 건국 이념 형성에 기여한 인물]
-
A.
rating
chosen
Indicates an evaluation relationship where one entity assigns a qualitative or quantitative score or judgment to another entity.
-
B.
ratingContext
Indicates the situational or contextual factors under which a rating is given or applies.
-
C.
evaluationModel
Indicates a relationship where one entity serves as a model, standard, or framework used to assess, judge, or measure the performance or quality of another entity.
-
D.
evaluationAspect
Indicates the specific dimension or criterion of performance or quality that is being assessed within an evaluation.
-
E.
reviewScale
Indicates the rating system or range (such as 1–5 stars, 0–10, etc.) used to evaluate or score something in a review.
- 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_69e245b0b01481908f636939bedd804c |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a7538a8c8190b7effcc39a3f9787 |
completed | April 29, 2026, 6:38 a.m. |
| PD | Predicate disambiguation | batch_69f0620ac3608190b36916261ea50f54 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 6:03 p.m.