Triple
T19092251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andy Lau |
E467315
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Carol Chu
Carol Chu is a former Malaysian model best known as the longtime wife of Hong Kong superstar Andy Lau.
|
E1358025
|
NE FINISHED |
How this triple was built (4 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: Carol Chu | Statement: [Andy Lau, spouse, Carol Chu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carol Chu Context triple: [Andy Lau, spouse, Carol Chu]
-
A.
Yvonne Chu
Yvonne Chu is the wife of Nobel Prize–winning physicist and former U.S. Secretary of Energy Steven Chu.
-
B.
Patricia Chin
Patricia Chin is a pioneering Jamaican music producer and entrepreneur best known as the co-founder of the influential reggae and dancehall label VP Records.
-
C.
Vivian Chan
Vivian Chan is a personal name shared by multiple individuals, including professionals in fields such as science, media, and business.
-
D.
Fay Chung
Fay Chung is a Zimbabwean educator and former government minister known for her influential role in shaping post-independence education policy in Zimbabwe.
-
E.
Fay Chang
Fay Chang is a computer scientist known for co-authoring the influential Google Bigtable paper on large-scale distributed storage systems.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Carol Chu Triple: [Andy Lau, spouse, Carol Chu]
Generated description
Carol Chu is a former Malaysian model best known as the longtime wife of Hong Kong superstar Andy Lau.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Carol Chu Target entity description: Carol Chu is a former Malaysian model best known as the longtime wife of Hong Kong superstar Andy Lau.
-
A.
Yvonne Chu
Yvonne Chu is the wife of Nobel Prize–winning physicist and former U.S. Secretary of Energy Steven Chu.
-
B.
Patricia Chin
Patricia Chin is a pioneering Jamaican music producer and entrepreneur best known as the co-founder of the influential reggae and dancehall label VP Records.
-
C.
Vivian Chan
Vivian Chan is a personal name shared by multiple individuals, including professionals in fields such as science, media, and business.
-
D.
Fay Chung
Fay Chung is a Zimbabwean educator and former government minister known for her influential role in shaping post-independence education policy in Zimbabwe.
-
E.
Fay Chang
Fay Chang is a computer scientist known for co-authoring the influential Google Bigtable paper on large-scale distributed storage systems.
- F. None of above. chosen
Provenance (5 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_69d8dd05ac4c8190b1967d8f97f3fb2f |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e34c22a08190bf34f92f727268c5 |
completed | April 20, 2026, 8:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a05dd94ce2881909c7487971ddfe44d |
completed | May 14, 2026, 2:35 p.m. |
| NEDg | Description generation | batch_6a05e0c9bf4c8190b748a768198d09d1 |
completed | May 14, 2026, 2:48 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a05e147a9848190a3d0503fad7354b9 |
completed | May 14, 2026, 2:50 p.m. |
Created at: April 10, 2026, 12:04 p.m.