Triple

T8929888
Position Surface form Disambiguated ID Type / Status
Subject Södertälje E212624 entity
Predicate headquartersOf P62 FINISHED
Object Scania AB E37748 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: Scania AB | Statement: [Södertälje, headquartersOf, Scania AB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Scania AB
Context triple: [Södertälje, headquartersOf, Scania AB]
  • A. Scania chosen
    Scania is a Swedish manufacturer renowned for its heavy trucks, buses, and industrial and marine engines.
  • B. Scania
    Scania is a historical province in southern Sweden known for its fertile farmland, coastal landscapes, and former status as part of Denmark.
  • C. Volvo Group
    Volvo Group is a Swedish multinational manufacturing company best known for producing trucks, buses, construction equipment, and marine and industrial engines.
  • D. DAF Trucks
    DAF Trucks is a Dutch manufacturer of commercial vehicles and heavy-duty trucks known for its reliable long-haul and distribution trucks across Europe and beyond.
  • E. Volvo Cars
    Volvo Cars is a Swedish automotive manufacturer known for its focus on safety, practical design, and premium vehicles.
  • 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_69ca8395c438819087d7cb844ab5990c completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6676d5d881908ce78cbb5561a68b completed April 1, 2026, 12:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfba5e887c8190851f2fb533653c6e completed April 3, 2026, 1:02 p.m.
Created at: March 30, 2026, 6:57 p.m.