Triple
T19116588
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saenuri Party |
E467921
|
entity |
| Predicate | stanceOnSecurity |
P89137
|
FINISHED |
| Object | alliance with the United States |
—
|
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: alliance with the United States | Statement: [Saenuri Party, stanceOnSecurity, alliance with the United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stanceOnSecurity Context triple: [Saenuri Party, stanceOnSecurity, alliance with the United States]
-
A.
positionOnSecurity
chosen
Indicates the stance, opinion, or policy an entity holds regarding security-related issues or measures.
-
B.
stanceOnAuthority
Indicates an entity’s attitude, position, or level of support or opposition toward authority or authoritative control.
-
C.
stanceTowardGovernment
Indicates the attitude, position, or level of support or opposition that an entity holds toward a government.
-
D.
relatedSecurity
Indicates that one security has a defined relationship or association with another security, such as dependency, linkage, or relevance.
-
E.
stanceOnProofs
Indicates the position or attitude an entity holds regarding the use, value, or nature of proofs.
- 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_69d8dd06a26481908039e2a1bae8c597 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e3984bf48190818fa2b01b75decb |
completed | April 20, 2026, 8:28 a.m. |
| PD | Predicate disambiguation | batch_69e4b9b085288190b974d649e12e0844 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:05 p.m.