Triple
T17445653
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | House of Gao |
E424774
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object | Gao Yang |
—
|
NE NERFINISHED |
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: Gao Yang | Statement: [House of Gao, hasMember, Gao Yang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gao Yang Context triple: [House of Gao, hasMember, Gao Yang]
-
A.
Gao Yang
chosen
Gao Yang, better known as Emperor Wenxuan of Northern Qi, was the founding emperor of the Northern Qi dynasty in 6th-century China.
-
B.
Gao Ying
Gao Ying is known primarily as the spouse of renowned Chinese poet Ai Qing.
-
C.
Gao Ying
Gao Ying is a participant featured in the documentary film "Ai Weiwei: Never Sorry," which chronicles the life and activism of Chinese artist Ai Weiwei.
-
D.
Hung Yan-yan
Hung Yan-yan is a Hong Kong martial artist, actor, and action choreographer known for his work in classic kung fu and action films.
-
E.
Yang Guang
Yang Guang, better known as Emperor Yang of Sui, was the second and last emperor of China’s Sui dynasty, noted for his ambitious public works and military campaigns that ultimately led to the dynasty’s downfall.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d889db0ba481908402409af3b37917 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e44ffafec48190b25980318cea353f |
completed | April 19, 2026, 3:46 a.m. |
Created at: April 10, 2026, 5:47 a.m.