Triple

T5607653
Position Surface form Disambiguated ID Type / Status
Subject Milo E147271 entity
Predicate introducedBy P513 FINISHED
Object Nestlé Australia E27582 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: Nestlé Australia | Statement: [Milo, introducedBy, Nestlé Australia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nestlé Australia
Context triple: [Milo, introducedBy, Nestlé Australia]
  • A. Nestlé chosen
    Nestlé is a Swiss multinational food and beverage conglomerate and one of the world’s largest consumer goods companies.
  • B. Cadbury Schweppes
    Cadbury Schweppes was a major British multinational confectionery and soft drinks company known for brands like Cadbury chocolate and Schweppes beverages.
  • C. Lindt & Sprüngli
    Lindt & Sprüngli is a Swiss premium chocolate and confectionery manufacturer renowned worldwide for its high-quality chocolate bars, pralines, and seasonal specialties.
  • D. Nestlé Waters
    Nestlé Waters is the bottled water division of Nestlé, responsible for producing and marketing a wide portfolio of still and sparkling water brands worldwide.
  • E. Ezaki Glico Co., Ltd.
    Ezaki Glico Co., Ltd. is a Japanese confectionery and food company best known for products like Pocky and Pretz, as well as its iconic advertising presence in Osaka.
  • 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_69c0090500f881908374285baf0ac46f completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c020fd1b2c81908da154f7e11b90d8 completed March 22, 2026, 5:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69c669cd6bb08190966b89a2129f5738 completed March 27, 2026, 11:28 a.m.
Created at: March 22, 2026, 3:39 p.m.