Triple
T5813000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Park Hae-soo |
E128914
|
entity |
| Predicate | koreanAgeSystemNote |
P66474
|
FINISHED |
| Object | often reported as being one year older in Korean age system |
—
|
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: often reported as being one year older in Korean age system | Statement: [Park Hae-soo, koreanAgeSystemNote, often reported as being one year older in Korean age system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: koreanAgeSystemNote Context triple: [Park Hae-soo, koreanAgeSystemNote, often reported as being one year older in Korean age system]
-
A.
hasJapaneseEraBirthYear
Indicates that an entity’s birth year is specified according to the Japanese era (gengō) calendar system.
-
B.
timeInChineseEraSystem
Indicates that a temporal reference is expressed using a specific Chinese era-based calendrical system (such as reign titles or traditional era names).
-
C.
nameInKorean
Indicates that an entity’s name is expressed in the Korean language.
-
D.
hasJapaneseEraDeathYear
Indicates that an entity’s year of death is specified according to the Japanese era (nengō) calendar system.
-
E.
currentOffsetInSouthKoreaSince
Indicates the time offset currently in effect in South Korea, measured relative to a given reference time since a specified starting point.
- 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_69c0084788848190bcf71f6bc5d71597 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c02b56044c8190847478a342d441c2 |
completed | March 22, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69c021d5ecd081908a62dd66e26f8598 |
completed | March 22, 2026, 5:07 p.m. |
| PDg | Predicate description generation | batch_69c028ffe180819099e084fe557e789c |
completed | March 22, 2026, 5:38 p.m. |
Created at: March 22, 2026, 3:52 p.m.