Triple
T10731006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yoo Soon-taek |
E253072
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Ban Woo-hyun |
E253072
|
NE 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: Ban Woo-hyun | Statement: [Yoo Soon-taek, child, Ban Woo-hyun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ban Woo-hyun Context triple: [Yoo Soon-taek, child, Ban Woo-hyun]
-
A.
Ban Woo-hyun
chosen
Ban Woo-hyun is one of the children of former UN Secretary-General Ban Ki-moon and his wife Yoo Soon-taek.
-
B.
Kim Swoo Geun
Kim Swoo Geun was a prominent South Korean architect renowned for pioneering modern Korean architecture and shaping Seoul’s urban landscape in the mid-20th century.
-
C.
Kim Je-hyuk
Kim Je-hyuk is the naive yet kindhearted star baseball player who becomes an unlikely inmate protagonist in the South Korean television drama "Prison Playbook."
-
D.
Yoon Je-moon
Yoon Je-moon is a South Korean actor known for his versatile performances in both critically acclaimed films and television dramas.
-
E.
Lee Dong-hwi
Lee Dong-hwi is a South Korean actor known for his roles in popular films and television dramas, including the hit series "Reply 1988."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aa5d8be481909a43218b2bfdbe95 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d70fcb1cd881909635def59ad5d19c |
completed | April 9, 2026, 2:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de84932abc8190907c32720e35442e |
completed | April 14, 2026, 6:16 p.m. |
Created at: April 8, 2026, 9:14 p.m.