{ "openapi": "3.0.1", "info": { "title": "🧬 Entity Resolution - Merge Duplicate Records, No Shared ID", "description": "⚡ Find which messy records are the same real-world entity when there is no shared ID. ✅ Fuzzy name/company matching, blocking so 50k records don't need 1.25bn comparisons, probabilistic scoring, transitive clustering.", "version": "1.0", "x-build-id": "Wb9NtpTAARtIUB16F" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/that_red_bird~entity-resolver/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-that_red_bird-entity-resolver", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/that_red_bird~entity-resolver/runs": { "post": { "operationId": "runs-sync-that_red_bird-entity-resolver", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/that_red_bird~entity-resolver/run-sync": { "post": { "operationId": "run-sync-that_red_bird-entity-resolver", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "records": { "title": "Records", "type": "array", "description": "The records to resolve, as an array of flat objects. Combine freely with sourceDatasetIds.", "default": [ { "name": "Jennifer Adams", "company": "Acme Corporation", "email": "jen@acme.com", "phone": "415-555-0100" }, { "name": "Jen Adams", "company": "Acme Corp.", "email": "jen@acme.com", "phone": "" }, { "name": "J. Adams", "company": "ACME, Inc.", "email": "", "phone": "(415) 555 0100" }, { "name": "Michael Chen", "company": "Globex Ltd", "email": "mchen@globex.io", "phone": "212-555-0199" }, { "name": "Mike Chen", "company": "Globex Limited", "email": "mchen@globex.io", "phone": "" } ] }, "sourceDatasetIds": { "title": "Source dataset IDs", "type": "array", "description": "Apify dataset IDs to pull records from. Rows are tagged with their dataset so sourcePriority survivorship can prefer one system over another.", "items": { "type": "string" } }, "fields": { "title": "Fields to compare", "type": "array", "description": "Leave empty to infer from the data. For control pass objects: {\"field\":\"email\",\"type\":\"email\",\"weight\":5}. Types: email, phone, person, company, address, numeric, text, exact. Higher weight = stronger evidence." }, "matchThreshold": { "title": "Match threshold (0-100)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Pairs scoring at or above this are merged. Higher = fewer false merges, more missed duplicates. Expressed 0-100; 85 means 0.85.", "default": 85 }, "reviewThreshold": { "title": "Review threshold (0-100)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Pairs between this and the match threshold are reported for human review instead of being merged. Silently fusing two real entities is worse than missing a duplicate.", "default": 70 }, "maxBlockSize": { "title": "Max block size", "minimum": 10, "maximum": 20000, "type": "integer", "description": "Blocks larger than this are skipped to avoid an O(n²) blowup when many records share a generic key such as a common email domain.", "default": 500 }, "survivorshipStrategy": { "title": "Which value wins", "enum": [ "mostComplete", "longest", "mostCommon", "newest", "first", "sourcePriority" ], "type": "string", "description": "Default rule for building the golden record from a cluster.", "default": "mostComplete" }, "fieldStrategies": { "title": "Per-field survivorship overrides", "type": "object", "description": "Override the rule for specific fields, e.g. {\"email\":\"newest\",\"company\":\"longest\"}." }, "dateField": { "title": "Date field", "type": "string", "description": "Field holding a record's last-updated date. Required by the \"newest\" strategy." }, "sourceField": { "title": "Source field", "type": "string", "description": "Field naming the record's origin system. Defaults to the automatic _source tag." }, "sourcePriority": { "title": "Source priority order", "type": "array", "description": "Most trusted source first, e.g. [\"crm\",\"webform\"]. Used by the sourcePriority strategy.", "items": { "type": "string" } }, "outputMode": { "title": "Output mode", "enum": [ "entities", "golden", "duplicates" ], "type": "string", "description": "entities = full clusters with members and provenance · golden = one clean row per entity · duplicates = only clusters that actually merged.", "default": "entities" }, "includeReviewPairs": { "title": "Include review pairs", "type": "boolean", "description": "Emit ambiguous pairs with their evidence so a human can decide.", "default": true }, "includeScoredPairs": { "title": "Include every scored pair", "type": "boolean", "description": "Emit all compared pairs with per-field similarity. Useful for tuning thresholds; verbose on large inputs.", "default": false } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }