Triple
T2995359
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ballers |
E81052
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object |
Stephen Levinson
Stephen Levinson is an American television and film producer and talent manager best known for producing hit series like "Entourage" and "Ballers."
|
E438876
|
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: Stephen Levinson | Statement: [Ballers, creator, Stephen Levinson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stephen Levinson Context triple: [Ballers, creator, Stephen Levinson]
-
A.
Philip Brownstein
Philip Brownstein was a professional basketball coach best known for leading the early NBA-era Chicago Stags franchise.
-
B.
Jonathan Stuart Leibowitz
Jonathan Stuart Leibowitz is an American comedian, writer, producer, and former host of "The Daily Show," better known professionally as Jon Stewart.
-
C.
Evan A. Lottman
Evan A. Lottman was an American film editor known for his work on acclaimed films including the adaptation of "Sophie's Choice."
-
D.
Jay O. Rothman
Jay O. Rothman is an American attorney and academic leader who serves as president of the University of Wisconsin System.
-
E.
Scott J. Horowitz
Scott J. Horowitz is a former NASA astronaut and U.S. Air Force colonel who flew on four Space Shuttle missions in the 1990s and early 2000s.
- 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: Stephen Levinson Triple: [Ballers, creator, Stephen Levinson]
Generated description
Stephen Levinson is an American television and film producer and talent manager best known for producing hit series like "Entourage" and "Ballers."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Stephen Levinson Target entity description: Stephen Levinson is an American television and film producer and talent manager best known for producing hit series like "Entourage" and "Ballers."
-
A.
Philip Brownstein
Philip Brownstein was a professional basketball coach best known for leading the early NBA-era Chicago Stags franchise.
-
B.
Jonathan Stuart Leibowitz
Jonathan Stuart Leibowitz is an American comedian, writer, producer, and former host of "The Daily Show," better known professionally as Jon Stewart.
-
C.
Evan A. Lottman
Evan A. Lottman was an American film editor known for his work on acclaimed films including the adaptation of "Sophie's Choice."
-
D.
Jay O. Rothman
Jay O. Rothman is an American attorney and academic leader who serves as president of the University of Wisconsin System.
-
E.
Scott J. Horowitz
Scott J. Horowitz is a former NASA astronaut and U.S. Air Force colonel who flew on four Space Shuttle missions in the 1990s and early 2000s.
- 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_69ad8b187fc8819085914d3c9ea3142d |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad99f2e5888190b3346012e2578dab |
completed | March 8, 2026, 3:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b61313c7e881909309d18b2d5b6699 |
completed | March 15, 2026, 2:01 a.m. |
| NEDg | Description generation | batch_69b613add8bc8190ae4bf442ae96b127 |
completed | March 15, 2026, 2:04 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b6146fd7ec8190942e685c87596695 |
completed | March 15, 2026, 2:07 a.m. |
Created at: March 8, 2026, 2:59 p.m.