Triple
T20132124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Derrick Brooks Charities |
E490920
|
entity |
| Predicate | namedAfter |
P63
|
FINISHED |
| Object | Derrick Brooks |
—
|
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: Derrick Brooks | Statement: [Derrick Brooks Charities, namedAfter, Derrick Brooks]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Derrick Brooks Context triple: [Derrick Brooks Charities, namedAfter, Derrick Brooks]
-
A.
Derrick Brooks
chosen
Derrick Brooks is a Hall of Fame NFL linebacker best known for anchoring the Tampa Bay Buccaneers’ dominant defense and helping lead the team to a Super Bowl title.
-
B.
Derrick Harvin
Derrick Harvin is a writer known for crafting feedback, likely in editorial, evaluative, or review-focused contexts.
-
C.
Antonio Davis
Antonio Davis is a retired American professional basketball player best known for his NBA career as a rugged, defensive-minded power forward and center, including an All-Star stint with the Toronto Raptors.
-
D.
DeVon Harris
DeVon Harris is a songwriter best known for his work on the track "So High."
-
E.
Reggie Johnson
Reggie Johnson is an American jazz double bassist known for his work in the hard bop and post-bop scenes from the 1960s onward.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da62651a0c8190a3e05e95e056a66b |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e66762f0448190b7dbbc665e179ffc |
completed | April 20, 2026, 5:50 p.m. |
Created at: April 11, 2026, 11:31 p.m.