Triple

T17055490
Position Surface form Disambiguated ID Type / Status
Subject Britannia Industries E413808 entity
Predicate brand P1500 FINISHED
Object Rusk
Rusk is a popular crisp, dry biscuit commonly consumed as a light snack or accompaniment to tea, produced and marketed in India by Britannia Industries.
 E1247815 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: Rusk | Statement: [Britannia Industries, brand, Rusk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Rusk
Context triple: [Britannia Industries, brand, Rusk]
  • A. Rusk
    Rusk is a surname most notably associated with Dean Rusk, who served as United States Secretary of State during the Kennedy and Johnson administrations.
  • B. Russaw
    Russaw is a surname most notably associated with Joshua Russaw, the son of singer Faith Evans and producer Kiyamma Griffin.
  • C. Rumsien
    Rumsien is a Native American group and language of the Ohlone people traditionally associated with the Monterey Bay area of California.
  • D. La Russa
    La Russa is an Italian surname most prominently associated with Hall of Fame Major League Baseball manager Tony La Russa.
  • E. Burúśaski
    Burúśaski is a language isolate spoken primarily in northern Pakistan, notable for its unique grammatical structure and lack of proven relation to any other language family.
  • 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: Rusk
Triple: [Britannia Industries, brand, Rusk]
Generated description
Rusk is a popular crisp, dry biscuit commonly consumed as a light snack or accompaniment to tea, produced and marketed in India by Britannia Industries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Rusk
Target entity description: Rusk is a popular crisp, dry biscuit commonly consumed as a light snack or accompaniment to tea, produced and marketed in India by Britannia Industries.
  • A. Rusk
    Rusk is a surname most notably associated with Dean Rusk, who served as United States Secretary of State during the Kennedy and Johnson administrations.
  • B. Russaw
    Russaw is a surname most notably associated with Joshua Russaw, the son of singer Faith Evans and producer Kiyamma Griffin.
  • C. Rumsien
    Rumsien is a Native American group and language of the Ohlone people traditionally associated with the Monterey Bay area of California.
  • D. La Russa
    La Russa is an Italian surname most prominently associated with Hall of Fame Major League Baseball manager Tony La Russa.
  • E. Burúśaski
    Burúśaski is a language isolate spoken primarily in northern Pakistan, notable for its unique grammatical structure and lack of proven relation to any other language family.
  • 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_69d886cde3d481908d4d01ba88ba7eb7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3db7934e881909e9f0ae956fb0816 completed April 18, 2026, 7:28 p.m.
NED1 Entity disambiguation (via context triple) batch_6a012346bcfc819093cd922baa94e186 completed May 11, 2026, 12:31 a.m.
NEDg Description generation batch_6a0125420bd08190b969849a206a67d1 completed May 11, 2026, 12:39 a.m.
NED2 Entity disambiguation (via description) batch_6a0125c7c4f48190b570dabd341b1ef1 completed May 11, 2026, 12:41 a.m.
Created at: April 10, 2026, 5:34 a.m.