Triple

T9226902
Position Surface form Disambiguated ID Type / Status
Subject Ford Fusion E221705 entity
Predicate competitor P1375 FINISHED
Object Hyundai Sonata E196142 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: Hyundai Sonata | Statement: [Ford Fusion, competitor, Hyundai Sonata]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hyundai Sonata
Context triple: [Ford Fusion, competitor, Hyundai Sonata]
  • A. Hyundai Sonata chosen
    The Hyundai Sonata is a popular mid-size family sedan known for its value, modern styling, and extensive features.
  • B. Hyundai Elantra
    The Hyundai Elantra is a compact sedan known for its value-oriented pricing, fuel efficiency, and extensive features, competing with popular models like the Honda Civic.
  • C. Kia Optima
    The Kia Optima is a midsize family sedan known for its value, modern styling, and generous features.
  • D. Hyundai Santa Fe
    The Hyundai Santa Fe is a popular mid-size crossover SUV known for its practicality, comfort, and value-oriented features.
  • E. Hyundai Accent
    The Hyundai Accent is a subcompact car produced by the South Korean automaker Hyundai, known for its affordability, fuel efficiency, and practicality as an entry-level vehicle.
  • 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_69ca83ec8db08190a9110df8232885d2 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccda9ecef48190b8aa0e316d07cec7 completed April 1, 2026, 8:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69d066521f288190a54b1199284db7a4 completed April 4, 2026, 1:16 a.m.
Created at: March 30, 2026, 7:28 p.m.