Triple

T30317022
Position Surface form Disambiguated ID Type / Status
Subject Tanabata E771084 entity
Predicate usesDecoration P38145 FINISHED
Object tanzaku 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: tanzaku | Statement: [Tanabata, usesDecoration, tanzaku]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: usesDecoration
Context triple: [Tanabata, usesDecoration, tanzaku]
  • A. hasDecor chosen
    Indicates that one entity possesses, features, or is adorned with a particular decorative element or style.
  • B. containsDecorationFrom
    Indicates that one entity includes or incorporates a decorative element that originates from another entity.
  • C. usesTraditionalDecoration
    Indicates that an entity employs customary or historically established decorative styles or motifs in its design or presentation.
  • D. relatedDecoration
    Indicates that one decoration is associated with, complements, or is contextually linked to another decoration.
  • E. valorDecoration
    Indicates that an entity has been awarded a decoration or honor specifically in recognition of acts of valor or bravery.
  • 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_69f22488f224819081b0f3ec41ab975c completed April 29, 2026, 3:32 p.m.
NER Named-entity recognition batch_69f6afebd7ec8190ab696f363d84abf0 completed May 3, 2026, 2:16 a.m.
PD Predicate disambiguation batch_69f6aca3dedc81908b519d53d2909868 completed May 3, 2026, 2:02 a.m.
Created at: April 29, 2026, 7:51 p.m.