Triple
T1979463
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Team KAIST |
E42990
|
entity |
| Predicate | leader |
P981
|
FINISHED |
| Object | Jun-Ho Oh |
E223655
|
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: Jun-Ho Oh | Statement: [Team KAIST, leader, Jun-Ho Oh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jun-Ho Oh Context triple: [Team KAIST, leader, Jun-Ho Oh]
-
A.
Jun-Ho Oh
chosen
Jun-Ho Oh is a South Korean roboticist best known for leading the development of the humanoid robot DRC-HUBO that won the DARPA Robotics Challenge.
-
B.
Do Ho Suh
Do Ho Suh is a South Korean contemporary artist known for his intricate sculptures and installations that explore themes of home, memory, and personal space.
-
C.
Dongjin Seo
Dongjin Seo is a neuroscientist and engineer known as one of the co-founders of the brain–computer interface company Neuralink.
-
D.
Cho Sang-woo
Cho Sang-woo is a central character in the South Korean series "Squid Game," portrayed as a once-successful investment banker whose desperation and moral decline drive much of the show's tension and drama.
-
E.
Lee Hak-rae
Lee Hak-rae is a South Korean sports official best known for delivering the judges' oath at the 1988 Seoul Summer Olympics.
- 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_69a8871289048190b00b0d7744b7b2b1 |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb7c698748190a10da0901952df07 |
completed | March 7, 2026, 5:29 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae0ad2a3888190a93e54b53a071afc |
completed | March 8, 2026, 11:48 p.m. |
Created at: March 4, 2026, 7:36 p.m.