Triple
T18952086
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rubbing/Loving |
E463679
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object | Do Ho Suh |
—
|
NE NERFINISHED |
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: Do Ho Suh | Statement: [Rubbing/Loving, creator, Do Ho Suh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Do Ho Suh Context triple: [Rubbing/Loving, creator, Do Ho Suh]
-
A.
Do Ho Suh
chosen
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.
-
B.
Yong-taek Jung
Yong-taek Jung is a notable individual recognized for bearing the Korean surname Jung.
-
C.
Sang-ok Shin
Sang-ok Shin was a South Korean film director known for his prolific career in Korean cinema and for having been abducted to North Korea in the 1970s to make films for the regime.
-
D.
Honglak Lee
Honglak Lee is a computer scientist and researcher known for his contributions to deep learning and representation learning, particularly in unsupervised feature learning.
-
E.
Bong Soo Han
Bong Soo Han was a renowned Korean martial artist and hapkido master who also worked as a stunt coordinator and actor in American films.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dcffc278819086792a4ebfddfafa |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d54385e08190903a054681352d11 |
completed | April 20, 2026, 7:26 a.m. |
Created at: April 10, 2026, noon