Triple
T37260239
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Africa–South Korea relations |
E924237
|
entity |
| Predicate | involvesSouthKoreanCompanies |
P155400
|
FINISHED |
| Object | Hyundai Motor Company |
—
|
NE NERFINISHED |
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: Hyundai Motor Company | Statement: [South Africa–South Korea relations, involvesSouthKoreanCompanies, Hyundai Motor Company]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: involvesSouthKoreanCompanies Context triple: [South Africa–South Korea relations, involvesSouthKoreanCompanies, Hyundai Motor Company]
-
A.
includesCompaniesInvolvedIn
chosen
Indicates that something encompasses or lists the companies that are involved in a particular context, activity, or transaction.
-
B.
SouthKoreaProvides
Indicates that South Korea supplies, grants, or makes available some resource, service, or support to another entity.
-
C.
SouthKoreaIs
Indicates that something has the status, identity, or characteristic of being South Korea.
-
D.
involvesBusiness
Indicates that an action, event, or relationship includes participation or engagement by a business entity.
-
E.
impactOnSouthKorea
Indicates the effect, influence, or consequences that something has on South Korea.
- 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_69f76eabd6c481909d414a80a1345c98 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fe920a437081908d5174e8cf7a53a6 |
completed | May 9, 2026, 1:46 a.m. |
| PD | Predicate disambiguation | batch_69fe919a9a6c8190acb4483f386e6db7 |
completed | May 9, 2026, 1:44 a.m. |
Created at: May 3, 2026, 4:15 p.m.