Triple
T16502205
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nam Kỳ Lục Tỉnh |
E400825
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | Nam Kỳ |
E93306
|
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: Nam Kỳ | Statement: [Nam Kỳ Lục Tỉnh, partOf, Nam Kỳ]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nam Kỳ Context triple: [Nam Kỳ Lục Tỉnh, partOf, Nam Kỳ]
-
A.
Nam Kỳ
chosen
Nam Kỳ is the Vietnamese name for Cochinchina, the historical southern region of Vietnam that was colonized by France and later became part of the modern Vietnamese state.
-
B.
Phuc Yen
Phuc Yen is a city in northern Vietnam known as an industrial and residential center within Vinh Phuc Province, near the capital Hanoi.
-
C.
Vinh Yen
Vinh Yen is an urban center in northern Vietnam that serves as the administrative, economic, and cultural hub of Vinh Phuc Province.
-
D.
Phong Điền
Phong Điền is a rural district of Cần Thơ in Vietnam’s Mekong Delta, known for its lush orchards and traditional floating markets.
-
E.
Cam Lộ
Cam Lộ is a rural district and township in Quảng Trị Province, central Vietnam, historically significant as a strategic area during the Vietnam War.
- 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_69d88381f6148190819958a038be990e |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32e4f7b7c8190adb5a113f798484f |
completed | April 18, 2026, 7:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00582e6e288190825af8758097e325 |
completed | May 10, 2026, 10:04 a.m. |
Created at: April 10, 2026, 5:14 a.m.