Triple
T16636187
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jobu Tupaki |
E404209
|
entity |
| Predicate | opposes |
P437
|
FINISHED |
| Object | Evelyn Wang |
E404207
|
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: Evelyn Wang | Statement: [Jobu Tupaki, opposes, Evelyn Wang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Evelyn Wang Context triple: [Jobu Tupaki, opposes, Evelyn Wang]
-
A.
Evelyn Wang
chosen
Evelyn Wang is the overwhelmed Chinese American laundromat owner and mother who becomes an unlikely multiverse-hopping hero in the film "Everything Everywhere All at Once."
-
B.
Alice Y. Ting
Alice Y. Ting is a chemical biologist known for pioneering methods to label and map proteins and cellular interactions in living cells.
-
C.
Anna M. Lee
Anna M. Lee was a party in the landmark U.S. Supreme Court case Hansberry v. Lee, which addressed issues of racially restrictive covenants and due process in property law.
-
D.
Eugenia Yuan
Eugenia Yuan is a Hong Kong–born American actress and former rhythmic gymnast known for her roles in international martial arts and drama films.
-
E.
Joanna Aizenberg
Joanna Aizenberg is a prominent materials scientist and bioinspired engineer known for pioneering work in biomimetic materials, surface science, and adaptive optical and structural systems.
- 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_69d8838a41f08190b0c3f79c47df5078 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e378e999d48190bff680040dbc883d |
completed | April 18, 2026, 12:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00918c998c81909b98d4fa9a8dbe3d |
completed | May 10, 2026, 2:09 p.m. |
Created at: April 10, 2026, 5:17 a.m.