Triple
T17853709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gao Wei |
E445875
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Empress Hu |
—
|
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: Empress Hu | Statement: [Gao Wei, spouse, Empress Hu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Empress Hu Context triple: [Gao Wei, spouse, Empress Hu]
-
A.
Empress Hu
Empress Hu was a Ming dynasty empress consort of the Xuande Emperor, known primarily for her role within the imperial court and as a member of the Chinese imperial harem.
-
B.
Empress Hu
chosen
Empress Hu was a Chinese imperial consort who became empress during the Northern Qi dynasty, known for her political influence and involvement in court intrigues.
-
C.
Empress Zhang
Empress Zhang was the primary consort of the Hongxi Emperor of the Ming dynasty and served briefly as empress of China in the early 15th century.
-
D.
Empress Zhang
Empress Zhang was the primary consort and empress of the Hongzhi Emperor of the Ming dynasty, known for her political influence and role in the imperial court of late 15th-century China.
-
E.
Empress Zhang
Empress Zhang was a Ming dynasty empress consort of the Jiajing Emperor, known for her influential yet often turbulent role within the imperial court.
- 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_69d8b9f26f18819089c9e43250bee6ae |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e49001d8b881908c8d4efc3d7ff04f |
completed | April 19, 2026, 8:19 a.m. |
Created at: April 10, 2026, 10:17 a.m.