Build Ontology
When your data finishes importing, RootCause automatically builds an ontology. It scans every dataset, identifies each column's type and role, and maps connections between columns that represent the same concept across different datasets. You do not need to create it — it is ready by the time your data is processed.
What the ontology does
The ontology is the semantic layer that makes everything downstream possible. When "customer_id" in your sales data and "cust_id" in your support data are recognized as the same concept, RootCause can join those datasets automatically. When a column is classified as a Time concept, causal discovery respects temporal ordering. When a column is classified as an Identifier, it is used as a join key rather than treated as a variable in the causal model.
Reviewing your ontology
Open Ontology in the top navigation bar. The Network visualization shows a relationship graph: datasets appear as colored clusters, concepts as labeled nodes, and edges between them show which concepts are shared across sources.
The right panel groups the ontology's actions:
Recommended Datasets — "Ways to combine your sources into datasets ready for analysis and digital twins": joins the platform has detected based on shared identifier concepts. This is the most important panel on the screen — it is the bridge between your ontology and Step 3.
Query your data — search, filter, and combine concepts across datasets. Recent queries are kept in a history list below the button.
Derive — derive a new concept from a SQL formula.
Concept classifications
Concepts can be classified as Identifier, Time, or Location — anything unclassified appears as Entity:
Identifier — unique keys that link records across datasets: Customer ID, Product SKU, Order Number. These serve as join keys and are not used as causal variables.
Time — temporal columns: Order Date, Timestamp, Created At. Defines event ordering for time-series analysis and temporal Digital Twins.
Location — geographic columns: City, Region, Postal Code. Enables location-based filtering and analysis.
Entity — everything without a specific classification: Revenue, Quantity, Churn, Monthly Charges. These are the variables that participate in causal relationships.
The visualization toggle at the top of the Ontology page offers three ways to browse the concepts: Table, Strata, and Network (shown above). A separate Grouping toggle controls how concepts are clustered in the view: by source Dataset, by dataset Links, by ID (identifier), or by Time.
In the graph, the legend distinguishes three kinds of node:
Identifier — a concept used as a key to match records across datasets (Customer ID, SKU). Identifiers are how separate files get linked together.
Concept — a single thing your data measures or describes, like Customer, Revenue, or Timestamp, unified across every dataset that mentions it.
Composite — a concept built by linking identifiers or time dimensions across datasets, so columns from several sources can be used together in one calculation.
Refining your ontology
For most projects the auto-generated ontology is accurate enough to proceed. If a concept has been misclassified, or if two columns that represent the same thing were created as separate concepts, you can correct this at any time — reclassify a concept, merge two into one, or split one that incorrectly combines two different things. Concepts can also carry tags: freeform labels you attach to a concept so that related concepts can be found and treated consistently in analysis.
Export and reset
Two further tools sit at the bottom of the right panel:
Export ontology — download the concept graph as JSON or GraphML, for use in external tools or as a snapshot before making large changes.
Reset ontology — delete all concepts and re-run extraction for the workspace or chosen sources.
Reset is destructive. All manual refinements — reclassifications, merges, groups — are lost when the ontology is re-extracted. Export the ontology first if you want a record. Use reset only when the ontology has drifted too far to repair by hand.
Next step
With the ontology in place, RootCause knows how your datasets connect. Step 3: Build 360 Table walks through creating the single analysis-ready dataset that the causal engine trains on.
Last updated