Triple

T17720973
Position Surface form Disambiguated ID Type / Status
Subject Montserrat E442335 entity
Predicate deFactoCapital P234 FINISHED
Object Brades 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: Brades | Statement: [Montserrat, deFactoCapital, Brades]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brades
Context triple: [Montserrat, deFactoCapital, 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. Bankal
    Bankal is a Jarawan Bantu language spoken by a small ethnic community in Nigeria.
  • C. BRI
    BRI is one of Indonesia’s largest and oldest state-owned banks, known for its extensive microfinance and rural banking services.
  • D. BRI
    BRI is a global infrastructure and economic development strategy launched by China to enhance trade and connectivity across Asia, Europe, Africa, and beyond.
  • E. BRI
    The BRI (Brigade de Recherche et d’Intervention) is an elite French police tactical unit specializing in high-risk operations such as counterterrorism, hostage rescue, and organized crime interventions.
  • 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_69d8b9ec79688190b86bdcef85a7b3aa completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4748520a881908dc3446d33236ff7 completed April 19, 2026, 6:21 a.m.
Created at: April 10, 2026, 10:07 a.m.