Triple
T15834198
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coupang, Inc. |
E383944
|
entity |
| Predicate | founder |
P104
|
FINISHED |
| Object | Bom Kim |
E383943
|
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: Bom Kim | Statement: [Coupang, Inc., founder, Bom Kim]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bom Kim Context triple: [Coupang, Inc., founder, Bom Kim]
-
A.
Bom Kim
chosen
Bom Kim is a Korean-American entrepreneur best known as the founder and CEO of Coupang, one of South Korea’s largest e-commerce companies.
-
B.
Chin-kim
Chin-kim, also known as Zhenjin, was a Yuan dynasty imperial prince and the designated heir of Kublai Khan in 13th-century Mongolia-China.
-
C.
Pil-dong
Pil-dong is a neighborhood in central Seoul, South Korea, known for its mix of traditional sites, educational institutions, and urban residential areas.
-
D.
Koh Bong-joon
Koh Bong-joon is a Korean individual notable enough to be recognized as a prominent bearer of the surname Koh.
-
E.
Dong Maeng
Dong Maeng is a joint South Korea–United States military exercise that succeeded earlier large-scale drills as part of their combined defense posture.
- 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_69d86da34c888190976e06c4019d415a |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e11e6670d48190a456581dd951f168 |
completed | April 16, 2026, 5:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffa93be478819099908e7242f532d7 |
completed | May 9, 2026, 9:38 p.m. |
Created at: April 10, 2026, 4:49 a.m.