Triple

T13903158
Position Surface form Disambiguated ID Type / Status
Subject Longjing tea E334278 entity
Predicate recommendedStorage P8611 FINISHED
Object airtight container 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: airtight container | Statement: [Longjing tea, recommendedStorage, airtight container]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: recommendedStorage
Context triple: [Longjing tea, recommendedStorage, airtight container]
  • A. recommendedLocation
    Indicates that one entity suggests or endorses another entity as a suitable or preferred place for a particular purpose or activity.
  • B. storageOption chosen
    Indicates how or where something is stored, specifying the chosen method, medium, or configuration for its storage.
  • C. recommendedMode
    Indicates that one entity is suggested or advised as the preferred mode, method, or way of doing or experiencing something in relation to another entity.
  • D. commendedFor
    Indicates that one entity has expressed praise or approval toward another entity specifically because of a particular action, quality, or achievement.
  • E. storageOrgan
    Indicates that one entity serves as a storage organ (a specialized structure for storing substances like nutrients or water) for another entity.
  • 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_69d81c5eaa9c819083b1ff8689179565 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de25db1e308190aaed6a21e443cc44 completed April 14, 2026, 11:32 a.m.
PD Predicate disambiguation batch_69dd464b1ab48190ae50bfc902bf6ef7 completed April 13, 2026, 7:38 p.m.
Created at: April 9, 2026, 10:16 p.m.