Triple

T5368780
Position Surface form Disambiguated ID Type / Status
Subject Peugeot 5008 E108793 entity
Predicate relatedModel P37 FINISHED
Object Peugeot 3008 E106567 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: Peugeot 3008 | Statement: [Peugeot 5008, relatedModel, Peugeot 3008]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peugeot 3008
Context triple: [Peugeot 5008, relatedModel, Peugeot 3008]
  • A. Peugeot 3008 chosen
    The Peugeot 3008 is a compact crossover SUV known for its distinctive design, practical interior, and advanced technology features.
  • B. Peugeot 5008
    The Peugeot 5008 is a mid-size crossover SUV, originally launched as an MPV, known for its seven-seat practicality and modern French styling.
  • C. Peugeot 2008
    The Peugeot 2008 is a subcompact crossover SUV produced by the French automaker Peugeot, known for its urban-friendly size, modern styling, and efficient engines.
  • D. Peugeot 308
    The Peugeot 308 is a compact family hatchback produced by the French automaker Peugeot, known for its stylish design, efficient engines, and comfortable ride.
  • E. Peugeot 508
    The Peugeot 508 is a mid-size family car produced by the French automaker Peugeot, known for its sleek design, comfortable ride, and range of efficient engines.
  • 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_69bd440c77948190aad2a5f39b7b80f5 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd86856f688190a34ab93619bae134 completed March 20, 2026, 5:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf292c4d1c819088f7b977ac212688 completed March 21, 2026, 11:26 p.m.
Created at: March 20, 2026, 2:02 p.m.