Triple

T17035636
Position Surface form Disambiguated ID Type / Status
Subject The Game Awards 2017 Best Narrative E413313 entity
Predicate primaryEvaluationAspect P7594 FINISHED
Object narrative-driven experience 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: narrative-driven experience | Statement: [The Game Awards 2017 Best Narrative, primaryEvaluationAspect, narrative-driven experience]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: primaryEvaluationAspect
Context triple: [The Game Awards 2017 Best Narrative, primaryEvaluationAspect, narrative-driven experience]
  • A. evaluationAspect
    Indicates the specific dimension or criterion of performance or quality that is being assessed within an evaluation.
  • B. primaryCriterion chosen
    Indicates that one factor is designated as the main or most important basis for a decision, judgment, or selection among alternatives.
  • C. primaryCharacteristics
    Indicates the main defining traits or features that most fundamentally characterize an entity.
  • D. primarySignificance
    Indicates that something has the greatest importance, relevance, or impact among a set of related things or factors.
  • E. primaryComparison
    Indicates that one entity is being used as the main reference point or standard against which another entity is compared.
  • 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_69d886cd18288190b006abab23f811b7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d8f26f50819085dfd0fbecd6394d completed April 18, 2026, 7:18 p.m.
PD Predicate disambiguation batch_69e35d5be7f48190af9db67a1e23850f completed April 18, 2026, 10:30 a.m.
Created at: April 10, 2026, 5:33 a.m.