Triple
T17223842
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Empress Zhang |
E418058
|
entity |
| Predicate | successorAsEmpress |
P37709
|
FINISHED |
| Object | Empress Xiaojie |
E388755
|
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: Empress Xiaojie | Statement: [Empress Zhang, successorAsEmpress, Empress Xiaojie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Empress Xiaojie Context triple: [Empress Zhang, successorAsEmpress, Empress Xiaojie]
-
A.
Empress Xiaojie
chosen
Empress Xiaojie was the primary consort and empress of the Zhengde Emperor during the Ming dynasty in China.
-
B.
Empress Xiaojiesheng
Empress Xiaojiesheng was a Qing dynasty empress consort of the Kangxi Emperor, remembered as the mother of his successor, the Yongzheng Emperor.
-
C.
Empress Xiaode
Empress Xiaode was the posthumous title of Empress Fang, a Ming dynasty empress consort known for her virtue and support of the imperial court.
-
D.
Empress Xiaojing
Empress Xiaojing was the principal consort of the Ming dynasty Longqing Emperor and an empress of China during the 16th century.
-
E.
Empress Xiaojing
Empress Xiaojing was a Ming dynasty empress consort of the Wanli Emperor, noted as the mother of his heir and a central figure in late Ming court politics.
- 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_69d886d779488190b131369541c04e7d |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42ddfe3bc8190b22cee4fc0590b74 |
completed | April 19, 2026, 1:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0491547b9081909876f88fe6a58ee7 |
completed | May 13, 2026, 2:57 p.m. |
Created at: April 10, 2026, 5:38 a.m.