Triple
T23357455
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Li Ka-shing |
E593087
|
entity |
| Predicate | nativeName |
P15
|
FINISHED |
| Object | 李嘉誠 |
—
|
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: 李嘉誠 | Statement: [Li Ka-shing, nativeName, 李嘉誠]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 李嘉誠 Context triple: [Li Ka-shing, nativeName, 李嘉誠]
-
A.
Li Ka-shing
chosen
Li Ka-shing is a Hong Kong business magnate, investor, and philanthropist who became one of Asia’s richest and most influential entrepreneurs.
-
B.
郭台銘
郭台銘 is a Taiwanese billionaire entrepreneur best known as the founder of Foxconn, one of the world’s largest electronics manufacturers.
-
C.
張榮發
張榮發是一位台灣企業家與慈善家，最知名於創辦長榮海運與長榮集團，對全球航運業發展具有重要影響。
-
D.
Zhang Jindong
Zhang Jindong is a Chinese billionaire entrepreneur best known as the founder of the Suning retail empire and a prominent figure in China’s consumer electronics and e-commerce sectors.
-
E.
James Soong
James Soong is a prominent Taiwanese politician and founder of the People First Party, known for his leadership role within the Pan-Blue Coalition and his multiple bids for the presidency.
- 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_69e25d24d2a4819092e6ede74c2a918d |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f19a18996c81909c7ad15cde616553 |
completed | April 29, 2026, 5:41 a.m. |
Created at: April 17, 2026, 5:28 p.m.