Triple
T22466438
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phương Liên |
E555366
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Phương Liên |
—
|
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: Phương Liên | Statement: [Phương Liên, givenName, Phương Liên]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Phương Liên Context triple: [Phương Liên, givenName, Phương Liên]
-
A.
Phương Liên
chosen
Phương Liên is a Vietnamese princess, the daughter of Vietnam’s last emperor Bảo Đại and a member of the former Nguyễn dynasty royal family.
-
B.
Fang Wanyi
Fang Wanyi was an 18th-century Chinese painter and poet of the Qing dynasty, known for her artistic talent and as a prominent woman in the circle of literati artists.
-
C.
Lien Fang Yu
Lien Fang Yu is a Taiwanese public figure and former television host best known as the wife of prominent Kuomintang politician and former Vice President of Taiwan, Lien Chan.
-
D.
Liu Fang
Liu Fang was a political advisor and official who served the Cao Wei state during China’s Three Kingdoms period, counseling Emperor Cao Rui.
-
E.
He Lian
He Lian is the pinyin romanization of the Chinese name 赫连, which can function as a surname or given name in Chinese-speaking contexts.
- 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_69e11e51fdec8190adfdf9f8a6362221 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b837ec081909c4e44d37e8b2acd |
completed | April 29, 2026, 1:14 a.m. |
Created at: April 16, 2026, 8:48 p.m.