Triple

T19001417
Position Surface form Disambiguated ID Type / Status
Subject Magic City E464961 entity
Predicate notableFeatureHighlighted P61000 FINISHED
Object skyline 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: skyline | Statement: [Magic City, notableFeatureHighlighted, skyline]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: notableFeatureHighlighted
Context triple: [Magic City, notableFeatureHighlighted, skyline]
  • A. notableFeatureOn chosen
    Indicates that one entity is a prominent or distinguishing feature located on or part of another entity.
  • B. notableFeatureInStory
    Indicates that a particular feature, element, or characteristic plays a significant or prominent role within a story.
  • C. notableTechnicalFeature
    Indicates that an entity possesses a significant or distinguishing technical characteristic or capability.
  • D. notableStyleFeature
    Indicates that an entity possesses a distinctive stylistic characteristic or design element that is especially noteworthy or defining.
  • E. notableFeat
    Indicates that an entity is recognized for having achieved or performed a particularly significant or distinguished feat.
  • 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_69d8dd01a56c81909694a128c66b21d7 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d6863cf4819096e471d19f9a714c completed April 20, 2026, 7:32 a.m.
PD Predicate disambiguation batch_69e4a2f88e0c81908cb20f08bf24cd32 completed April 19, 2026, 9:40 a.m.
Created at: April 10, 2026, 12:01 p.m.