Triple

T820323
Position Surface form Disambiguated ID Type / Status
Subject Montserrat E17737 entity
Predicate largestCity P235 FINISHED
Object Brades E98377 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: Brades | Statement: [Montserrat, largestCity, Brades]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brades
Context triple: [Montserrat, largestCity, Brades]
  • A. Brades chosen
    Brades is a town on the Caribbean island of Montserrat that serves as the territory’s temporary administrative and commercial center following the abandonment of Plymouth due to volcanic activity.
  • B. Blackrock
    Blackrock is a suburban residential area of Cork city in County Cork, Ireland, known for its riverside location along the River Lee and historic maritime and industrial heritage.
  • C. Danske Bank
    Danske Bank is a major Nordic financial institution headquartered in Copenhagen, Denmark, offering a wide range of banking and financial services across Northern Europe.
  • D. Girobank
    Girobank was a British state-owned financial institution that provided banking and giro transfer services, originally established and run through the national postal system.
  • E. Breg
    Breg is a river in Germany’s Black Forest region that forms one of the main headwaters of the Danube.
  • 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_69a4937bcaac8190a322524ac6f45a5a completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4ab6698d881908d8c5d91259f97ec completed March 1, 2026, 9:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7928f8a808190aaf5f2a2f3ee676f completed March 4, 2026, 2:01 a.m.
Created at: March 1, 2026, 7:38 p.m.