Triple

T723813
Position Surface form Disambiguated ID Type / Status
Subject UC Berkeley wordmarks E14675 entity
Predicate fileType P8462 FINISHED
Object vector files 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: vector files | Statement: [UC Berkeley wordmarks, fileType, vector files]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: fileType
Context triple: [UC Berkeley wordmarks, fileType, vector files]
  • A. mediaType
    Indicates the format or category of media associated with an entity, such as text, image, audio, or video.
  • B. hasFileFormat chosen
    Indicates that one entity (typically a digital file or resource) is encoded, stored, or represented using a specific file format defined by the other entity.
  • C. dataTransferType
    Indicates the method or mode by which data is transmitted or exchanged between entities.
  • D. frameType
    Indicates the specific structural or categorical kind of frame associated with an entity or relation.
  • E. fieldType
    Indicates the classification or category that defines the nature or kind of a given field within a structure or context.
  • 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_69a4934c753c81909b309027e48b9b3a completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a5a5360c8190b16e1e4f4206d0aa completed March 1, 2026, 8:46 p.m.
PD Predicate disambiguation batch_69a4a4f700cc81908c6de3eedf68433c completed March 1, 2026, 8:43 p.m.
Created at: March 1, 2026, 7:37 p.m.