Triple
T25595881
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clarence Davis |
E641649
|
entity |
| Predicate | nflProfileId |
P123948
|
FINISHED |
| Object | clarencedavis/2512620 |
—
|
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: clarencedavis/2512620 | Statement: [Clarence Davis, nflProfileId, clarencedavis/2512620]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nflProfileId Context triple: [Clarence Davis, nflProfileId, clarencedavis/2512620]
-
A.
nflId
Indicates a unique identifier assigned to an NFL player or entity within the dataset, used to distinguish it from all others.
-
B.
formerNFLPlayerAssociated
Indicates that a person was previously an NFL player and has or had some form of association or connection with another entity (such as a team, organization, or individual).
-
C.
proFootballReferenceID
Indicates that an entity is associated with a specific identifier used by Pro-Football-Reference.com to uniquely reference it in their database.
-
D.
nflComId
chosen
Indicates that an entity is associated with a specific NFL.com identifier used to uniquely reference it in the NFL.com system.
-
E.
NFLRookieRushingTouchdowns
Indicates the number of rushing touchdowns scored by an NFL player during their rookie season.
- 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_69e75dc60d108190b7e2419e36b0134b |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f9a251cc8190b2632bc5f9b4ca90 |
completed | May 2, 2026, 1:18 p.m. |
| PD | Predicate disambiguation | batch_69f480789be08190ab252a6de3797200 |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 4:27 p.m.