Triple
T6366090
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patriots |
E143232
|
entity |
| Predicate | athleticDirector |
P745
|
FINISHED |
| Object |
Brad Edwards
Brad Edwards is a former American football safety who played in the NFL and later transitioned into collegiate athletic administration as an athletic director.
|
E588199
|
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: Brad Edwards | Statement: [Patriots, athleticDirector, Brad Edwards]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brad Edwards Context triple: [Patriots, athleticDirector, Brad Edwards]
-
A.
Rob Edwards
Rob Edwards is an American screenwriter best known for his work on animated films such as Disney's "Treasure Planet" and "The Princess and the Frog."
-
B.
Jake Scott
Jake Scott was an American NFL safety best known for his standout play with the Miami Dolphins in the early 1970s, including their perfect season.
-
C.
Jake Scott
Jake Scott is a British film and music video director known for his work with prominent rock bands and artists.
-
D.
Quayle
Quayle is the surname of Dan Quayle, the 44th vice president of the United States who served under President George H. W. Bush.
-
E.
Jeff Cunningham
Jeff Cunningham is a former professional soccer forward best known as one of Major League Soccer’s most prolific goal scorers.
- 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: Brad Edwards Triple: [Patriots, athleticDirector, Brad Edwards]
Generated description
Brad Edwards is a former American football safety who played in the NFL and later transitioned into collegiate athletic administration as an athletic director.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Brad Edwards Target entity description: Brad Edwards is a former American football safety who played in the NFL and later transitioned into collegiate athletic administration as an athletic director.
-
A.
Rob Edwards
Rob Edwards is an American screenwriter best known for his work on animated films such as Disney's "Treasure Planet" and "The Princess and the Frog."
-
B.
Jake Scott
Jake Scott was an American NFL safety best known for his standout play with the Miami Dolphins in the early 1970s, including their perfect season.
-
C.
Jake Scott
Jake Scott is a British film and music video director known for his work with prominent rock bands and artists.
-
D.
Quayle
Quayle is the surname of Dan Quayle, the 44th vice president of the United States who served under President George H. W. Bush.
-
E.
Jeff Cunningham
Jeff Cunningham is a former professional soccer forward best known as one of Major League Soccer’s most prolific goal scorers.
- 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_69c008d8c61081908bcaf61510d881ed |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c068106e18819087ed2e9841d2b365 |
completed | March 22, 2026, 10:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c62d8059588190a7d052889b25a8b6 |
completed | March 27, 2026, 7:10 a.m. |
| NEDg | Description generation | batch_69c62e8a7dd48190950b220460eb2d6f |
completed | March 27, 2026, 7:15 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c62ee892208190b3b005a9bd41b744 |
completed | March 27, 2026, 7:16 a.m. |
Created at: March 22, 2026, 4:32 p.m.