Triple

T6313581
Position Surface form Disambiguated ID Type / Status
Subject Pepsi Max E141561 entity
Predicate hasVariant P455 FINISHED
Object Pepsi Max Cherry
Pepsi Max Cherry is a cherry-flavored, sugar-free cola variant of Pepsi Max marketed as a low-calorie soft drink.
E583821 NE FINISHED

How this triple was built (4 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: Pepsi Max Cherry | Statement: [Pepsi Max, hasVariant, Pepsi Max Cherry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pepsi Max Cherry
Context triple: [Pepsi Max, hasVariant, Pepsi Max Cherry]
  • A. Cherry Coke
    Cherry Coke is a cherry-flavored soft drink produced by The Coca-Cola Company as a variation of its classic cola.
  • B. Pepsi Lime
    Pepsi Lime is a citrus-flavored variation of the Pepsi soft drink that combines cola with a hint of lime.
  • C. Pepsi Vanilla
    Pepsi Vanilla is a flavored cola soft drink that combines the classic taste of Pepsi with added vanilla flavoring.
  • D. Pepsi Mango
    Pepsi Mango is a flavored cola soft drink that combines the taste of classic Pepsi with a sweet mango flavor.
  • E. Pepsi Max
    Pepsi Max is a sugar-free, low-calorie cola soft drink produced by PepsiCo as an alternative to regular Pepsi.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Pepsi Max Cherry
Triple: [Pepsi Max, hasVariant, Pepsi Max Cherry]
Generated description
Pepsi Max Cherry is a cherry-flavored, sugar-free cola variant of Pepsi Max marketed as a low-calorie soft drink.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pepsi Max Cherry
Target entity description: Pepsi Max Cherry is a cherry-flavored, sugar-free cola variant of Pepsi Max marketed as a low-calorie soft drink.
  • A. Cherry Coke
    Cherry Coke is a cherry-flavored soft drink produced by The Coca-Cola Company as a variation of its classic cola.
  • B. Pepsi Lime
    Pepsi Lime is a citrus-flavored variation of the Pepsi soft drink that combines cola with a hint of lime.
  • C. Pepsi Vanilla
    Pepsi Vanilla is a flavored cola soft drink that combines the classic taste of Pepsi with added vanilla flavoring.
  • D. Pepsi Mango
    Pepsi Mango is a flavored cola soft drink that combines the taste of classic Pepsi with a sweet mango flavor.
  • E. Pepsi Max
    Pepsi Max is a sugar-free, low-calorie cola soft drink produced by PepsiCo as an alternative to regular Pepsi.
  • F. None of above. chosen

Provenance (5 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_69c008d00efc8190a36c05b4b4a3bf4b completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c064a075dc8190acf7ec010cb4b00c completed March 22, 2026, 9:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69c5e469355c81908049e0c68a8c0259 completed March 27, 2026, 1:59 a.m.
NEDg Description generation batch_69c5ee04b2388190b36dc9bb23b4a18a completed March 27, 2026, 2:40 a.m.
NED2 Entity disambiguation (via description) batch_69c5ee780bb08190a97c90804f9c6b68 completed March 27, 2026, 2:42 a.m.
Created at: March 22, 2026, 4:28 p.m.