Triple
T23485685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nguyễn Cao Kỳ |
E570526
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Nguyễn Cao Kỳ Duyên |
—
|
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: Nguyễn Cao Kỳ Duyên | Statement: [Nguyễn Cao Kỳ, child, Nguyễn Cao Kỳ Duyên]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nguyễn Cao Kỳ Duyên Context triple: [Nguyễn Cao Kỳ, child, Nguyễn Cao Kỳ Duyên]
-
A.
Nguyễn Cao Kỳ Duyên
chosen
Nguyễn Cao Kỳ Duyên is a Vietnamese-American lawyer and television personality best known as a longtime co-host of the popular Paris By Night musical variety show.
-
B.
Lê Thị Nham
Lê Thị Nham was a consort of Emperor Đồng Khánh of the Nguyễn dynasty in late 19th-century Vietnam.
-
C.
Trinh Hoi Quan
Trinh Hoi Quan is an individual known primarily for being a notable bearer of the surname Quan.
-
D.
Hoang Minh Thao
Hoang Minh Thao was a prominent North Vietnamese general renowned for his strategic leadership in major campaigns during the Vietnam War.
-
E.
Đặng Tuyết Mai
Đặng Tuyết Mai was a prominent South Vietnamese socialite and former flight attendant who became widely known as the glamorous wife of Air Vice Marshal and Prime Minister Nguyễn Cao Kỳ.
- 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_69e245b0b01481908f636939bedd804c |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a7538a8c8190b7effcc39a3f9787 |
completed | April 29, 2026, 6:38 a.m. |
Created at: April 17, 2026, 6:03 p.m.