Triple

T11630884
Position Surface form Disambiguated ID Type / Status
Subject Bernhard Scholz E276392 entity
Predicate notableWork P4 FINISHED
Object Soufflé Datalog engine E938555 NE FINISHED

How this triple was built (2 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: Soufflé Datalog engine | Statement: [Bernhard Scholz, notableWork, Soufflé Datalog engine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Soufflé Datalog engine
Context triple: [Bernhard Scholz, notableWork, Soufflé Datalog engine]
  • A. Soufflé Datalog engine chosen
    Soufflé Datalog engine is a high-performance, open-source Datalog compiler and analysis framework widely used for static program analysis and other logic-based data processing tasks.
  • B. DLV
    DLV is the commonly used abbreviation for the German Athletics Association, the national governing body for athletics in Germany.
  • C. Practical Aspects of Declarative Languages
    Practical Aspects of Declarative Languages is an academic conference focused on the practical implementation, application, and evaluation of declarative programming languages and related technologies.
  • D. SPICE in-memory engine
    SPICE in-memory engine is Amazon QuickSight’s high-performance, columnar, in-memory data store designed to enable fast, scalable, and interactive analytics on large datasets.
  • 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.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6aafa51148190ab84940694c00235 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a127b2688190ae3a340f851e834b completed April 10, 2026, 7:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69ef135cde4881908d1cf9f752592d60 completed April 27, 2026, 7:42 a.m.
Created at: April 8, 2026, 9:39 p.m.