Triple
T23645989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Democratic Party of Korea |
E584033
|
entity |
| Predicate | producedPrimeMinisterOfSouthKorea |
P10631
|
FINISHED |
| Object | Kim Boo-kyum |
—
|
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: Kim Boo-kyum | Statement: [Democratic Party of Korea, producedPrimeMinisterOfSouthKorea, Kim Boo-kyum]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: producedPrimeMinisterOfSouthKorea Context triple: [Democratic Party of Korea, producedPrimeMinisterOfSouthKorea, Kim Boo-kyum]
-
A.
SouthKoreanPresidentAtTime
Indicates that a person holds the office of President of South Korea during a specified time period.
-
B.
successorAsMayorOfSeoul
Indicates that one person became the next mayor of Seoul following another person in office.
-
C.
producedPrimeMinister
chosen
Indicates that one entity (typically a place, institution, or group) has been the origin or source of an individual who became a prime minister.
-
D.
producedHeadOfGovernment
Indicates that an entity (such as an election, process, or event) resulted in or brought into office a specific head of government.
-
E.
NorthKoreanLeaderAtTime
Indicates that a specified person is the leader of North Korea during a given time period.
- 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_69e248fefafc81909656921192f30e80 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b28571bc8190b3f7275068d19320 |
completed | April 29, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69f118d7903c8190bb590a71771e93af |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:48 p.m.