Triple
T21570304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Playdom |
E532264
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
Michael Chang
Michael Chang is an entrepreneur best known as a co-founder of the social gaming company Playdom.
|
E1491385
|
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: Michael Chang | Statement: [Playdom, foundedBy, Michael Chang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Chang Context triple: [Playdom, foundedBy, Michael Chang]
-
A.
Michael Chang
Michael Chang is an animation director best known for his work on DC Comics–based animated films and television series.
-
B.
Victor Koo
Victor Koo is a Chinese entrepreneur best known as the co-founder and former CEO of Youku, one of China’s leading online video platforms.
-
C.
Michael Thorpe
Michael Thorpe is a relatively obscure individual whose specific public achievements or distinguishing characteristics are not widely documented.
-
D.
Wayne Cherry
Wayne Cherry is an American automobile designer best known for his influential leadership of General Motors’ global design studios and his role in shaping the look of numerous GM brands and models from the late 20th century onward.
-
E.
Kay McEnroe
Kay McEnroe is the mother of tennis legend John McEnroe and part of the McEnroe family known for its prominence in professional tennis.
- 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: Michael Chang Triple: [Playdom, foundedBy, Michael Chang]
Generated description
Michael Chang is an entrepreneur best known as a co-founder of the social gaming company Playdom.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Michael Chang Target entity description: Michael Chang is an entrepreneur best known as a co-founder of the social gaming company Playdom.
-
A.
Michael Chang
Michael Chang is an animation director best known for his work on DC Comics–based animated films and television series.
-
B.
Victor Koo
Victor Koo is a Chinese entrepreneur best known as the co-founder and former CEO of Youku, one of China’s leading online video platforms.
-
C.
Michael Thorpe
Michael Thorpe is a relatively obscure individual whose specific public achievements or distinguishing characteristics are not widely documented.
-
D.
Wayne Cherry
Wayne Cherry is an American automobile designer best known for his influential leadership of General Motors’ global design studios and his role in shaping the look of numerous GM brands and models from the late 20th century onward.
-
E.
Kay McEnroe
Kay McEnroe is the mother of tennis legend John McEnroe and part of the McEnroe family known for its prominence in professional tennis.
- 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_69e0c460db088190828c64206a450273 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eee9cc5c448190887a836f577d01ba |
completed | April 27, 2026, 4:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09f6707578819095e5ac0312066df6 |
completed | May 17, 2026, 5:10 p.m. |
| NEDg | Description generation | batch_6a09f71df0308190b5953a76da60c6d4 |
completed | May 17, 2026, 5:13 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09f80784648190ae073b4db90032c1 |
completed | May 17, 2026, 5:16 p.m. |
Created at: April 16, 2026, 6:30 p.m.