Triple
T23022685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nguyen Hue |
E573209
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Phú Xuân |
—
|
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: Phú Xuân | Statement: [Nguyen Hue, capital, Phú Xuân]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Phú Xuân Context triple: [Nguyen Hue, capital, Phú Xuân]
-
A.
Phú Xuân
chosen
Phú Xuân was the historic city that served as the imperial capital of Vietnam, located in present-day Huế.
-
B.
Lao Bảo
Lao Bảo is a border town in Quảng Trị Province, Vietnam, known as a key commercial and transit point on the route between Vietnam and Laos.
-
C.
Tuy Hoa
Tuy Hoa is a coastal city in south-central Vietnam known for its beaches, rice fields, and role as the capital of Phú Yên Province.
-
D.
Long Xuyen
Long Xuyen is a major city in Vietnam’s Mekong Delta region, serving as the capital of An Giang Province and an important economic and cultural center.
-
E.
Hoa Hao
Hoa Hao is a Vietnamese Buddhist reform movement known for its simple, rural-focused practice, strong ethical emphasis, and significant following among Vietnamese communities both in Vietnam and abroad.
- 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_69e245b821008190b0e09cb02092aae1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183ea23088190b2f42d9bf01514ac |
completed | April 29, 2026, 4:07 a.m. |
Created at: April 17, 2026, 3:52 p.m.