Dontopedia

Intent Precision

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-11.)

Intent Precision has 9 facts recorded in Dontopedia across 3 references, with 1 live disagreement.

9 facts·6 predicates·3 sources·1 in dispute

Mostly:rdf:type(3), has value(1), has unit(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (9)

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.

contentContainsContent Contains(2)

measuresMeasures(2)

mentionsMentions(2)

attemptingToOptimizeAttempting to Optimize(1)

evaluatesEvaluates(1)

targetMetricTarget Metric(1)

Other facts (8)

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.

8 facts
PredicateValueRef
Rdf:typeMetric[1]
Rdf:typeMetric[2]
Rdf:typeMetric[3]
Has Value88[1]
Has Unitpercent[1]
Applies toLlm Prompts[1]
Measured inExperiment[3]
Target Value88%[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/c0dac4b7-a8bf-4fc4-b8c0-172938ac7e75
ex:Metric
hasValuebeam/c0dac4b7-a8bf-4fc4-b8c0-172938ac7e75
88
hasUnitbeam/c0dac4b7-a8bf-4fc4-b8c0-172938ac7e75
percent
appliesTobeam/c0dac4b7-a8bf-4fc4-b8c0-172938ac7e75
ex:LLM-prompts
typebeam/d307a23c-1866-4ea9-9a82-42827b961a77
ex:Metric
typebeam/5da37977-83e8-48be-bdd8-808083c26ac7
ex:Metric
labelbeam/5da37977-83e8-48be-bdd8-808083c26ac7
Intent Precision
measuredInbeam/5da37977-83e8-48be-bdd8-808083c26ac7
ex:experiment
targetValuebeam/5da37977-83e8-48be-bdd8-808083c26ac7
88%

References (3)

3 references
  1. ctx:claims/beam/c0dac4b7-a8bf-4fc4-b8c0-172938ac7e75
    • full textbeam-chunk
      text/plain1 KBdoc:beam/c0dac4b7-a8bf-4fc4-b8c0-172938ac7e75
      Show excerpt
      [Turn 10470] User: I'm trying to optimize the intent precision of my LLM prompts, and I've been experimenting with different context weights. Currently, I'm achieving 88% intent precision on 2,500 test queries, but I want to improve it furt
  2. ctx:claims/beam/d307a23c-1866-4ea9-9a82-42827b961a77
    • full textbeam-chunk
      text/plain1 KBdoc:beam/d307a23c-1866-4ea9-9a82-42827b961a77
      Show excerpt
      context_weights['system_state'] = combo[2] context_weights['external_data_sources'] = combo[3] # Ensure the sum of weights equals 1 total_weight = sum(context_weights.values()) normalized_weights = {k: v / total_wei
  3. ctx:claims/beam/5da37977-83e8-48be-bdd8-808083c26ac7

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.