Triple
T23016058
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chinese democracy movement |
E573030
|
entity |
| Predicate | hasDissident |
P119817
|
FINISHED |
| Object | Bao Tong |
—
|
NE NERFINISHED |
How this triple was built (3 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: Bao Tong | Statement: [Chinese democracy movement, hasDissident, Bao Tong]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bao Tong Context triple: [Chinese democracy movement, hasDissident, Bao Tong]
-
A.
Bao Si
Bao Si was a famed beauty of ancient China whose relationship with King You of Zhou is often blamed in legend for contributing to the downfall of the Western Zhou dynasty.
-
B.
Gao Huang
Gao Huang is a computer scientist and researcher in deep learning, best known for co-developing the DenseNet convolutional neural network architecture.
-
C.
Chien-Pao
Chien-Pao is an Ice/Dark-type legendary Pokémon from the Paldea region, known as one of the Treasures of Ruin and characterized by its sword-like fangs formed from the blades of many fallen warriors.
-
D.
Xian Tong
Xian Tong was the era name used during the reign of Emperor Yizong of the Tang dynasty in China.
-
E.
Cheng Pu
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.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bao Tong Target entity description: Bao Tong was a prominent Chinese political reformer and outspoken dissident best known for his opposition to the Chinese Communist Party’s hardline stance after the 1989 Tiananmen Square protests.
-
A.
Bao Si
Bao Si was a famed beauty of ancient China whose relationship with King You of Zhou is often blamed in legend for contributing to the downfall of the Western Zhou dynasty.
-
B.
Gao Huang
Gao Huang is a computer scientist and researcher in deep learning, best known for co-developing the DenseNet convolutional neural network architecture.
-
C.
Chien-Pao
Chien-Pao is an Ice/Dark-type legendary Pokémon from the Paldea region, known as one of the Treasures of Ruin and characterized by its sword-like fangs formed from the blades of many fallen warriors.
-
D.
Xian Tong
Xian Tong was the era name used during the reign of Emperor Yizong of the Tang dynasty in China.
-
E.
Cheng Pu
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.
- F. None of above. chosen
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_69e245b764cc8190a51be76f1d9611e1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183e4dcd48190b2b1c2ab43205e41 |
completed | April 29, 2026, 4:07 a.m. |
Created at: April 17, 2026, 3:51 p.m.