Triple

T881135
Position Surface form Disambiguated ID Type / Status
Subject Saab 96 E19028 entity
Predicate notableDriver P2087 FINISHED
Object Erik Carlsson E102362 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: Erik Carlsson | Statement: [Saab 96, notableDriver, Erik Carlsson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Erik Carlsson
Context triple: [Saab 96, notableDriver, Erik Carlsson]
  • A. Erik Carlsson chosen
    Erik Carlsson was a legendary Swedish rally driver famed for his success in international competitions during the 1950s and 1960s, particularly with Saab.
  • B. Allan Larsson
    Allan Larsson is a Swedish entrepreneur and software developer best known for co-founding and helping create the MySQL relational database system.
  • C. Tobias Enström
    Tobias Enström is a Swedish former professional ice hockey defenseman best known for his puck-moving skills and long tenure in the NHL with the Atlanta Thrashers/Winnipeg Jets.
  • D. Johan Nordström
    Johan Nordström, better known as John W. Nordstrom, was a Swedish-American businessman who co-founded the upscale department store chain Nordstrom in the United States.
  • E. Jon Ekstrand
    Jon Ekstrand is a Swedish film composer and sound designer known for his atmospheric scores for documentaries and feature films, including collaborations with director Daniel Espinosa.
  • 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_69a4939c32488190a7ccd41cf0abb22b completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b2b8063081909566c404ca63a29e completed March 1, 2026, 9:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac2a0d31e8819091d3402546d8fa33 completed March 7, 2026, 1:37 p.m.
Created at: March 1, 2026, 7:39 p.m.