Triple

T18204309
Position Surface form Disambiguated ID Type / Status
Subject DistilBERT E435865 entity
Predicate performanceRetention P130210 FINISHED
Object retains about 97 percent of BERT base performance on GLUE 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: retains about 97 percent of BERT base performance on GLUE | Statement: [DistilBERT, performanceRetention, retains about 97 percent of BERT base performance on GLUE]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: performanceRetention
Context triple: [DistilBERT, performanceRetention, retains about 97 percent of BERT base performance on GLUE]
  • A. retentionMethod
    Indicates the method or strategy used to retain or keep something (such as data, customers, or resources) over time.
  • B. supportsPersistence
    Indicates that one entity enables or provides the capability for another entity’s data or state to be stored and retained over time.
  • C. dataRetentionPeriod
    Indicates the length of time data is stored or kept before it is deleted, archived, or otherwise disposed of.
  • D. retained
    Indicates that one entity keeps possession, control, or continued engagement of another entity over a period of time.
  • E. permanence
    Indicates that a state, condition, or relationship continues to hold over time without significant change or interruption.
  • F. None of above. chosen

Provenance (4 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_69d8b90dba6481908e119eb9aa4ca0cb completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e222831081908f7d5500424e3acb completed April 19, 2026, 2:09 p.m.
PD Predicate disambiguation batch_69e4332155d88190b106d0dceb4554af completed April 19, 2026, 1:42 a.m.
PDg Predicate description generation batch_69e438f684e48190b38c64b58c518b6a completed April 19, 2026, 2:07 a.m.
Created at: April 10, 2026, 10:32 a.m.