Triple
T23485904
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 안창호 |
E570531
|
entity |
| Predicate | 교육활동 |
P12759
|
FINISHED |
| Object | 청년 교육과 인격 수양 강조 |
—
|
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: 청년 교육과 인격 수양 강조 | Statement: [안창호, 교육활동, 청년 교육과 인격 수양 강조]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 교육활동 Context triple: [안창호, 교육활동, 청년 교육과 인격 수양 강조]
-
A.
educationalActivity
chosen
Indicates an action or relationship in which one entity engages in or provides a learning or teaching activity for another.
-
B.
schoolActivity
Indicates that an entity participates in, organizes, or is otherwise involved in an activity associated with a school or educational setting.
-
C.
educationalSector
Indicates a relationship in which something is part of, associated with, or operates within the education or schooling domain.
-
D.
educationSystem
Indicates the relationship in which an entity is part of, governed by, or operates within a particular system or structure of education.
-
E.
educationalApostolateIncludes
Indicates that a broader educational apostolate encompasses or contains a particular educational activity, program, or initiative as one of its components.
- 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.