Triple
T7785436
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gim Man-il |
E187229
|
entity |
| Predicate | hasNameRomanizationSystemVariant |
P23170
|
FINISHED |
| Object | older Korean romanization systems |
—
|
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: older Korean romanization systems | Statement: [Gim Man-il, hasNameRomanizationSystemVariant, older Korean romanization systems]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNameRomanizationSystemVariant Context triple: [Gim Man-il, hasNameRomanizationSystemVariant, older Korean romanization systems]
-
A.
hasRomanizationOf
Indicates that one entity is a romanized representation (written in the Latin alphabet) of the other entity’s original script form.
-
B.
hasRomanizationStandard
chosen
Indicates that an entity’s romanized form follows a specified romanization standard or system.
-
C.
hasOfficialNameVariant
Indicates that an entity has an alternative official form or version of its name.
-
D.
hasHakkaRomanization
Indicates that an entity is associated with a specific representation of its name or term in Hakka Romanization.
-
E.
hasLatinizedName
Indicates that an entity is associated with a version of its name that has been converted into Latin form or spelling.
- 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_69ca82af2d2c8190963861f5e0b8bf21 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cae7e779ec8190b77296d9c2ac3210 |
completed | March 30, 2026, 9:15 p.m. |
| PD | Predicate disambiguation | batch_69caa488532c819093ac40bba0b3c7ef |
completed | March 30, 2026, 4:27 p.m. |
Created at: March 30, 2026, 4:23 p.m.