Triple
T15625430
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Scott Pilgrim vs. the World |
E375664
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Ellen Wong |
E1169272
|
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: Ellen Wong | Statement: [Scott Pilgrim vs. the World, castMember, Ellen Wong]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ellen Wong Context triple: [Scott Pilgrim vs. the World, castMember, Ellen Wong]
-
A.
Ellen Wong
chosen
Ellen Wong is a Canadian actress best known for her breakout role as Knives Chau in the film "Scott Pilgrim vs. the World."
-
B.
Gloria Fong
Gloria Fong was the wife of American character actor and restaurateur Benson Fong.
-
C.
Michelle Yee
Michelle Yee is an American philanthropist and investor best known as the wife of LinkedIn co-founder Reid Hoffman.
-
D.
Edith Chao
Edith Chao was the wife of Chinese warlord and political figure Zhang Xueliang, accompanying him through his long years of house arrest and exile.
-
E.
Rosalind Chao
Rosalind Chao is an American actress best known for her roles in "The Joy Luck Club" and the "Star Trek" franchise.
- 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_69d85cd035a48190b73d5579ab73969a |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e9e5e248190ae54cda1fde51efb |
completed | April 16, 2026, 2:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff6ece07608190a705f108c8c2979a |
completed | May 9, 2026, 5:28 p.m. |
Created at: April 10, 2026, 4:14 a.m.