Triple
T26535815
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chinju |
E671240
|
entity |
| Predicate | KoreanNameRevisedRomanization |
P105016
|
FINISHED |
| Object | Jinju-si |
—
|
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: Jinju-si | Statement: [Chinju, KoreanNameRevisedRomanization, Jinju-si]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: KoreanNameRevisedRomanization Context triple: [Chinju, KoreanNameRevisedRomanization, Jinju-si]
-
A.
hangulNameRomanized
chosen
Indicates that an entity’s Korean Hangul name is represented in its romanized (Latin alphabet) form.
-
B.
languageOfKoreanName
Indicates that the specified language is the language in which the given Korean name is expressed or written.
-
C.
nameInMcCuneReischauer
Indicates that an entity’s name is represented using the McCune–Reischauer romanization system.
-
D.
hanjaName
Indicates that one entity is the Sino-Korean (hanja) written form corresponding to the name 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.
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_69eeb3206e748190b90c85cc81f38c91 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f613fb435c8190b586d8a73880f673 |
completed | May 2, 2026, 3:10 p.m. |
| PD | Predicate disambiguation | batch_69f602d7b1b0819095ddd3b5169f8ce2 |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 27, 2026, 1:38 a.m.