Triple
T26362373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jake Matthews |
E660240
|
entity |
| Predicate | primaryPositionNFL |
P195627
|
FINISHED |
| Object | left tackle |
—
|
LITERAL FINISHED |
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: left tackle | Statement: [Jake Matthews, primaryPositionNFL, left tackle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryPositionNFL Context triple: [Jake Matthews, primaryPositionNFL, left tackle]
-
A.
nflPositionCategory
Indicates the general positional role or category that a player’s specific NFL position belongs to (e.g., offense, defense, special teams).
-
B.
HeismanTrophyPosition
Indicates the playing position associated with a recipient of the Heisman Trophy.
-
C.
nflId
Indicates a unique identifier assigned to an NFL player or entity within the dataset, used to distinguish it from all others.
-
D.
homeQuarterback
Indicates that the subject is the quarterback for the home team in a given game or matchup.
-
E.
primaryDefensiveLine
Indicates the main line of defense that first engages or protects against an opposing force or threat.
- F. None of above. chosen
Provenance (4 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_69ee8126d52c8190bc0b34337c2c9aa8 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69fddd373cdc8190be1b12e70e4deb1f |
completed | May 8, 2026, 12:55 p.m. |
| PD | Predicate disambiguation | batch_69fddc6915a88190ad41e379aa3ede13 |
completed | May 8, 2026, 12:51 p.m. |
| PDg | Predicate description generation | batch_69fddd364c1481908794c9d423bdc2d7 |
completed | May 8, 2026, 12:55 p.m. |
Created at: April 26, 2026, 10:52 p.m.