Triple
T15459416
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liu |
E371857
|
entity |
| Predicate | simplifiedForm |
P52959
|
FINISHED |
| Object | 刘 |
E1157469
|
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: 刘 | Statement: [Liu, simplifiedForm, 刘]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 刘 Context triple: [Liu, simplifiedForm, 刘]
-
A.
刘
chosen
刘 is a common Chinese surname and given name character, historically associated with several prominent clans and figures in Chinese history.
-
B.
趙
趙 is a common Chinese surname with historical roots in ancient China, notably associated with the State of Zhao during the Warring States period.
-
C.
Liu Bian
Liu Bian was a briefly reigning, deposed emperor of the late Eastern Han dynasty whose overthrow marked the beginning of the dynasty’s final collapse.
-
D.
Gaozu
Gaozu is the posthumous temple name honoring the influential Cao Wei statesman and strategist Sima Yi, later revered as a dynastic founder figure.
-
E.
Gaozu
Gaozu was the temple name of Emperor Gaozu of Tang, the founder and first emperor of China’s Tang dynasty.
- 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_69d85cc8bd308190886949510b42e764 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f1623f0819086f6fc2bfd536609 |
completed | April 16, 2026, 1:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff2cfd76cc8190b3d8148ffe872887 |
completed | May 9, 2026, 12:47 p.m. |
Created at: April 10, 2026, 3:32 a.m.