Triple

T15223604
Position Surface form Disambiguated ID Type / Status
Subject T-formation E363820 entity
Predicate backfieldBalance P105837 FINISHED
Object symmetrical 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: symmetrical | Statement: [T-formation, backfieldBalance, symmetrical]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: backfieldBalance
Context triple: [T-formation, backfieldBalance, symmetrical]
  • A. sharedBackfieldWith
    Indicates that two players were part of the same offensive backfield unit on a team during overlapping time periods.
  • B. typicalBalancingPositions chosen
    Indicates the standard or commonly used positions in which elements are arranged or adjusted to achieve balance or equilibrium in a given context.
  • C. fieldingAbility
    Indicates the level or quality of an entity’s skill and effectiveness in performing fielding actions in a game or sport.
  • D. middleLinebacker
    Indicates that one entity serves in the role of middle linebacker in relation to a football team, formation, or defensive alignment.
  • E. associatedWithQuarterback
    Indicates a relationship where an entity has a connection, role, or involvement with a quarterback.
  • 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_69d85a0ce24c81909c4d3b6475548c95 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0078a9318819081db3b7bcc28e04f completed April 15, 2026, 9:47 p.m.
PD Predicate disambiguation batch_69deca8479188190b2e5d3bc708d7d07 completed April 14, 2026, 11:15 p.m.
Created at: April 10, 2026, 3:12 a.m.