Triple

T21005596
Position Surface form Disambiguated ID Type / Status
Subject Keller und Knappich Augsburg E517405 entity
Predicate historicalNameOf P65 FINISHED
Object KUKA NE NERFINISHED

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: KUKA | Statement: [Keller und Knappich Augsburg, historicalNameOf, KUKA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KUKA
Context triple: [Keller und Knappich Augsburg, historicalNameOf, KUKA]
  • A. KUKA chosen
    KUKA is a German industrial robotics and automation company known for its advanced robotic arms used in manufacturing and entertainment applications.
  • B. ABB Robotics
    ABB Robotics is a leading global provider of industrial robots and automation solutions used across manufacturing, logistics, and other industries.
  • C. Festo SE & Co. KG
    Festo SE & Co. KG is a German multinational company specializing in automation technology and industrial control solutions, particularly pneumatic and electric drive systems.
  • D. Kinetix
    Kinetix is Rockwell Automation’s line of motion control products and servo drives used for precise, integrated industrial automation.
  • E. Ibaraki Robots
    Ibaraki Robots is a professional Japanese basketball team based in Ibaraki Prefecture that competes in the B.League.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69e0b50192308190a284fcc89dd23a49 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fc3b25ec8190aa4530d1f0bb2b9e completed April 21, 2026, 4:25 a.m.
Created at: April 16, 2026, 1:52 p.m.