Triple

T23367409
Position Surface form Disambiguated ID Type / Status
Subject Oerlikon tram depot E593361 entity
Predicate servesDistrict P82 FINISHED
Object Oerlikon 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: Oerlikon | Statement: [Oerlikon tram depot, servesDistrict, Oerlikon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oerlikon
Context triple: [Oerlikon tram depot, servesDistrict, Oerlikon]
  • A. Oerlikon chosen
    Oerlikon is a district in the north of Zurich, Switzerland, known as a major residential, commercial, and transportation hub of the city.
  • B. Oerlikon Contraves
    Oerlikon Contraves is a Swiss defense company renowned for its anti-aircraft and air-defense gun systems used by militaries worldwide.
  • C. Oerlikon Balzers
    Oerlikon Balzers is a global technology company specializing in advanced surface coatings and thin-film solutions for tools, components, and precision parts across various industries.
  • D. Ruhrstahl
    Ruhrstahl was a German armaments manufacturer best known for producing advanced World War II munitions and guided weapons.
  • E. Steyr
    Steyr is a historic industrial city in northern Austria known for its well-preserved old town and long tradition of metalworking and manufacturing.
  • 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_69e25d2593c88190bcdf4a716a94ccb2 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a0ad621881908a909f236e6e9c90 completed April 29, 2026, 6:09 a.m.
Created at: April 17, 2026, 5:32 p.m.