Triple
T36666254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1983 NFL season |
E905272
|
entity |
| Predicate | passingYardsLeader |
P92019
|
FINISHED |
| Object | Dan Fouts |
—
|
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: Dan Fouts | Statement: [1983 NFL season, passingYardsLeader, Dan Fouts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: passingYardsLeader Context triple: [1983 NFL season, passingYardsLeader, Dan Fouts]
-
A.
collegiatePassingYardsLeader
Indicates the player who recorded the highest total passing yards in collegiate football over a specified season or time period.
-
B.
passingYardsInSeason
Indicates the total number of yards a player gained by passing the ball during a specific season.
-
C.
AFLPassingTouchdownsLeader
Indicates that the subject is the player who led the AFL in passing touchdowns over a specified season or time period.
-
D.
NFLPassingTitle
chosen
Indicates that a player has led the NFL in passing yards (won the passing title) for a given season.
-
E.
careerPassingYardsNFL
Indicates the total number of passing yards a player has accumulated over their entire career in the NFL.
- 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_69f76e6f10008190aea41746aa1b186e |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c780ecd0819080da2a286bf91257 |
completed | May 3, 2026, 10:09 p.m. |
| PD | Predicate disambiguation | batch_69f7c4796ebc819084a0dc08505e5f14 |
completed | May 3, 2026, 9:56 p.m. |
Created at: May 3, 2026, 4:12 p.m.