Triple
T9853684
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ali Wong |
E239531
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Justin Hakuta
Justin Hakuta is a Japanese-Filipino American entrepreneur and former tech executive, known publicly as the ex-husband of comedian and actress Ali Wong.
|
E825039
|
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: Justin Hakuta | Statement: [Ali Wong, spouse, Justin Hakuta]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Justin Hakuta Context triple: [Ali Wong, spouse, Justin Hakuta]
-
A.
David Kahne
David Kahne is an American record producer and engineer known for his work with major artists across rock and pop, including Paul McCartney.
-
B.
Jeff Okin
Jeff Okin is a television producer best known for his executive production work on the Amazon drama series "Good Girls Revolt."
-
C.
J. Todd Harris
J. Todd Harris is an American film producer known for his work on independent and genre films, including the horror-comedy "Idle Hands."
-
D.
Eliot Lindauer
Eliot Lindauer is an individual notable enough to be specifically cited as a bearer of the Lindauer surname.
-
E.
Andrew Barto
Andrew Barto is an American computer scientist and a pioneering researcher in reinforcement learning, known for co-authoring the influential textbook "Reinforcement Learning: An Introduction."
- 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: Justin Hakuta Triple: [Ali Wong, spouse, Justin Hakuta]
Generated description
Justin Hakuta is a Japanese-Filipino American entrepreneur and former tech executive, known publicly as the ex-husband of comedian and actress Ali Wong.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Justin Hakuta Target entity description: Justin Hakuta is a Japanese-Filipino American entrepreneur and former tech executive, known publicly as the ex-husband of comedian and actress Ali Wong.
-
A.
David Kahne
David Kahne is an American record producer and engineer known for his work with major artists across rock and pop, including Paul McCartney.
-
B.
Jeff Okin
Jeff Okin is a television producer best known for his executive production work on the Amazon drama series "Good Girls Revolt."
-
C.
J. Todd Harris
J. Todd Harris is an American film producer known for his work on independent and genre films, including the horror-comedy "Idle Hands."
-
D.
Eliot Lindauer
Eliot Lindauer is an individual notable enough to be specifically cited as a bearer of the Lindauer surname.
-
E.
Andrew Barto
Andrew Barto is an American computer scientist and a pioneering researcher in reinforcement learning, known for co-authoring the influential textbook "Reinforcement Learning: An Introduction."
- 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_69ca84e4fdc08190a624425bcef98665 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb376d32c819089381cf6ed83629d |
completed | April 2, 2026, 12:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1d5f21a04819099f23ede55ec3417 |
completed | April 5, 2026, 3:24 a.m. |
| NEDg | Description generation | batch_69d1d7a6a87c81908dcd79c776bb19a1 |
completed | April 5, 2026, 3:31 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d1d82007088190ac372c67a6760e65 |
completed | April 5, 2026, 3:33 a.m. |
Created at: March 30, 2026, 8:34 p.m.