Triple
T22466444
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phương Liên |
E555366
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Phương Dung |
—
|
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 Dung | Statement: [Phương Liên, sibling, Phương Dung]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Phương Dung Context triple: [Phương Liên, sibling, Phương Dung]
-
A.
Phương Dung
chosen
Phương Dung is a child of Bảo Đại, the last emperor of the Nguyễn dynasty in Vietnam.
-
B.
Mei Lanfang
Mei Lanfang was a legendary 20th-century Peking opera artist renowned for his pioneering performances in female roles and his influential international tours.
-
C.
Chow Mei-ching
Chow Mei-ching is a Taiwanese lawyer and the wife of former President Ma Ying-jeou, who served as First Lady of the Republic of China (Taiwan).
-
D.
Bai Ling
Bai Ling is a Chinese-American actress known for her eccentric persona and roles in films such as "The Crow," "Red Corner," and various independent and genre movies.
-
E.
Cheng Pei-pei
Cheng Pei-pei is a pioneering Chinese actress and martial arts film star, best known for her influential roles in classic wuxia cinema.
- 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.