Dontopedia

Construction Phase

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-07.)

Construction Phase has 13 facts recorded in Dontopedia across 4 references, with 2 live disagreements.

13 facts·9 predicates·4 sources·2 in dispute

Mostly:rdf:type(4), uses(2), compared to(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (7)

Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.

hasPhaseHas Phase(3)

phasePhase(3)

controlsPhaseControls Phase(1)

Other facts (13)

The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.

13 facts
PredicateValueRef
Rdf:typeIndex Phase[1]
Rdf:typeAlgorithmic Phase[2]
Rdf:typeIndex Phase[3]
Rdf:typeIndex Building Phase[4]
UsesM Parameter[1]
UsesEf Construction Parameter[1]
Compared toIvfpq[2]
Has PropertySlower Than Ivfpq[2]
Is Slower forHnsw[2]
Is Part ofHnsw[2]
PrecedesSearch Phase[3]
RequiresTraining Data[3]
Has ParameterEf Construction[3]

Timeline

Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.

typebeam/42a434b2-95aa-4616-a1af-a5af03a4baf6
ex:IndexPhase
usesbeam/42a434b2-95aa-4616-a1af-a5af03a4baf6
ex:M-parameter
usesbeam/42a434b2-95aa-4616-a1af-a5af03a4baf6
ex:efConstruction-parameter
typebeam/a4f328d2-64d4-4628-9ccd-e5fcf0511f60
ex:Algorithmic-Phase
comparedTobeam/a4f328d2-64d4-4628-9ccd-e5fcf0511f60
ex:ivfpq
hasPropertybeam/a4f328d2-64d4-4628-9ccd-e5fcf0511f60
ex:slower-than-ivfpq
isSlowerForbeam/a4f328d2-64d4-4628-9ccd-e5fcf0511f60
ex:hnsw
isPartOfbeam/a4f328d2-64d4-4628-9ccd-e5fcf0511f60
ex:hnsw
typebeam/8e356af0-5214-4a1f-8615-f270ae5ec1c9
ex:IndexPhase
precedesbeam/8e356af0-5214-4a1f-8615-f270ae5ec1c9
ex:search-phase
requiresbeam/8e356af0-5214-4a1f-8615-f270ae5ec1c9
ex:training-data
hasParameterbeam/8e356af0-5214-4a1f-8615-f270ae5ec1c9
ex:efConstruction
typebeam/df24a991-d039-4192-a12c-a5c3848a597a
ex:IndexBuildingPhase

References (4)

4 references
  1. ctx:claims/beam/42a434b2-95aa-4616-a1af-a5af03a4baf6
    • full textbeam-chunk
      text/plain1 KBdoc:beam/42a434b2-95aa-4616-a1af-a5af03a4baf6
      Show excerpt
      Here's an example using the `IndexHNSW` index, which is more scalable and efficient for large datasets: ```python import numpy as np import faiss # Assuming I have a dataset of vectors vectors = np.random.rand(1000, 128).astype('float32')
  2. ctx:claims/beam/a4f328d2-64d4-4628-9ccd-e5fcf0511f60
    • full textbeam-chunk
      text/plain1 KBdoc:beam/a4f328d2-64d4-4628-9ccd-e5fcf0511f60
      Show excerpt
      [Turn 1968] User: hmm, which indexing method would you say is more suitable for real-time search applications? [Turn 1969] Assistant: For real-time search applications, the choice of indexing method in FAISS depends on the specific require
  3. ctx:claims/beam/8e356af0-5214-4a1f-8615-f270ae5ec1c9
    • full textbeam-chunk
      text/plain1 KBdoc:beam/8e356af0-5214-4a1f-8615-f270ae5ec1c9
      Show excerpt
      - `efConstruction` and `efSearch` parameters control the construction and search phases, respectively. 2. **IVFPQ Index**: - `IndexIVFPQ`: Creates an IVFPQ index with a specified number of clusters (`nlist`), subquantizers (`m`), and
  4. ctx:claims/beam/df24a991-d039-4192-a12c-a5c3848a597a
    • full textbeam-chunk
      text/plain1 KBdoc:beam/df24a991-d039-4192-a12c-a5c3848a597a
      Show excerpt
      By following these steps, you can leverage FAISS to efficiently handle large-scale similarity searches, reducing memory usage and improving search times. [Turn 4870] User: I'm trying to integrate Annoy 1.17.3 for similarity search in my pr

See also

Keep researching

Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.