Triple
T10141397
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emperor Wuzong of Tang |
E231591
|
entity |
| Predicate | father |
P120
|
FINISHED |
| Object | Li Kuan |
E808650
|
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: Li Kuan | Statement: [Emperor Wuzong of Tang, father, Li Kuan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Li Kuan Context triple: [Emperor Wuzong of Tang, father, Li Kuan]
-
A.
Li Kuan
chosen
Li Kuan was a Tang dynasty imperial prince, known primarily as a son of Emperor Xianzong of Tang.
-
B.
Li Shan
Li Shan is Po’s long-lost biological father and a jovial panda villager introduced in Kung Fu Panda 3.
-
C.
Meng Haoran
Meng Haoran was a renowned High Tang poet celebrated for his tranquil landscape and nature-themed verse that deeply influenced classical Chinese poetry.
-
D.
Yan Xiu
Yan Xiu was a prominent early 20th-century Chinese educator and reformer who played a key role in modernizing China's education system.
-
E.
Liu Ye
Liu Ye is a Chinese actor known for his versatile performances in both commercial blockbusters and critically acclaimed films.
- 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_69ca848364f881908a24366a6feec1db |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cdeb2599e0819090184631e481310c |
completed | April 2, 2026, 4:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d3008e56a481908d64077851063dbf |
completed | April 6, 2026, 12:38 a.m. |
Created at: March 30, 2026, 9:07 p.m.