Triple

T4734346
Position Surface form Disambiguated ID Type / Status
Subject Peugeot 308 E105086 entity
Predicate competitor P1375 FINISHED
Object Ford Focus E392697 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: Ford Focus | Statement: [Peugeot 308, competitor, Ford Focus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ford Focus
Context triple: [Peugeot 308, competitor, Ford Focus]
  • A. Ford Focus chosen
    The Ford Focus is a popular compact car known for its agile handling, practicality, and strong sales in global markets.
  • B. Ford Fiesta
    The Ford Fiesta is a popular supermini/subcompact car produced by Ford, known for its practicality, efficiency, and wide appeal in urban and everyday driving.
  • C. Ford Mondeo
    The Ford Mondeo is a mid-size family car produced by Ford, known for its practicality, comfort, and strong presence in the European market.
  • D. Ford Fusion
    The Ford Fusion is a mid-size sedan produced by Ford, known for its mainstream appeal, fuel-efficient powertrains, and role as one of the brand’s core passenger cars in the 2000s and 2010s.
  • E. Ford Escape
    The Ford Escape is a compact crossover SUV produced by Ford, known for its family-friendly practicality, car-like handling, and broad range of engine and technology options.
  • 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_69bd43ee52048190b81a4f066534ffb3 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6467a1fc819089485b4d76e0edc4 completed March 20, 2026, 3:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69be10b0b8d08190ad1cd262ee870f08 completed March 21, 2026, 3:29 a.m.
Created at: March 20, 2026, 1:19 p.m.