Triple
T22354366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Simon |
E552612
|
entity |
| Predicate | livesWith |
P4704
|
FINISHED |
| Object | Wei-Tung Gao |
—
|
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: Wei-Tung Gao | Statement: [Simon, livesWith, Wei-Tung Gao]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wei-Tung Gao Context triple: [Simon, livesWith, Wei-Tung Gao]
-
A.
Wai-Tung Gao
chosen
Wai-Tung Gao is the Taiwanese-American gay protagonist of Ang Lee’s film "The Wedding Banquet," whose sham marriage to appease his traditional parents drives the movie’s central comedic and emotional conflicts.
-
B.
Ching-Yun Hu
Ching-Yun Hu is a Taiwanese-American concert pianist acclaimed for her international competition successes and performances with major orchestras worldwide.
-
C.
Wei-Ning Hsu
Wei-Ning Hsu is a researcher in speech and audio processing, known for co-developing the HuBERT self-supervised learning model for speech representation.
-
D.
Chiwei Yu
Chiwei Yu is a small, remote islet in the East China Sea that is part of the disputed Diaoyutai/Senkaku Islands archipelago.
-
E.
Huichi Chiu
Huichi Chiu is an actress known for her role in the Spanish television prison drama series "Locked Up" ("Vis a Vis").
- 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_69e11e4a0ad08190a385b4d343cf6524 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f157ceb2308190941f6507e605a612 |
completed | April 29, 2026, 12:58 a.m. |
Created at: April 16, 2026, 8:44 p.m.