Triple
T13266098
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrew Bryniarski |
E315927
|
entity |
| Predicate | characterPortrayed |
P1507
|
FINISHED |
| Object |
Steve Lattimer
Steve Lattimer is a fictional college football player best known as the intense, steroid-abusing defensive end in the 1993 sports drama film "The Program."
|
E1038012
|
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: Steve Lattimer | Statement: [Andrew Bryniarski, characterPortrayed, Steve Lattimer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Steve Lattimer Context triple: [Andrew Bryniarski, characterPortrayed, Steve Lattimer]
-
A.
Clive Gillinson
Clive Gillinson is a British arts administrator and former cellist best known for his long tenure as managing and artistic director of Carnegie Hall.
-
B.
Jeffrey Stott
Jeffrey Stott is a film producer best known for his work on the political comedy film "The American President."
-
C.
Philip Giffin
Philip Giffin is a film and television composer known for his work on the series "Boomtown."
-
D.
Gary Maitland
Gary Maitland is a Scottish actor best known for his roles in Ken Loach films, including the comedy-drama "The Angels' Share."
-
E.
Geoffrey Thompson
Geoffrey Thompson is a notable member of the Thompson family, recognized for his prominence and contributions associated with the family’s legacy.
- 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: Steve Lattimer Triple: [Andrew Bryniarski, characterPortrayed, Steve Lattimer]
Generated description
Steve Lattimer is a fictional college football player best known as the intense, steroid-abusing defensive end in the 1993 sports drama film "The Program."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Steve Lattimer Target entity description: Steve Lattimer is a fictional college football player best known as the intense, steroid-abusing defensive end in the 1993 sports drama film "The Program."
-
A.
Clive Gillinson
Clive Gillinson is a British arts administrator and former cellist best known for his long tenure as managing and artistic director of Carnegie Hall.
-
B.
Jeffrey Stott
Jeffrey Stott is a film producer best known for his work on the political comedy film "The American President."
-
C.
Philip Giffin
Philip Giffin is a film and television composer known for his work on the series "Boomtown."
-
D.
Gary Maitland
Gary Maitland is a Scottish actor best known for his roles in Ken Loach films, including the comedy-drama "The Angels' Share."
-
E.
Geoffrey Thompson
Geoffrey Thompson is a notable member of the Thompson family, recognized for his prominence and contributions associated with the family’s legacy.
- 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_69d806b1d9ac8190852c5571d5bd5f0f |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d9901e44bc8190966f87ae219d6bf4 |
completed | April 11, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7305e1d70819096ff9784e9fafde9 |
completed | May 3, 2026, 11:24 a.m. |
| NEDg | Description generation | batch_69f7315007c081909ae53890e0782059 |
completed | May 3, 2026, 11:28 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f731b63f6081909658ce3af7103fe8 |
completed | May 3, 2026, 11:29 a.m. |
Created at: April 9, 2026, 9:25 p.m.