Triple
T8111863
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chiang |
E189372
|
entity |
| Predicate | hasVariantSpelling |
P457
|
FINISHED |
| Object | Cheung |
E318877
|
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: Cheung | Statement: [Chiang, hasVariantSpelling, Cheung]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cheung Context triple: [Chiang, hasVariantSpelling, Cheung]
-
A.
Cheung
chosen
Cheung is a Cantonese romanization of the Chinese surname commonly spelled "Zhang" in Mandarin pinyin.
-
B.
Chi-chung
Chi-chung is an alternative romanized spelling of the Chinese given name commonly written as Zhizhong.
-
C.
Chen
Chen is a common Chinese surname borne by many notable individuals across politics, arts, science, and technology.
-
D.
Lee-Chin
Lee-Chin is the surname of Jamaican-Canadian billionaire businessman and philanthropist Michael Lee-Chin.
-
E.
Hong Chau
Hong Chau is an American actress acclaimed for her nuanced performances in film and television, including prominent roles in projects like "Downsizing," "The Whale," and various prestige TV series.
- 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_69ca82b9d5848190a24672775d5c5011 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb432bcb648190b5ddbcc2a3dbc9b1 |
completed | March 31, 2026, 3:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc942a9af881908b7ddc724755893e |
completed | April 1, 2026, 3:42 a.m. |
Created at: March 30, 2026, 5:32 p.m.