Triple

T22326901
Position Surface form Disambiguated ID Type / Status
Subject Strømmens Værksted E551923 entity
Predicate acquiredBy P347 FINISHED
Object Adtranz 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: Adtranz | Statement: [Strømmens Værksted, acquiredBy, Adtranz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Adtranz
Context triple: [Strømmens Værksted, acquiredBy, Adtranz]
  • A. ADtranz chosen
    ADtranz was a major European rail engineering company known for designing and manufacturing locomotives, multiple units, and other railway rolling stock before its acquisition by Bombardier.
  • B. Siemens Transportation Systems
    Siemens Transportation Systems is a division of Siemens AG that designs and manufactures rail vehicles and related transportation infrastructure and technologies.
  • C. Hitachi Rail
    Hitachi Rail is a global rail transport and engineering company that designs, manufactures, and maintains trains and railway systems for urban, intercity, and high-speed networks.
  • D. Alstom Juniper
    Alstom Juniper is a family of electric multiple unit trains built by Alstom for use on the British railway network.
  • E. Alstom
    Alstom is a French multinational company that designs, manufactures, and services rail transport equipment and systems, including trains, metros, and signaling solutions.
  • 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_69e11e482f788190b78d1588fc26d606 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f157693460819087c165481eb9e128 completed April 29, 2026, 12:57 a.m.
Created at: April 16, 2026, 8:42 p.m.