Triple

T7977372
Position Surface form Disambiguated ID Type / Status
Subject Ivar Jacobson E185479 entity
Predicate founded P104 FINISHED
Object Objectory AB E699659 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: Objectory AB | Statement: [Ivar Jacobson, founded, Objectory AB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Objectory AB
Context triple: [Ivar Jacobson, founded, Objectory AB]
  • A. Objectory AB chosen
    Objectory AB was a Swedish software company known for developing and commercializing the Objectory method, an early object-oriented software engineering approach later integrated into the Rational Unified Process.
  • B. Innobase Oy
    Innobase Oy is a Finnish software company best known for creating the InnoDB transactional storage engine used in MySQL databases.
  • C. Pandox AB
    Pandox AB is a Swedish hotel property company that owns and manages a large portfolio of hotel real estate across Europe.
  • D. Blocket AB
    Blocket AB is a Swedish online classifieds marketplace company best known for its popular platform for buying and selling second-hand goods.
  • E. Intility AS
    Intility AS is a Norwegian IT company that provides cloud-based platform and infrastructure services to businesses.
  • 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_69ca829851908190b4e03829353ee7c3 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3bf716508190b4245bd5d89ae8c4 completed March 31, 2026, 3:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc5677968881908835169157244962 completed March 31, 2026, 11:19 p.m.
Created at: March 30, 2026, 5:14 p.m.