Triple

T277354
Position Surface form Disambiguated ID Type / Status
Subject Power BI E5276 entity
Predicate supportsStandard P1587 FINISHED
Object OLE DB
OLE DB (Object Linking and Embedding, Database) is a Microsoft data access API that provides a uniform way for applications to access data from a wide variety of relational and non-relational data sources.
 E35619 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: OLE DB | Statement: [Power BI, supportsStandard, OLE DB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: OLE DB
Context triple: [Power BI, supportsStandard, OLE DB]
  • A. ODBC
    ODBC (Open Database Connectivity) is a standard API that enables applications to access and query data from a wide variety of relational and non-relational database management systems using a common interface.
  • B. SQL Server
    SQL Server is Microsoft's enterprise-grade relational database management system used for storing, managing, and analyzing data in a wide range of applications.
  • C. SQL
    SQL (Structured Query Language) is a standardized programming language used to manage, query, and manipulate data in relational database management systems.
  • D. IBM DB2
    IBM DB2 is a family of enterprise-grade relational database management systems developed by IBM, widely used for high-performance, scalable data storage and transaction processing across mainframe, distributed, and cloud environments.
  • E. SQLite
    SQLite is a lightweight, self-contained, serverless SQL database engine widely embedded in applications, operating systems, and devices.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: OLE DB
Triple: [Power BI, supportsStandard, OLE DB]
Generated description
OLE DB (Object Linking and Embedding, Database) is a Microsoft data access API that provides a uniform way for applications to access data from a wide variety of relational and non-relational data sources.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: OLE DB
Target entity description: OLE DB (Object Linking and Embedding, Database) is a Microsoft data access API that provides a uniform way for applications to access data from a wide variety of relational and non-relational data sources.
  • A. ODBC chosen
    ODBC (Open Database Connectivity) is a standard API that enables applications to access and query data from a wide variety of relational and non-relational database management systems using a common interface.
  • B. SQL Server
    SQL Server is Microsoft's enterprise-grade relational database management system used for storing, managing, and analyzing data in a wide range of applications.
  • C. SQL
    SQL (Structured Query Language) is a standardized programming language used to manage, query, and manipulate data in relational database management systems.
  • D. IBM DB2
    IBM DB2 is a family of enterprise-grade relational database management systems developed by IBM, widely used for high-performance, scalable data storage and transaction processing across mainframe, distributed, and cloud environments.
  • E. SQLite
    SQLite is a lightweight, self-contained, serverless SQL database engine widely embedded in applications, operating systems, and devices.
  • F. None of above.

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69a257e6c8788190987dfe705ca2912a completed Feb. 28, 2026, 2:50 a.m.
NER Named-entity recognition batch_69a25ded68c88190b1fc595ce329aeb9 completed Feb. 28, 2026, 3:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69a394a13b688190951b070facd01d8c completed March 1, 2026, 1:21 a.m.
NEDg Description generation batch_69a394f7fd408190a1413b03fd664ea6 completed March 1, 2026, 1:23 a.m.
NED2 Entity disambiguation (via description) batch_69a3954367f4819087d9e143d703dff5 completed March 1, 2026, 1:24 a.m.
Created at: Feb. 28, 2026, 2:59 a.m.