Triple
T23485911
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 안창호 |
E570531
|
entity |
| Predicate | 관련지명 |
P122228
|
FINISHED |
| Object | 도산대로 명명 |
—
|
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: 도산대로 명명 | Statement: [안창호, 관련지명, 도산대로 명명]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 관련지명 Context triple: [안창호, 관련지명, 도산대로 명명]
-
A.
hasToponymicAssociation
chosen
Indicates a relationship where one entity is associated with, derived from, or named after a particular place or geographic name (toponym).
-
B.
typicalGeographicalAssociation
Indicates a usual or characteristic geographical connection between entities, such as a place commonly associated with a person, group, or phenomenon.
-
C.
regionNamedAfter
Indicates that a geographic region derives its name from a specific person, place, event, or other entity.
-
D.
relatedPlace
Indicates a relationship where one place is connected or associated with another place in a relevant or meaningful way.
-
E.
fictionalLocationAssociatedWith
Indicates a relationship where a fictional entity (such as a character, event, or work) is connected to or set in a particular fictional location.
- 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.