Triple

T13893971
Position Surface form Disambiguated ID Type / Status
Subject Hadamard matrix E334040 entity
Predicate usedIn P98 FINISHED
Object Walsh–Hadamard transform
The Walsh–Hadamard transform is an orthogonal, non-sinusoidal signal transform that decomposes data into a basis of square-wave-like functions, widely used in communications, coding theory, and signal processing.
E1067314 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: Walsh–Hadamard transform | Statement: [Hadamard matrix, usedIn, Walsh–Hadamard transform]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Walsh–Hadamard transform
Context triple: [Hadamard matrix, usedIn, Walsh–Hadamard transform]
  • A. Haar wavelet
    The Haar wavelet is the simplest and oldest wavelet function, used as a basic building block in wavelet analysis for representing signals with abrupt changes.
  • B. Modified Discrete Cosine Transform
    Modified Discrete Cosine Transform is a lapped transform widely used in audio coding and compression (e.g., MP3, AAC) to efficiently represent overlapping time-domain signals in the frequency domain with reduced artifacts.
  • C. Hilbert transform
    The Hilbert transform is an integral transform that produces the harmonic conjugate of a real-valued function, playing a central role in signal processing, harmonic analysis, and the theory of analytic signals.
  • D. Cooley–Tukey Fast Fourier Transform algorithm
    The Cooley–Tukey Fast Fourier Transform algorithm is a widely used, efficient method for computing the discrete Fourier transform that revolutionized digital signal processing and numerical analysis.
  • E. Daubechies wavelets
    Daubechies wavelets are a family of compactly supported orthogonal wavelets widely used in signal processing and image compression for their efficient time-frequency localization.
  • 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: Walsh–Hadamard transform
Triple: [Hadamard matrix, usedIn, Walsh–Hadamard transform]
Generated description
The Walsh–Hadamard transform is an orthogonal, non-sinusoidal signal transform that decomposes data into a basis of square-wave-like functions, widely used in communications, coding theory, and signal processing.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Walsh–Hadamard transform
Target entity description: The Walsh–Hadamard transform is an orthogonal, non-sinusoidal signal transform that decomposes data into a basis of square-wave-like functions, widely used in communications, coding theory, and signal processing.
  • A. Haar wavelet
    The Haar wavelet is the simplest and oldest wavelet function, used as a basic building block in wavelet analysis for representing signals with abrupt changes.
  • B. Modified Discrete Cosine Transform
    Modified Discrete Cosine Transform is a lapped transform widely used in audio coding and compression (e.g., MP3, AAC) to efficiently represent overlapping time-domain signals in the frequency domain with reduced artifacts.
  • C. Hilbert transform
    The Hilbert transform is an integral transform that produces the harmonic conjugate of a real-valued function, playing a central role in signal processing, harmonic analysis, and the theory of analytic signals.
  • D. Cooley–Tukey Fast Fourier Transform algorithm
    The Cooley–Tukey Fast Fourier Transform algorithm is a widely used, efficient method for computing the discrete Fourier transform that revolutionized digital signal processing and numerical analysis.
  • E. Daubechies wavelets
    Daubechies wavelets are a family of compactly supported orthogonal wavelets widely used in signal processing and image compression for their efficient time-frequency localization.
  • 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_69d81c5dd2d48190b7a5fc1e009de936 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de23a741908190bdf46d76c5f1411a completed April 14, 2026, 11:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c71ca8a881908ac02687fbfe62fb completed May 3, 2026, 10:07 p.m.
NEDg Description generation batch_69f7c7e1247481908073c1e282c3619f completed May 3, 2026, 10:10 p.m.
NED2 Entity disambiguation (via description) batch_69f7c8f5675c8190906f37cee6d8c493 completed May 3, 2026, 10:15 p.m.
Created at: April 9, 2026, 10:15 p.m.