Triple
T7997983
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emperor Taizu of Song |
E186175
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Zhao |
E81603
|
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: Zhao | Statement: [Emperor Taizu of Song, familyName, Zhao]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zhao Context triple: [Emperor Taizu of Song, familyName, Zhao]
-
A.
Zhao
chosen
Zhao is a common Chinese surname, historically borne by some members of the Jewish community of Kaifeng in China.
-
B.
Zhao
Zhao was an ancient Chinese state during the Warring States period, known for its military strength and role in the political fragmentation preceding the Qin unification.
-
C.
Zhao Lin
Zhao Lin is a Chinese film composer known for scoring numerous contemporary Chinese movies.
-
D.
Zhao Sheng
Zhao Sheng was a Chinese revolutionary associated with the Tongmenghui, the anti-Qing organization that helped pave the way for the 1911 Xinhai Revolution and the founding of the Republic of China.
-
E.
Zeng
Zeng is a Chinese surname and given name commonly rendered in pinyin and borne by numerous historical and contemporary figures in China.
- 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_69ca82aaaf24819084b94d18f699ba53 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3c98e39081908904d36a31bd6768 |
completed | March 31, 2026, 3:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc93991e9c8190a6834b8d9fd82128 |
completed | April 1, 2026, 3:40 a.m. |
Created at: March 30, 2026, 5:17 p.m.