Triple
T8012854
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Faina Ipatyevna Vakhreva |
E186535
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Chiang Fang-liang |
E641447
|
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: Chiang Fang-liang | Statement: [Faina Ipatyevna Vakhreva, name, Chiang Fang-liang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Chiang Fang-liang Context triple: [Faina Ipatyevna Vakhreva, name, Chiang Fang-liang]
-
A.
Chiang Fang-liang
chosen
Chiang Fang-liang was the Belarusian-born wife of Chiang Ching-kuo and former First Lady of the Republic of China (Taiwan).
-
B.
Chiang Hsiao-yung
Chiang Hsiao-yung was a member of Taiwan’s influential Chiang family and a son of former President Chiang Ching-kuo.
-
C.
Wu Chih-yang
Wu Chih-yang is a Taiwanese politician and public figure known primarily as the son of former Kuomintang chairman Wu Po-hsiung.
-
D.
Chang Yung-fa
Chang Yung-fa was a Taiwanese shipping magnate and philanthropist best known as the billionaire founder of the Evergreen Group conglomerate.
-
E.
Chang Chun-hsiung
Chang Chun-hsiung is a Taiwanese politician and lawyer who twice served as premier and was a prominent member of the Democratic Progressive Party.
- 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_69ca82abaffc8190ab8af79cdbc31ab3 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3d73bf048190ad8066a7e95c34b0 |
completed | March 31, 2026, 3:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cdc64982d08190976144beafcd231d |
completed | April 2, 2026, 1:28 a.m. |
Created at: March 30, 2026, 5:19 p.m.