Triple
T16328234
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khải Định |
E396479
|
entity |
| Predicate | father |
P120
|
FINISHED |
| Object | Đồng Khánh |
E396251
|
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: Đồng Khánh | Statement: [Khải Định, father, Đồng Khánh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Đồng Khánh Context triple: [Khải Định, father, Đồng Khánh]
-
A.
Đồng Khánh
chosen
Đồng Khánh was an emperor of Vietnam’s Nguyễn dynasty who ruled in the late 19th century under significant French colonial influence.
-
B.
Khánh
Khánh is a Vietnamese given name commonly used for both males and females, often associated with meanings like celebration, joy, or respect.
-
C.
Dinh Can
Dinh Can is the given name of Ngo Dinh Can, a prominent member of South Vietnam’s influential Ngo family during the mid-20th century.
-
D.
Chau Thanh
Chau Thanh is a rural district-level town in Vietnam’s Kien Giang Province, known for its agricultural landscape and proximity to the Mekong Delta region.
-
E.
Vinh Thuan
Vinh Thuan is a town in Vietnam’s Kien Giang Province, known as a local administrative and commercial center in the Mekong Delta region.
- 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_69d87f255b788190a400eba031dd85d8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2c4dcd034819081d849003d918245 |
completed | April 17, 2026, 11:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a003556630081909e60e378e97b06fb |
completed | May 10, 2026, 7:35 a.m. |
Created at: April 10, 2026, 5:07 a.m.