Triple
T32549723
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pat Swilling |
E831940
|
entity |
| Predicate | sackLeaderSeason |
P101935
|
FINISHED |
| Object | 1991 |
—
|
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: 1991 | Statement: [Pat Swilling, sackLeaderSeason, 1991]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sackLeaderSeason Context triple: [Pat Swilling, sackLeaderSeason, 1991]
-
A.
ERAleaderSeasons
Indicates that the subject led a league or competition in earned run average (ERA) for the specified number of seasons.
-
B.
tacklesLeaderNFLSeasons
Indicates the number of NFL seasons in which a player led the league in tackles.
-
C.
savesLeaderSeasons
Indicates the relationship where an entity is the leader in total saves for one or more seasons.
-
D.
seasonLedLeague
chosen
Indicates that, in a given season, the subject entity led the league in a particular statistical category or performance measure.
-
E.
sacks
Indicates that one entity tackles and brings another entity to the ground, typically behind a line of scrimmage or in a way that stops their progress.
- 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_69f34925fd08819084cfe4ec566cb704 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c5c5a8c4819088fcf00fcbcc7f51 |
completed | May 3, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69f6bd2a14b081908162923dfbf0a6f4 |
completed | May 3, 2026, 3:12 a.m. |
Created at: May 1, 2026, 1:02 a.m.