Triple

T36490176
Position Surface form Disambiguated ID Type / Status
Subject Neural Machine Translation by Jointly Learning to Align and Translate E899030 entity
Predicate attentionAggregation P185597 FINISHED
Object weighted sum of encoder hidden states 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: weighted sum of encoder hidden states | Statement: [Neural Machine Translation by Jointly Learning to Align and Translate, attentionAggregation, weighted sum of encoder hidden states]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: attentionAggregation
Context triple: [Neural Machine Translation by Jointly Learning to Align and Translate, attentionAggregation, weighted sum of encoder hidden states]
  • A. attentionScoreFunction chosen
    Indicates a function that quantifies the level or distribution of attention given to entities or interactions.
  • B. focusTrait
    Indicates that one entity is characterized by, or primarily associated with, a particular trait or attribute of another entity.
  • C. hasAttentionPattern
    Indicates that one entity exhibits a specific, identifiable pattern of attention or focus directed toward another entity or stimulus.
  • D. focusMode
    Indicates that an entity is currently in a concentrated or distraction-minimized state directed toward a specific task, target, or context.
  • E. focusTheory
    Indicates that one entity serves as the primary theoretical framework, perspective, or model that another entity is based on, organized around, or chiefly concerned with.
  • 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_69f76e5ad4588190bdbce60c52fbb785 completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_69f7c371931c8190afb1d4dd5157f92c completed May 3, 2026, 9:51 p.m.
PD Predicate disambiguation batch_69f7c1b91fd88190ab85afd626603769 completed May 3, 2026, 9:44 p.m.
Created at: May 3, 2026, 4:10 p.m.