Triple

T5743726
Position Surface form Disambiguated ID Type / Status
Subject Peugeot 301 E126676 entity
Predicate hasFacelift P34431 FINISHED
Object 2017 facelift LITERAL 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: 2017 facelift | Statement: [Peugeot 301, hasFacelift, 2017 facelift]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasFacelift
Context triple: [Peugeot 301, hasFacelift, 2017 facelift]
  • A. faceliftOf
    Indicates that one entity is a redesigned, updated, or cosmetically improved version of another existing entity.
  • B. facelift
    Indicates that an entity undergoes a cosmetic surgical procedure intended to tighten or rejuvenate its facial appearance.
  • C. faceliftFeature
    Indicates that one entity is a specific feature, component, or aspect involved in a facelift procedure or facelift-related modification of the other entity.
  • D. faceliftYear chosen
    Indicates the year in which an entity underwent a significant redesign, update, or cosmetic revision.
  • E. hasFace
    Indicates that one entity possesses, displays, or is characterized by a face.
  • F. None of above.

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_69c0083179548190b384b0bf3c08ca4d completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c02b52663c8190ab44258468d4296d completed March 22, 2026, 5:48 p.m.
PD Predicate disambiguation batch_69c021ca61688190875bd6107161c284 completed March 22, 2026, 5:07 p.m.
Created at: March 22, 2026, 3:48 p.m.