Triple

T150106
Position Surface form Disambiguated ID Type / Status
Subject Alfred Nobel E3411 entity
Predicate owned P347 FINISHED
Object Bofors E18029 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: Bofors | Statement: [Alfred Nobel, owned, Bofors]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bofors
Context triple: [Alfred Nobel, owned, Bofors]
  • A. Bofors (as an arms manufacturer) chosen
    Bofors is a Swedish arms manufacturer historically renowned for its artillery and anti-aircraft guns, which played a significant role in 20th-century warfare.
  • B. Erla Maschinenwerk
    Erla Maschinenwerk was a German aircraft manufacturing company best known for producing Messerschmitt fighter planes under license during World War II.
  • C. Rockwell
    Rockwell is an American singer and songwriter best known for his 1984 hit single "Somebody's Watching Me."
  • D. Mauser BK-27 27 mm cannon
    The Mauser BK-27 is a German-designed 27 mm revolver cannon widely used in modern fighter aircraft for high-rate, accurate air-to-air and air-to-ground fire.
  • E. Saab AB
    Saab AB is a Swedish aerospace and defense company known for developing military aircraft, advanced defense systems, and security solutions.
  • 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_69a252868de4819080e21c9938bfe8b6 completed Feb. 28, 2026, 2:27 a.m.
NER Named-entity recognition batch_69a2580dda148190a522e0ac276d5f33 completed Feb. 28, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2c93bbd508190b81527bd95c6e5f4 completed Feb. 28, 2026, 10:53 a.m.
Created at: Feb. 28, 2026, 2:31 a.m.