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.