Triple

T20228107
Position Surface form Disambiguated ID Type / Status
Subject Bloomsbury Publishing E495444 entity
Predicate stockTicker P1447 FINISHED
Object BMY 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: BMY | Statement: [Bloomsbury Publishing, stockTicker, BMY]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BMY
Context triple: [Bloomsbury Publishing, stockTicker, BMY]
  • A. BMY chosen
    BMY is the stock ticker symbol for Bloomsbury Publishing, a British independent publishing house best known for publishing the Harry Potter series.
  • B. BMO
    BMO is a popular R&B single by American singer Ari Lennox, known for its smooth, soulful vibe and playful lyrics.
  • C. BMO
    BMO is a sentient, childlike video game console and robot who serves as a loyal friend and roommate to Finn and Jake in the animated series Adventure Time.
  • D. BMO
    BMO is the National Rail station code for Birmingham Moor Street railway station in Birmingham, England.
  • E. BMO
    BMO is the stock ticker symbol for the Bank of Montreal, one of Canada’s largest and oldest financial institutions.
  • 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_69da626cff80819097b530718a7c98b6 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66fdb61b08190b850a9648ebfb720 completed April 20, 2026, 6:26 p.m.
Created at: April 11, 2026, 11:39 p.m.