Triple
T16162663
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2010 NFC Championship Game |
E392214
|
entity |
| Predicate | BearsStartingQBLeftReason |
P121641
|
FINISHED |
| Object | knee injury |
—
|
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: knee injury | Statement: [2010 NFC Championship Game, BearsStartingQBLeftReason, knee injury]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: BearsStartingQBLeftReason Context triple: [2010 NFC Championship Game, BearsStartingQBLeftReason, knee injury]
-
A.
SanFranciscoStartingQuarterback
Indicates that an entity serves as the starting quarterback for the San Francisco football team.
-
B.
RavensQuarterback
Indicates that the subject is a quarterback who plays for the Baltimore Ravens football team.
-
C.
quarterbackGreenBay
Indicates that an entity serves as the quarterback for the Green Bay football team.
-
D.
homeTeamQuarterbackStarter
Indicates that the specified quarterback is the starting quarterback for the home team in a given game or event.
-
E.
JetsQuarterback
Indicates that the subject is a quarterback who plays for, or is associated with, the New York Jets football team.
- 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_69d87f1d32208190942e4e499a80c18c |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e21e5ffba88190b9dc7bb9afb6fdf2 |
completed | April 17, 2026, 11:49 a.m. |
| PD | Predicate disambiguation | batch_69e1828abb608190a99d86bce1d77de2 |
completed | April 17, 2026, 12:44 a.m. |
| PDg | Predicate description generation | batch_69e18445155481909892b8aaa23cc159 |
completed | April 17, 2026, 12:52 a.m. |
Created at: April 10, 2026, 5:02 a.m.