Triple
T2375391
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Super Bowl 50 |
E46185
|
entity |
| Predicate | referee |
P268
|
FINISHED |
| Object |
Clete Blakeman
Clete Blakeman is an American NFL official best known for serving as the head referee in major games, including Super Bowl 50.
|
E267331
|
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: Clete Blakeman | Statement: [Super Bowl 50, referee, Clete Blakeman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Clete Blakeman Context triple: [Super Bowl 50, referee, Clete Blakeman]
-
A.
Ric Binkley
Ric Binkley was an American illustrator best known for his science fiction and fantasy cover art in the mid-20th century.
-
B.
Semeka Randall
Semeka Randall is a former American college basketball star and WNBA guard best known for her standout career under coach Pat Summitt at the University of Tennessee.
-
C.
Ronnie Knox
Ronnie Knox was an American football quarterback active in the 1950s, known for his college career at UCLA and California and a brief stint in the NFL and CFL.
-
D.
Bobby Reed
Bobby Reed was the husband of actress and vaudeville performer June Havoc.
-
E.
Roy Hinson
Roy Hinson is a former American professional basketball player and standout forward from Rutgers University who played several seasons in the NBA during the 1980s.
- 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: Clete Blakeman Triple: [Super Bowl 50, referee, Clete Blakeman]
Generated description
Clete Blakeman is an American NFL official best known for serving as the head referee in major games, including Super Bowl 50.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Clete Blakeman Target entity description: Clete Blakeman is an American NFL official best known for serving as the head referee in major games, including Super Bowl 50.
-
A.
Ric Binkley
Ric Binkley was an American illustrator best known for his science fiction and fantasy cover art in the mid-20th century.
-
B.
Semeka Randall
Semeka Randall is a former American college basketball star and WNBA guard best known for her standout career under coach Pat Summitt at the University of Tennessee.
-
C.
Ronnie Knox
Ronnie Knox was an American football quarterback active in the 1950s, known for his college career at UCLA and California and a brief stint in the NFL and CFL.
-
D.
Bobby Reed
Bobby Reed was the husband of actress and vaudeville performer June Havoc.
-
E.
Roy Hinson
Roy Hinson is a former American professional basketball player and standout forward from Rutgers University who played several seasons in the NBA during the 1980s.
- 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_69a88a145268819083e2736cb835c696 |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abc7935fe881909696a3ce27822db4 |
completed | March 7, 2026, 6:37 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69aef094fd8081909fc9a19f3e36c0d0 |
completed | March 9, 2026, 4:08 p.m. |
| NEDg | Description generation | batch_69aef252765081909e36c8355cb14c18 |
completed | March 9, 2026, 4:16 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69aef5b78e248190b1f064f3942a24ff |
completed | March 9, 2026, 4:30 p.m. |
Created at: March 4, 2026, 7:56 p.m.