Triple
T31665123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hyangchal |
E808103
|
entity |
| Predicate | scriptUsageMethod |
P45018
|
FINISHED |
| Object | phonetic transcription of Korean syllables |
—
|
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: phonetic transcription of Korean syllables | Statement: [Hyangchal, scriptUsageMethod, phonetic transcription of Korean syllables]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scriptUsageMethod Context triple: [Hyangchal, scriptUsageMethod, phonetic transcription of Korean syllables]
-
A.
scriptUsageChange
Indicates a change in how a script is used, such as modifications to its invocation, parameters, frequency, or execution context over time.
-
B.
sampleUsage
Indicates that an entity is used as an example or illustration to demonstrate how something works or is applied.
-
C.
scriptUsagePeriod
Indicates the time span during which a particular script is or was actively used or valid.
-
D.
hasScriptUsage
chosen
Indicates that one entity uses, employs, or is written in the script or writing system specified by another entity.
-
E.
usagePattern
Indicates how something is typically used or the recurring manner in which it is employed or consumed.
- 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_69f348dbeef4819080b446a7feb6340b |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f78c61ed4c8190ad84c918fa9af55a |
completed | May 3, 2026, 5:56 p.m. |
| PD | Predicate disambiguation | batch_69f78b8cb3a881909ebaac1b503988c2 |
completed | May 3, 2026, 5:53 p.m. |
Created at: April 30, 2026, 10:59 p.m.