Triple

T22975585
Position Surface form Disambiguated ID Type / Status
Subject Apple "Mac vs. PC" campaign E571307 entity
Predicate agency P5602 FINISHED
Object TBWA\Media Arts Lab NE NERFINISHED

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: TBWA\Media Arts Lab | Statement: [Apple "Mac vs. PC" campaign, agency, TBWA\Media Arts Lab]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TBWA\Media Arts Lab
Context triple: [Apple "Mac vs. PC" campaign, agency, TBWA\Media Arts Lab]
  • A. TBWA Worldwide chosen
    TBWA Worldwide is a global advertising agency network known for its disruptive creative campaigns for major brands around the world.
  • B. Wieden+Kennedy
    Wieden+Kennedy is a globally renowned independent advertising agency best known for its groundbreaking creative campaigns for major brands like Nike.
  • C. Wolff Olins
    Wolff Olins is a global brand consultancy known for creating bold and sometimes controversial visual identities for major organizations and events.
  • D. Saatchi & Saatchi
    Saatchi & Saatchi is a global advertising agency network renowned for its creative campaigns and influential role in the modern advertising industry.
  • E. BBDO
    BBDO is a major global advertising agency network known for creating high-profile, award-winning campaigns for leading brands.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245b2c6548190a0e4c7f2f7df2d48 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18235de508190ab9675d005870ff6 completed April 29, 2026, 3:59 a.m.
Created at: April 17, 2026, 3:48 p.m.