Triple
T10453356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Maze Runner |
E246488
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Ki Hong Lee
Ki Hong Lee is a Korean-American actor best known for his role as Minho in the Maze Runner film series.
|
E863490
|
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: Ki Hong Lee | Statement: [The Maze Runner, starring, Ki Hong Lee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ki Hong Lee Context triple: [The Maze Runner, starring, Ki Hong Lee]
-
A.
Jin Lee
Jin Lee is the gentle, supportive father of protagonist Meilin "Mei" Lee in Pixar's animated film "Turning Red."
-
B.
Michael Kang
Michael Kang is an American musician best known as a multi-instrumentalist and prominent member of the jam band The String Cheese Incident.
-
C.
Will Yun Lee
Will Yun Lee is an American actor and martial artist known for his roles in films like "Die Another Day" and "The Wolverine" and TV series such as "Altered Carbon" and "Hawaii Five-0."
-
D.
Honglak Lee
Honglak Lee is a computer scientist and researcher known for his contributions to deep learning and representation learning, particularly in unsupervised feature learning.
-
E.
Ken Kao
Ken Kao is an American film producer known for backing a range of independent and auteur-driven projects.
- 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: Ki Hong Lee Triple: [The Maze Runner, starring, Ki Hong Lee]
Generated description
Ki Hong Lee is a Korean-American actor best known for his role as Minho in the Maze Runner film series.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ki Hong Lee Target entity description: Ki Hong Lee is a Korean-American actor best known for his role as Minho in the Maze Runner film series.
-
A.
Jin Lee
Jin Lee is the gentle, supportive father of protagonist Meilin "Mei" Lee in Pixar's animated film "Turning Red."
-
B.
Michael Kang
Michael Kang is an American musician best known as a multi-instrumentalist and prominent member of the jam band The String Cheese Incident.
-
C.
Will Yun Lee
Will Yun Lee is an American actor and martial artist known for his roles in films like "Die Another Day" and "The Wolverine" and TV series such as "Altered Carbon" and "Hawaii Five-0."
-
D.
Honglak Lee
Honglak Lee is a computer scientist and researcher known for his contributions to deep learning and representation learning, particularly in unsupervised feature learning.
-
E.
Ken Kao
Ken Kao is an American film producer known for backing a range of independent and auteur-driven projects.
- 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_69d381c04fe08190957c26c526a3b05a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4fe0d73d48190acb687b96918e0cf |
completed | April 7, 2026, 12:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d87f07c9f48190b0fce7740a2e003a |
completed | April 10, 2026, 4:39 a.m. |
| NEDg | Description generation | batch_69d886c562c081908aae846da8efb1a5 |
completed | April 10, 2026, 5:12 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d88dce21448190b093b4f548e29f84 |
completed | April 10, 2026, 5:42 a.m. |
Created at: April 6, 2026, 12:17 p.m.