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.