Triple

T1101003
Position Surface form Disambiguated ID Type / Status
Subject Super Bowl I E24378 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 I, mvpPosition, quarterback]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: mvpPosition
Context triple: [Super Bowl I, mvpPosition, quarterback]
  • A. MVPposition chosen
    Indicates the position or role in which an entity served when it was recognized as the Most Valuable Player (MVP).
  • B. 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.
  • 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. MVPPoints
    Indicates the number of points an entity has earned toward a Most Valuable Player (MVP) recognition or award.
  • 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.

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_69a4940542308190ac2a0b1f730b7cfc completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4b9c079f48190a0e0ddda182f7a01 completed March 1, 2026, 10:12 p.m.
PD Predicate disambiguation batch_69a4b745ef3481909a7ce4647c8567b3 completed March 1, 2026, 10:01 p.m.
Created at: March 1, 2026, 7:43 p.m.