Triple
T5580004
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Korean government |
E146615
|
entity |
| Predicate | sharesUNSeatWith |
P56677
|
FINISHED |
| Object | South Korean government (separate seats) |
—
|
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: South Korean government (separate seats) | Statement: [North Korean government, sharesUNSeatWith, South Korean government (separate seats)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesUNSeatWith Context triple: [North Korean government, sharesUNSeatWith, South Korean government (separate seats)]
-
A.
shareUNMembership
chosen
Indicates that the entities are both member states of the United Nations at the same time.
-
B.
sharesSecretariatWith
Indicates that two entities are served or administered by the same secretariat or administrative office.
-
C.
joinedUNTogetherWith
Indicates that one entity became a member of or affiliated with the University of North Texas together with another entity, at the same time or as part of the same event.
-
D.
sharesSovereignWith
Indicates that two entities are under the authority of the same sovereign state or ruler.
-
E.
sharesCountryWith
Indicates that two entities are located in, originate from, or are otherwise associated with the same country.
- 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_69c0090287a08190b4098411effe970c |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c0206d62548190b8a3c6efc1825661 |
completed | March 22, 2026, 5:01 p.m. |
| PD | Predicate disambiguation | batch_69c01b147cc081909237f3f2967d4cb8 |
completed | March 22, 2026, 4:38 p.m. |
Created at: March 22, 2026, 3:37 p.m.