Triple
T11797635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shreveport Pirates |
E280539
|
entity |
| Predicate | notableQuarterback |
P304
|
FINISHED |
| Object |
Billy Joe Tolliver
Billy Joe Tolliver is a former American football quarterback best known for his NFL career in the late 1980s and 1990s with teams such as the San Diego Chargers, Atlanta Falcons, and New Orleans Saints.
|
E1306113
|
NE FINISHED |
How this triple was built (3 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.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Billy Joe Tolliver Context triple: [Shreveport Pirates, notableQuarterback, Billy Joe Tolliver]
-
A.
Ray Blanton
Ray Blanton was an American Democratic politician who served as governor of Tennessee in the late 1970s and became notorious for a clemency scandal involving the controversial pardoning of prisoners.
-
B.
Bucky Barrett
Bucky Barrett is an American guitarist and session musician known for his work in rock and country music, including collaborations with prominent artists and bands.
-
C.
Billy Hobbs
Billy Hobbs was an American football player best known as a standout linebacker who played professionally in the early 1970s, including in the World Football League.
-
D.
Tuck Jones
Tuck Jones is a person known primarily for being a relative of Bailey Ndugu.
-
E.
Rallo Tubbs
Rallo Tubbs is a precocious, sharp-tongued young boy and one of the central comedic characters in the animated sitcom "The Cleveland Show."
- 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: Billy Joe Tolliver Triple: [Shreveport Pirates, notableQuarterback, Billy Joe Tolliver]
Generated description
Billy Joe Tolliver is a former American football quarterback best known for his NFL career in the late 1980s and 1990s with teams such as the San Diego Chargers, Atlanta Falcons, and New Orleans Saints.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Billy Joe Tolliver Target entity description: Billy Joe Tolliver is a former American football quarterback best known for his NFL career in the late 1980s and 1990s with teams such as the San Diego Chargers, Atlanta Falcons, and New Orleans Saints.
-
A.
Ray Blanton
Ray Blanton was an American Democratic politician who served as governor of Tennessee in the late 1970s and became notorious for a clemency scandal involving the controversial pardoning of prisoners.
-
B.
Bucky Barrett
Bucky Barrett is an American guitarist and session musician known for his work in rock and country music, including collaborations with prominent artists and bands.
-
C.
Billy Hobbs
Billy Hobbs was an American football player best known as a standout linebacker who played professionally in the early 1970s, including in the World Football League.
-
D.
Tuck Jones
Tuck Jones is a person known primarily for being a relative of Bailey Ndugu.
-
E.
Rallo Tubbs
Rallo Tubbs is a precocious, sharp-tongued young boy and one of the central comedic characters in the animated sitcom "The Cleveland Show."
- F. None of above. chosen
Provenance (4 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_69d6ab258b808190b1735835c841e3a4 |
completed | April 8, 2026, 7:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a037c1792a081909cce0eb4cd1d6870 |
completed | May 12, 2026, 7:14 p.m. |
| NEDg | Description generation | batch_6a037ca6f5888190b0ed34777aae862f |
completed | May 12, 2026, 7:16 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a037d319be48190b01a1b8d1f239078 |
completed | May 12, 2026, 7:19 p.m. |
Created at: April 8, 2026, 9:42 p.m.