Triple
T6409427
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Korean political system |
E127666
|
entity |
| Predicate | partyCongress |
P70477
|
FINISHED |
| Object | highest party meeting |
—
|
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: highest party meeting | Statement: [North Korean political system, partyCongress, highest party meeting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partyCongress Context triple: [North Korean political system, partyCongress, highest party meeting]
-
A.
oppositionPartyInCongress
Indicates that a political party serves as the primary opposing party to the ruling or majority party within a specific congress or legislative body.
-
B.
lastCongress
Indicates that one entity is the most recent (or final) congress associated with, or held by, another entity.
-
C.
congressionalNumber
Indicates the specific numbered session or term of a legislative congress to which an entity is associated.
-
D.
houseMinorityParty
Indicates that the referenced political party is the minority party in a legislative house, having fewer seats than the majority party.
-
E.
parliamentaryHouse
Indicates that one entity functions as a parliamentary chamber or house within the legislative system of another entity.
- 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_69c0083723d88190b1e37b19df162c08 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c068cdf25881908d42a5d979637ad6 |
completed | March 22, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69c060f40ecc8190b1df17b96767675c |
completed | March 22, 2026, 9:36 p.m. |
| PDg | Predicate description generation | batch_69c0623d23448190a75cf5d802fc0a02 |
completed | March 22, 2026, 9:42 p.m. |
Created at: March 22, 2026, 4:41 p.m.