What kinds of entities are most important to extract in ecommerce support?

Order numbers, tracking numbers, product names, SKUs, email addresses, dates, and monetary amounts cover the vast majority of ecommerce support use cases. Brand-specific entities — loyalty tier names, subscription plan labels, custom product identifiers — are worth adding for stores where those are common in support conversations.

What happens if entity extraction misidentifies something?

The downstream action is likely wrong — looking up the wrong order, responding about the wrong product. Well-designed systems confirm extracted entities before taking action on them: 'I see order #1023. Is that the order you're asking about?' prevents acting on an extraction error.

Can entity extraction handle variations in how customers write order numbers?

Yes — modern extractors handle format variations (with or without hashes, dashes, spaces) and can be trained on your store's specific order number format. Bookbag also cross-references extracted order numbers against your Shopify data to verify they're valid before using them.

Glossary

Entity Extraction

Entity extraction is the AI process of identifying and pulling specific, structured pieces of information from a customer's free-form message — such as order numbers, product names, email addresses, delivery dates, or monetary amounts — making that data available for downstream actions like order lookups, ticket creation, or personalized responses.

Book a demo See pricing

What it means

Key insight

Entity extraction is what lets an AI read 'I never got order #1023' and immediately look up that order — without asking the customer to fill out a form.

When a customer contacts support, their message often contains specific data points the support system needs: an order number, a product SKU, a shipping address, a date, an amount. Entity extraction is the task of automatically identifying and structuring those data points from free-form text. In traditional support workflows, agents manually copy order numbers from messages into lookup tools. AI entity extraction does this automatically: the system reads 'I never received order 1023-B that I placed on March 12' and extracts {order_id: '1023-B', event_date: 'March 12'} as structured data, immediately usable for an API call to Shopify to retrieve that order. The combination of entity extraction with intent classification is what enables true end-to-end AI resolution: the intent tells the system what to do, the extracted entities provide the data needed to do it.

Why it matters

Every question an AI has to ask a customer to get information it could have extracted from the original message is unnecessary friction. 'Can I get your order number?' when the order number was in the first message is a failure of entity extraction that delays resolution and erodes trust in the AI. For Shopify merchants, strong entity extraction means the AI can immediately look up the specific order, product, or account the customer is asking about — delivering a personalized, accurate response rather than a generic one that requires a follow-up exchange.

How Bookbag helps

Shopify-Aware Entity Recognition

Bookbag recognizes Shopify-specific entity formats — order IDs, tracking numbers, variant SKUs, discount codes — and maps them directly to Shopify API lookups without additional configuration.

Contextual Entity Resolution

When a customer references 'my last order' rather than a specific order number, Bookbag resolves the reference using account history and conversation context — extracting the intended entity even when it's implicit.

Multi-Entity Extraction

Bookbag extracts all relevant entities from a message simultaneously — order number, product name, and date in one pass — so the full context is available for the downstream action without multiple follow-up questions.

Frequently Asked Questions

See Bookbag in action

Join the ecommerce teams resolving more tickets, answering 24/7, and turning support into a revenue channel with Bookbag.