Triple
T9819836
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oh Jun-ho |
E238500
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | KAIST |
E153919
|
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: KAIST | Statement: [Oh Jun-ho, employer, KAIST]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KAIST Context triple: [Oh Jun-ho, employer, KAIST]
-
A.
KAIST
chosen
KAIST is a leading South Korean research university renowned for its strengths in science, engineering, and technology.
-
B.
UNIST
UNIST is a leading South Korean science and technology research university located in Ulsan, known for its strong emphasis on engineering, innovation, and interdisciplinary research.
-
C.
Korea Basic Science Institute
The Korea Basic Science Institute is a national research organization in South Korea dedicated to advancing fundamental science through state-of-the-art analytical and experimental facilities.
-
D.
Chungnam National University
Chungnam National University is a major national research university in South Korea known for its comprehensive academic programs and strong emphasis on science and technology, located in the city of Daejeon.
-
E.
Seoul National University
Seoul National University is South Korea’s premier national research university, renowned for its highly competitive admissions and leading role in the country’s higher education and academic research.
- 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_69ca84dfde1481909f47c286d715f892 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb2f74e348190be8e4394ae6fe3fe |
completed | April 2, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1d5b599f88190a8f54771c4a75e58 |
completed | April 5, 2026, 3:23 a.m. |
Created at: March 30, 2026, 8:31 p.m.