Triple
T23485909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 안창호 |
E570531
|
entity |
| Predicate | 관련기념물 |
P45155
|
FINISHED |
| Object | 도산공원 안장 |
—
|
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: 도산공원 안장 | Statement: [안창호, 관련기념물, 도산공원 안장]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 관련기념물 Context triple: [안창호, 관련기념물, 도산공원 안장]
-
A.
relatedMemorial
chosen
Indicates a relationship where one entity serves as a memorial or commemorative reference to another entity.
-
B.
otherMonuments
Indicates that there exists a relationship between an entity and additional monuments that are associated with or related to it in some relevant way.
-
C.
relatedMemorialElement
Indicates that one memorial element is associated with, connected to, or commemoratively linked to another memorial element.
-
D.
memorialSiteFor
Indicates that a place or structure serves as a dedicated site of remembrance or commemoration for a particular person, group, or event.
-
E.
commemorativeRelation
Indicates a relationship where one entity serves to honor, remember, or memorialize another entity, event, or person.
- 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.