Triple
T15459387
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liu Shaoqi |
E371856
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Cheng Pu |
E668203
|
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: Cheng Pu | Statement: [Liu Shaoqi, spouse, Cheng Pu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cheng Pu Context triple: [Liu Shaoqi, spouse, Cheng Pu]
-
A.
Cheng Pu
chosen
Cheng Pu was a prominent military general and veteran officer who served the warlord Sun Quan and played a key role in the early expansion of the Eastern Wu state during the late Eastern Han and Three Kingdoms period of China.
-
B.
Yang Chengwu
Yang Chengwu was a prominent Chinese military leader and general in the People’s Liberation Army who played key roles in the Chinese Civil War and early PRC military development.
-
C.
Chen Qimei
Chen Qimei was an influential early Chinese revolutionary leader and close ally of Sun Yat-sen who played a key role in the overthrow of the Qing dynasty.
-
D.
Liu Cunhou
Liu Cunhou was a Chinese military officer and warlord associated with the Yunnan clique during the early Republican era.
-
E.
Cheng Wei
Cheng Wei is a Chinese entrepreneur best known as the founder and CEO of ride-hailing giant Didi Chuxing.
- 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_6a0025e9b00c81908cb5f305c894363f |
completed | May 10, 2026, 6:30 a.m. |
Created at: April 10, 2026, 3:32 a.m.