Triple
T3747853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 대한민국 해병대 |
E81249
|
entity |
| Predicate | hasRecruitType |
P51087
|
FINISHED |
| Object | 징병제 병사 |
—
|
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: 징병제 병사 | Statement: [대한민국 해병대, hasRecruitType, 징병제 병사]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRecruitType Context triple: [대한민국 해병대, hasRecruitType, 징병제 병사]
-
A.
hasWorkforceType
Indicates the type or category of workforce associated with an entity (such as permanent, temporary, contract, or part-time).
-
B.
recruitedAs
Indicates that one entity has been brought into a role, position, or organization by another through a recruitment process.
-
C.
recruitsFor
Indicates that one entity actively seeks out, enlists, or brings in participants, members, or resources on behalf of another entity, such as an organization, event, or cause.
-
D.
hasCadetType
Indicates that an entity is associated with or classified under a specific type or category of cadet.
-
E.
isRecruitableCharacter
Indicates that a character can be obtained and added to the player’s controllable roster or party.
- F. None of above. chosen
Provenance (4 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_69ad8b19b7b08190a6188804e99c53e9 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcb6ac5ac8190934ec1a6c887a8f5 |
completed | March 8, 2026, 7:18 p.m. |
| PD | Predicate disambiguation | batch_69adc04adebc819088d7f36d0ac343a6 |
completed | March 8, 2026, 6:30 p.m. |
| PDg | Predicate description generation | batch_69adc1560c248190b07438d766880990 |
completed | March 8, 2026, 6:35 p.m. |
Created at: March 8, 2026, 3:35 p.m.