Triple

T19997796
Position Surface form Disambiguated ID Type / Status
Subject UserLand Software E494240 entity
Predicate developed P73 FINISHED
Object Frontier object database — NE NERFINISHED

How this triple was built (3 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: Frontier object database | Statement: [UserLand Software, developed, Frontier object database]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Frontier object database
Context triple: [UserLand Software, developed, Frontier object database]
  • A. Gamma parallel database system project
    The Gamma parallel database system project was an influential research initiative in the 1980s that pioneered techniques for scalable, high-performance parallel relational database processing.
  • B. H-Store
    H-Store is a pioneering in-memory, distributed OLTP database system designed for high-throughput transaction processing on modern multicore hardware.
  • C. Wisconsin Benchmark for database systems
    The Wisconsin Benchmark for database systems is a pioneering performance evaluation suite developed to systematically compare and analyze relational database management systems under various workloads.
  • D. “The Design and Implementation of INGRES”
    “The Design and Implementation of INGRES” is a seminal technical book that documents the architecture, design decisions, and implementation details of the pioneering INGRES relational database system.
  • E. INGRES relational database system
    INGRES relational database system is an influential early relational DBMS developed at the University of California, Berkeley, that pioneered many concepts and technologies later adopted by commercial database systems.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Frontier object database
Target entity description: Frontier object database is a hierarchical, scriptable database system created by UserLand Software, best known for powering early web content management and scripting applications.
  • A. Gamma parallel database system project
    The Gamma parallel database system project was an influential research initiative in the 1980s that pioneered techniques for scalable, high-performance parallel relational database processing.
  • B. H-Store
    H-Store is a pioneering in-memory, distributed OLTP database system designed for high-throughput transaction processing on modern multicore hardware.
  • C. Wisconsin Benchmark for database systems
    The Wisconsin Benchmark for database systems is a pioneering performance evaluation suite developed to systematically compare and analyze relational database management systems under various workloads.
  • D. “The Design and Implementation of INGRES”
    “The Design and Implementation of INGRES” is a seminal technical book that documents the architecture, design decisions, and implementation details of the pioneering INGRES relational database system.
  • E. INGRES relational database system
    INGRES relational database system is an influential early relational DBMS developed at the University of California, Berkeley, that pioneered many concepts and technologies later adopted by commercial database systems.
  • F. None of above. chosen

Provenance (2 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_69da626b2d748190886981ea90c8b2ea completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65fe6827481909469129feb9aad91 completed April 20, 2026, 5:18 p.m.
Created at: April 11, 2026, 3:32 p.m.