Triple
T2075304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maya Soetoro-Ng |
E44907
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Konrad Ng
Konrad Ng is a Canadian-American scholar and former director of the Smithsonian Asian Pacific American Center, known also as the husband of Maya Soetoro-Ng, Barack Obama’s half-sister.
|
E232863
|
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: Konrad Ng | Statement: [Maya Soetoro-Ng, spouse, Konrad Ng]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Konrad Ng Context triple: [Maya Soetoro-Ng, spouse, Konrad Ng]
-
A.
Victor Wong
Victor Wong was an American character actor known for his distinctive presence in films such as "The Last Emperor," "Big Trouble in Little China," and "Tremors."
-
B.
Gerald Chan
Gerald Chan is a Hong Kong-born American billionaire investor and philanthropist known for major donations to Harvard University and leadership of the Morningside Group.
-
C.
John Cheng
John Cheng is a film producer best known for his work on the dark comedy movie "Horrible Bosses."
-
D.
Ken Seng
Ken Seng is a cinematographer known for his visually distinctive work on films such as "Obsessed."
-
E.
Daren Tang
Daren Tang is a Singaporean lawyer and intellectual property expert who serves as the Director General of the World Intellectual Property Organization (WIPO).
- 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: Konrad Ng Triple: [Maya Soetoro-Ng, spouse, Konrad Ng]
Generated description
Konrad Ng is a Canadian-American scholar and former director of the Smithsonian Asian Pacific American Center, known also as the husband of Maya Soetoro-Ng, Barack Obama’s half-sister.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Konrad Ng Target entity description: Konrad Ng is a Canadian-American scholar and former director of the Smithsonian Asian Pacific American Center, known also as the husband of Maya Soetoro-Ng, Barack Obama’s half-sister.
-
A.
Victor Wong
Victor Wong was an American character actor known for his distinctive presence in films such as "The Last Emperor," "Big Trouble in Little China," and "Tremors."
-
B.
Gerald Chan
Gerald Chan is a Hong Kong-born American billionaire investor and philanthropist known for major donations to Harvard University and leadership of the Morningside Group.
-
C.
John Cheng
John Cheng is a film producer best known for his work on the dark comedy movie "Horrible Bosses."
-
D.
Ken Seng
Ken Seng is a cinematographer known for his visually distinctive work on films such as "Obsessed."
-
E.
Daren Tang
Daren Tang is a Singaporean lawyer and intellectual property expert who serves as the Director General of the World Intellectual Property Organization (WIPO).
- 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_69a88916c2b48190a5ca2e9b12cad3ed |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abba116ea0819086d16c3913159e9e |
completed | March 7, 2026, 5:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae2730d2548190b51dc61520981ca0 |
completed | March 9, 2026, 1:49 a.m. |
| NEDg | Description generation | batch_69ae27e4a6f88190a6af44f2cc822f31 |
completed | March 9, 2026, 1:52 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae2876710c81909451744f48337998 |
completed | March 9, 2026, 1:55 a.m. |
Created at: March 4, 2026, 7:41 p.m.