Triple
T16177129
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nancy Kwan |
E392592
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Kwan |
E197729
|
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: Kwan | Statement: [Nancy Kwan, familyName, Kwan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kwan Context triple: [Nancy Kwan, familyName, Kwan]
-
A.
Kwan
chosen
Kwan is a Chinese-origin surname shared by many individuals, including the renowned American figure skater Michelle Kwan.
-
B.
Kwan-non
Kwan-non is an alternative spelling of Kannon, the Japanese Buddhist bodhisattva of compassion derived from the Chinese Guanyin.
-
C.
Wou-Ki
Wou-Ki is the given name of Zao Wou-Ki, a renowned Chinese-French painter known for his lyrical abstract works.
-
D.
Kang
Kang is a recurring alien character from the animated television series "The Simpsons," often appearing in satirical and Halloween-themed episodes alongside his companion Kodos.
-
E.
Kang
Kang is a common Korean surname borne by many individuals in Korea and the Korean diaspora.
- 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_69d87f1d32208190942e4e499a80c18c |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e22059e7048190b4592cb1516b5f8d |
completed | April 17, 2026, 11:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fff7c11bc881909211a668f48092aa |
completed | May 10, 2026, 3:13 a.m. |
Created at: April 10, 2026, 5:02 a.m.