Triple

T2374404
Position Surface form Disambiguated ID Type / Status
Subject Alexander Melville Bell E46162 entity
Predicate developed P73 FINISHED
Object Visible Speech alphabet
The Visible Speech alphabet is a 19th-century phonetic writing system that represents the physical positions and movements of the speech organs to visually depict spoken sounds.
E260096 NE FINISHED

How this triple was built (4 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: Visible Speech alphabet | Statement: [Alexander Melville Bell, developed, Visible Speech alphabet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Visible Speech alphabet
Context triple: [Alexander Melville Bell, developed, Visible Speech alphabet]
  • A. Versoix
    Versoix is a Swiss municipality on the shores of Lake Geneva, known as a residential suburb of Geneva with lakeside promenades and a mix of urban and natural landscapes.
  • B. Speech Analysis, Synthesis and Perception
    "Speech Analysis, Synthesis and Perception" is a foundational technical book that systematically explores the theory, modeling, and processing of human speech signals for analysis, synthesis, and recognition.
  • C. Hearsay speech understanding system
    The Hearsay speech understanding system is an early, influential AI project that pioneered blackboard architectures for integrating multiple knowledge sources in continuous speech recognition.
  • D. Glottolog
    Glottolog is a comprehensive bibliographic and classification database of the world’s languages and dialects, maintained by linguists at the Max Planck Institute.
  • E. WaveGlow
    WaveGlow is a flow-based generative neural network model for fast, high-quality text-to-speech audio synthesis.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Visible Speech alphabet
Triple: [Alexander Melville Bell, developed, Visible Speech alphabet]
Generated description
The Visible Speech alphabet is a 19th-century phonetic writing system that represents the physical positions and movements of the speech organs to visually depict spoken sounds.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Visible Speech alphabet
Target entity description: The Visible Speech alphabet is a 19th-century phonetic writing system that represents the physical positions and movements of the speech organs to visually depict spoken sounds.
  • A. Versoix
    Versoix is a Swiss municipality on the shores of Lake Geneva, known as a residential suburb of Geneva with lakeside promenades and a mix of urban and natural landscapes.
  • B. Speech Analysis, Synthesis and Perception
    "Speech Analysis, Synthesis and Perception" is a foundational technical book that systematically explores the theory, modeling, and processing of human speech signals for analysis, synthesis, and recognition.
  • C. Hearsay speech understanding system
    The Hearsay speech understanding system is an early, influential AI project that pioneered blackboard architectures for integrating multiple knowledge sources in continuous speech recognition.
  • D. Glottolog
    Glottolog is a comprehensive bibliographic and classification database of the world’s languages and dialects, maintained by linguists at the Max Planck Institute.
  • E. WaveGlow
    WaveGlow is a flow-based generative neural network model for fast, high-quality text-to-speech audio synthesis.
  • F. None of above. chosen

Provenance (5 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_69a88a145268819083e2736cb835c696 completed March 4, 2026, 7:37 p.m.
NER Named-entity recognition batch_69abc791c4688190a4b8f0e540e84eb4 completed March 7, 2026, 6:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69aea8a8c2b88190a18dbf35d745958f completed March 9, 2026, 11:02 a.m.
NEDg Description generation batch_69aea92cc66c81909a46b83200960fe2 completed March 9, 2026, 11:04 a.m.
NED2 Entity disambiguation (via description) batch_69aea9b8dff08190a09f0c965dfd6738 completed March 9, 2026, 11:06 a.m.
Created at: March 4, 2026, 7:56 p.m.