Triple
T4449974
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sansei |
E96382
|
entity |
| Predicate | sharesAncestryWith |
P3438
|
FINISHED |
| Object | Yonsei |
E99070
|
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: Yonsei | Statement: [Sansei, sharesAncestryWith, Yonsei]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yonsei Context triple: [Sansei, sharesAncestryWith, Yonsei]
-
A.
Yonsei
chosen
Yonsei are fourth-generation Japanese Americans, typically the great-grandchildren of Japanese immigrants to the United States.
-
B.
Yonsei University
Yonsei University is one of South Korea’s leading private research universities, renowned for its strong international programs and membership in prestigious global academic networks.
-
C.
Chosun University
Chosun University is a major private research university in South Korea known for its comprehensive academic programs and regional influence.
-
D.
Korea University
Korea University is a leading private research university in Seoul, South Korea, renowned for its comprehensive academic programs and status as one of the country’s top institutions.
-
E.
Keimyung University
Keimyung University is a private Christian university in Daegu, South Korea, known for its international programs and picturesque campus.
- 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_69b345415ba481908df738e7174448ba |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b355d5975c8190bfe8a2d5d2dbf075 |
completed | March 13, 2026, 12:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b6281cef58819095182f8c89fe6e59 |
completed | March 15, 2026, 3:31 a.m. |
Created at: March 12, 2026, 11:32 p.m.