Triple
T9590191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Middle Korean |
E231395
|
entity |
| Predicate | languageCodeISO |
P36930
|
FINISHED |
| Object | okm |
—
|
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: okm | Statement: [Middle Korean, languageCodeISO, okm]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageCodeISO Context triple: [Middle Korean, languageCodeISO, okm]
-
A.
languageCodeISO639-1
Indicates that the subject entity is associated with the specified two-letter ISO 639-1 language code.
-
B.
languageCodeISO639-2
Indicates that an entity is associated with a language identified by its ISO 639-2 three-letter code.
-
C.
ISO639CollectiveCode
Indicates that the relationship assigns or associates an ISO 639 collective language code (a code representing a group of related languages) to the relevant language entity or set of languages.
-
D.
ISO639-3CodeOfLanguage
chosen
Indicates that one entity is the ISO 639-3 three-letter language code assigned to the language represented by the other entity.
-
E.
languageCodeRelation
Indicates a relationship where one entity is associated with, identified by, or mapped to a specific language code of another entity.
- 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_69ca8482884481908eccdfdf64d6fbf7 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd99f32e688190bb13bccfa5031f16 |
completed | April 1, 2026, 10:19 p.m. |
| PD | Predicate disambiguation | batch_69ccd59fd7408190b36831902e3f37f7 |
completed | April 1, 2026, 8:21 a.m. |
Created at: March 30, 2026, 8:06 p.m.