Triple
T12650953
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 韓国統監 |
E302155
|
entity |
| Predicate | 支配形態 |
P35013
|
FINISHED |
| Object | 保護国体制の下での実質的支配 |
—
|
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: 保護国体制の下での実質的支配 | Statement: [韓国統監, 支配形態, 保護国体制の下での実質的支配]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 支配形態 Context triple: [韓国統監, 支配形態, 保護国体制の下での実質的支配]
-
A.
dominantForm
Indicates that one form, type, or variant is the primary or most prevalent version relative to others in a given context.
-
B.
governingForm
chosen
Indicates that one entity specifies or embodies the authoritative rules, structure, or format that control or regulate another entity.
-
C.
grammaticalForm
Indicates the specific grammatical structure or morphological form that an expression or word takes in a given linguistic context.
-
D.
dominantFormOf
Indicates that one form of something is the primary, prevailing, or most influential version relative to another form.
-
E.
grammaticalMood
Indicates the grammatical mood used in an utterance, specifying the speaker’s attitude toward the action or state (such as indicative, imperative, or subjunctive).
- 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_69d7bded71a88190bb76e2413af9ea66 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9617b07ec8190b714f04ae6654060 |
completed | April 10, 2026, 8:45 p.m. |
| PD | Predicate disambiguation | batch_69d960b78ce8819091f15dd5013e6da5 |
completed | April 10, 2026, 8:42 p.m. |
Created at: April 9, 2026, 5:18 p.m.