Triple
T17749625
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shadow (2018 film) |
E443077
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object |
Leo Wu
Leo Wu is a popular Chinese actor known for his roles in historical and fantasy television dramas and films.
|
E1289608
|
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: Leo Wu | Statement: [Shadow (2018 film), castMember, Leo Wu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leo Wu Context triple: [Shadow (2018 film), castMember, Leo Wu]
-
A.
Jeff Wu
Jeff Wu is a machine learning researcher known for his work on large language models, including co-authoring the original GPT-2 paper at OpenAI.
-
B.
Joseph Wu
Joseph Wu is a Taiwanese politician and diplomat who has served in key roles managing Taiwan’s relations with China and its broader foreign affairs.
-
C.
Richard Cheng
Richard Cheng is a character in the "Crazy Rich Asians" universe, known as the wealthy, old-money uncle of Nick Young.
-
D.
Stephen Wang
Stephen Wang is an entrepreneur best known as a co-founder of the film and television review aggregation website Rotten Tomatoes.
-
E.
Roger Yuan
Roger Yuan is an American martial artist, fight choreographer, and actor known for his roles and stunt work in numerous action films.
- 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: Leo Wu Triple: [Shadow (2018 film), castMember, Leo Wu]
Generated description
Leo Wu is a popular Chinese actor known for his roles in historical and fantasy television dramas and films.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Leo Wu Target entity description: Leo Wu is a popular Chinese actor known for his roles in historical and fantasy television dramas and films.
-
A.
Jeff Wu
Jeff Wu is a machine learning researcher known for his work on large language models, including co-authoring the original GPT-2 paper at OpenAI.
-
B.
Joseph Wu
Joseph Wu is a Taiwanese politician and diplomat who has served in key roles managing Taiwan’s relations with China and its broader foreign affairs.
-
C.
Richard Cheng
Richard Cheng is a character in the "Crazy Rich Asians" universe, known as the wealthy, old-money uncle of Nick Young.
-
D.
Stephen Wang
Stephen Wang is an entrepreneur best known as a co-founder of the film and television review aggregation website Rotten Tomatoes.
-
E.
Roger Yuan
Roger Yuan is an American martial artist, fight choreographer, and actor known for his roles and stunt work in numerous action films.
- 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48418c0188190beb31809b40e4648 |
completed | April 19, 2026, 7:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a02ff51215881909a1fd82d7ed3e351 |
completed | May 12, 2026, 10:22 a.m. |
| NEDg | Description generation | batch_6a03007f298881908743c16e17bd5877 |
completed | May 12, 2026, 10:27 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a03014a86308190b8f68fa279298575 |
completed | May 12, 2026, 10:30 a.m. |
Created at: April 10, 2026, 10:10 a.m.