Triple
T25563187
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NATO |
E640768
|
entity |
| Predicate | hasGlobalPartner |
P8946
|
FINISHED |
| Object | South Korea |
—
|
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: South Korea | Statement: [NATO, hasGlobalPartner, South Korea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGlobalPartner Context triple: [NATO, hasGlobalPartner, South Korea]
-
A.
hasPartner
Indicates that one entity is in a partner relationship (such as romantic, life, or business partnership) with another entity.
-
B.
hasNetworkPartner
chosen
Indicates that an entity is connected to another entity through a formal or recognized network partnership relationship.
-
C.
hasPartnerOrganization
Indicates that an entity is formally associated or collaborates with another entity as a partner organization.
-
D.
hasExternalPartner
Indicates that an entity is engaged in a relationship, collaboration, or interaction with a partner organization or individual outside its own structure or system.
-
E.
hasCityPartner
Indicates that two cities are formally linked through a partnership, such as a sister-city or twinning relationship.
- 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_69e75dc1beb08190bac7d76b8d6e7bc4 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f606c79ad081908369605f72e65ca6 |
completed | May 2, 2026, 2:14 p.m. |
| PD | Predicate disambiguation | batch_69f602ce79ec8190b8336c2b9de18ac7 |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 21, 2026, 3:47 p.m.