Triple

T17590991
Position Surface form Disambiguated ID Type / Status
Subject Andy Bond E428445 entity
Predicate employer P7 FINISHED
Object Asda 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: Asda | Statement: [Andy Bond, employer, Asda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Asda
Context triple: [Andy Bond, employer, Asda]
  • A. Asda chosen
    Asda is a major British supermarket and retail chain known for its low-cost groceries, general merchandise, and large-format stores across the United Kingdom.
  • B. Tesco
    Tesco is a major British multinational grocery and general merchandise retailer and one of the largest supermarket chains in the world.
  • C. Sainsbury
    Sainsbury is a prominent British family name most closely associated with the founders and owners of the J Sainsbury supermarket chain and notable figures in business and public life.
  • D. Morrisons
    Morrisons is one of the United Kingdom’s largest supermarket chains, offering groceries and household goods through an extensive network of stores and online services.
  • E. Woolworths
    Woolworths is a major Australian supermarket and grocery retail chain.
  • 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_69d889e1030481909950e140c63255b9 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e469e6e3888190b73a5b6d7e8c0a55 completed April 19, 2026, 5:36 a.m.
Created at: April 10, 2026, 5:51 a.m.