Triple
T678657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Super Bowl XXI |
E13132
|
entity |
| Predicate | MVPposition |
P17440
|
FINISHED |
| Object | quarterback |
—
|
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: quarterback | Statement: [Super Bowl XXI, MVPposition, quarterback]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: MVPposition Context triple: [Super Bowl XXI, MVPposition, quarterback]
-
A.
MVP
Indicates that an entity has been selected or recognized as the “Most Valuable Player,” i.e., the most outstanding or impactful participant within a specific game, season, event, or context.
-
B.
MVPPoints
Indicates the number of points an entity has earned toward a Most Valuable Player (MVP) recognition or award.
-
C.
MVPRecord
Indicates that an entity holds a record for the most valuable player (MVP) distinction within a particular context, competition, or time period.
-
D.
MVPGoals
Indicates that an entity has been recognized as the Most Valuable Player (MVP) based on achieving specific performance goals or criteria.
-
E.
MVPRebounds
Indicates that the subject, as a league MVP, recorded a specified number of rebounds (or achieved a notable rebounding performance).
- 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_69a4933d3bf88190972041cd8cf143b9 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4a04e17088190943d54977eb3f83a |
completed | March 1, 2026, 8:23 p.m. |
| PD | Predicate disambiguation | batch_69a49d1d79608190a849ba9ffad2879d |
completed | March 1, 2026, 8:10 p.m. |
| PDg | Predicate description generation | batch_69a49df19c9481909cc9bc33ed7f011b |
completed | March 1, 2026, 8:13 p.m. |
Created at: March 1, 2026, 7:36 p.m.