Triple
T24467255
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nam-gu |
E617002
|
entity |
| Predicate | hasRevisedRomanizationName |
P65970
|
FINISHED |
| Object | Nam-gu |
—
|
NE NERFINISHED |
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: Nam-gu | Statement: [Nam-gu, hasRevisedRomanizationName, Nam-gu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRevisedRomanizationName Context triple: [Nam-gu, hasRevisedRomanizationName, Nam-gu]
-
A.
hasTitleInRevisedRomanization
chosen
Indicates that an entity has a specific title expressed using the Revised Romanization system for Korean.
-
B.
hasFormerRomanization
Indicates that an entity was previously written or represented using an earlier or superseded system of Romanized spelling.
-
C.
hasRomanizationOf
Indicates that one entity is a romanized representation (written in the Latin alphabet) of the other entity’s original script form.
-
D.
hasRomanizationStandard
Indicates that an entity’s romanized form follows a specified romanization standard or system.
-
E.
romanizationStandardReplacedBy
Indicates that one system or convention for romanization has been superseded and replaced by another romanization standard.
- 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_69e2d7f197588190889a03e620558059 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f299403a8c819095e31aa2dace6921 |
completed | April 29, 2026, 11:50 p.m. |
| PD | Predicate disambiguation | batch_69f287d76c7c81909494f12e606a9149 |
completed | April 29, 2026, 10:36 p.m. |
Created at: April 18, 2026, 2:20 a.m.