Triple

T23460692
Position Surface form Disambiguated ID Type / Status
Subject Government of Rhodesia E568965 entity
Predicate capital P234 FINISHED
Object Salisbury 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: Salisbury | Statement: [Government of Rhodesia, capital, Salisbury]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Salisbury
Context triple: [Government of Rhodesia, capital, Salisbury]
  • A. Salisbury
    Salisbury is a suburban city in the northern part of the Adelaide metropolitan area in South Australia, serving as a key residential and industrial hub.
  • B. Salisbury
    Salisbury is a coastal town in northeastern Massachusetts, United States, known for its beaches along the Atlantic Ocean and its history dating back to the early colonial era.
  • C. Salisbury
    Salisbury is a small Canadian village in southeastern New Brunswick known as a local service and residential community along the Petitcodiac River.
  • D. Salisbury
    Salisbury is a village on the west coast of Dominica known for its fishing community and proximity to scenic Caribbean beaches.
  • E. Salisbury chosen
    Salisbury is the former colonial-era name of Zimbabwe’s capital city, now known as Harare.
  • 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_69e2458ebd808190b3298163132cfb0b completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a69afba88190b1b1dd27d331309f completed April 29, 2026, 6:35 a.m.
Created at: April 17, 2026, 5:53 p.m.