Triple
T30230606
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Samuel Davis Mills Jr. |
E768615
|
entity |
| Predicate | ProBowlTeam |
P64630
|
FINISHED |
| Object | New Orleans Saints |
—
|
NE NERFINISHED |
How this triple was built (2 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: New Orleans Saints | Statement: [Samuel Davis Mills Jr., ProBowlTeam, New Orleans Saints]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ProBowlTeam Context triple: [Samuel Davis Mills Jr., ProBowlTeam, New Orleans Saints]
-
A.
proBowlTeam
chosen
Indicates that a player was selected to and participated on a specific team in the Pro Bowl all-star game.
-
B.
superBowlTeam
Indicates that a team participated as one of the competing teams in a specific Super Bowl game.
-
C.
NFLTeam
Indicates a relationship where an entity is identified as a professional American football team that competes in the National Football League.
-
D.
americanFootballTeamOf
Indicates that one entity is the American football team associated with, representing, or belonging to another entity (such as a school, city, or organization).
-
E.
cbaTeam
Indicates that one entity is a member of, or associated with, a specific CBA (Collective Bargaining Agreement) team.
- F. None of above.
Provenance (3 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_69f2248108208190be60bf1af343ce70 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68025551081908f282e9ae3efebe7 |
completed | May 2, 2026, 10:52 p.m. |
| PD | Predicate disambiguation | batch_69f6760216108190bbb708d53a6c2c25 |
completed | May 2, 2026, 10:09 p.m. |
Created at: April 29, 2026, 7:36 p.m.