Triple
T24892022
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Revised Romanization of Korean |
E623027
|
entity |
| Predicate | exampleRomanization |
P157446
|
FINISHED |
| Object | 서울 → Seoul |
—
|
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: 서울 → Seoul | Statement: [Revised Romanization of Korean, exampleRomanization, 서울 → Seoul]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exampleRomanization Context triple: [Revised Romanization of Korean, exampleRomanization, 서울 → Seoul]
-
A.
hasRomanizationOf
Indicates that one entity is a romanized representation (written in the Latin alphabet) of the other entity’s original script form.
-
B.
romanizationVariantOf
Indicates that one written form is a different romanized representation of the same underlying word or expression as another.
-
C.
romanizationType
Indicates the specific system or method used to convert text from one writing system into its Roman (Latin) alphabet representation.
-
D.
romanizationFrom
Indicates that one entity is a romanized representation derived from the script or writing system of another entity.
-
E.
laterRomanizedInto
Indicates that an entity’s original form (such as a name, word, or title) was subsequently converted into a later Romanized (Latin-script) version.
- F. None of above. chosen
Provenance (4 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_69e2fac597708190a922bf39a49ec70a |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f43043512481909501a3979cac9947 |
completed | May 1, 2026, 4:46 a.m. |
| PD | Predicate disambiguation | batch_69f420fd375c81908ea4a4e60b76ee8f |
completed | May 1, 2026, 3:41 a.m. |
| PDg | Predicate description generation | batch_69f4303fad6c8190844f069164f0904d |
completed | May 1, 2026, 4:46 a.m. |
Created at: April 18, 2026, 5:26 a.m.