Triple
T25305054
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KR-48 |
E634457
|
entity |
| Predicate | localRomanizedName |
P157446
|
FINISHED |
| Object | Gyeongsangnam-do |
—
|
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: Gyeongsangnam-do | Statement: [KR-48, localRomanizedName, Gyeongsangnam-do]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: localRomanizedName Context triple: [KR-48, localRomanizedName, Gyeongsangnam-do]
-
A.
fullRomanName
Indicates that one entity is the complete Roman-style personal name (including all components) corresponding to another entity.
-
B.
exampleRomanization
chosen
Indicates that one entity is a romanized representation (in Latin script) of the other entity’s original text or name.
-
C.
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.
-
D.
hasRomanName
Indicates that an entity is associated with or known by a name derived from or used in ancient Rome.
-
E.
romanNomen
Indicates that an entity has a specific Roman nomen, i.e., the clan or gens name within the traditional Roman naming system.
- 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_69e75a972c6481909bc11710e8d30a6c |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f49399bf3881908b36a2b009be4f87 |
completed | May 1, 2026, 11:50 a.m. |
| PD | Predicate disambiguation | batch_69f4806d93dc8190b9dff4c63186faff |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 1:25 p.m.