Triple
T19116714
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Korean local elections |
E467924
|
entity |
| Predicate | firstMajorReformYear |
P50931
|
FINISHED |
| Object | 1995 |
—
|
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: 1995 | Statement: [South Korean local elections, firstMajorReformYear, 1995]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstMajorReformYear Context triple: [South Korean local elections, firstMajorReformYear, 1995]
-
A.
timeOfMajorReforms
chosen
Indicates the specific time period during which significant reforms or major changes took place.
-
B.
lastReform
Indicates the most recent reform or change that was applied to an entity, typically linking the entity to its latest reform event or version.
-
C.
modernizationStartDate
Indicates the date on which a modernization process or upgrade for the entity was initiated.
-
D.
majorAmendmentYear
Indicates the year in which a significant or major amendment was made to something (such as a document, law, or agreement).
-
E.
yearOfGovernmentChange
Indicates the specific year in which a government was replaced, overthrown, or otherwise changed.
- 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.