Triple

T30338347
Position Surface form Disambiguated ID Type / Status
Subject Embeddings from Language Models E771680 entity
Predicate differenceFromStaticEmbeddings P168867 FINISHED
Object context-dependent representations 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: context-dependent representations | Statement: [Embeddings from Language Models, differenceFromStaticEmbeddings, context-dependent representations]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: differenceFromStaticEmbeddings
Context triple: [Embeddings from Language Models, differenceFromStaticEmbeddings, context-dependent representations]
  • A. embeddingType
    Indicates the specific kind or category of embedding representation used to encode an entity or data.
  • B. differenceFromStates
    Indicates that one state or condition is distinct from, or deviates in some way from, another state or condition.
  • C. isDifferenceOf
    Indicates that one quantity or entity represents the result obtained by subtracting one specified quantity or entity from another.
  • D. isDynamicallyDistinctFrom
    Indicates that two entities differ in their behavior, state changes, or evolution over time, even if they may appear similar in static properties.
  • E. differenceFromIFF
    Indicates that two entities differ from each other if and only if a specified condition or set of criteria holds.
  • 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_69f2248aba24819095bb86480d55b23b completed April 29, 2026, 3:32 p.m.
NER Named-entity recognition batch_69f681cf69588190b1a6373ddf29dd6a completed May 2, 2026, 10:59 p.m.
PD Predicate disambiguation batch_69f67603526c81908295a1ece8727c66 completed May 2, 2026, 10:09 p.m.
PDg Predicate description generation batch_69f676f73c3481909f01fa69851b7298 completed May 2, 2026, 10:13 p.m.
Created at: April 29, 2026, 7:55 p.m.