Triple
T19603179
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhao Erkang |
E470534
|
entity |
| Predicate | romanticPartnerInStory |
P9994
|
FINISHED |
| Object | Xia Ziwei |
—
|
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: Xia Ziwei | Statement: [Zhao Erkang, romanticPartnerInStory, Xia Ziwei]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Xia Ziwei Context triple: [Zhao Erkang, romanticPartnerInStory, Xia Ziwei]
-
A.
Xia Ziwei
chosen
Xia Ziwei is a central fictional character in the popular Chinese television drama "My Fair Princess" (Huan Zhu Ge Ge), known as the gentle and talented illegitimate daughter of the emperor.
-
B.
Wang Xiaoxiao
Wang Xiaoxiao is an actress known for appearing in the Chinese crime drama film "Shanghai Triad."
-
C.
Wang Ziwen
Wang Ziwen is a Chinese actress best known internationally for her role as the younger Ye Wenjie in the adaptation of Liu Cixin’s science fiction novel "The Three-Body Problem."
-
D.
Yang Tianyi
Yang Tianyi is an online content creator known for gaining popularity and a significant following on digital platforms.
-
E.
Li Weihan
Li Weihan was a prominent Chinese Communist revolutionary and politician who played key roles in party organization and United Front work in the early and mid-20th century.
- 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_69d8e510024481908415c0d616fa6186 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e64080a57c8190837cbe82b93163bf |
completed | April 20, 2026, 3:04 p.m. |
Created at: April 10, 2026, 1:43 p.m.