Triple

T5012710
Position Surface form Disambiguated ID Type / Status
Subject Inner Hebrides E112663 entity
Predicate hasIsland P970 FINISHED
Object Kerrera E89641 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: Kerrera | Statement: [Inner Hebrides, hasIsland, Kerrera]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kerrera
Context triple: [Inner Hebrides, hasIsland, Kerrera]
  • A. Kerrera chosen
    Kerrera is a small Scottish island in the Inner Hebrides, located near Oban on the country’s west coast.
  • B. Kerria
    Kerria is a small genus of deciduous flowering shrubs, best known for the ornamental Japanese kerria with its bright yellow, rose-like blooms.
  • C. Caledonia
    Caledonia is the Latin name used by the Romans for the region roughly corresponding to modern-day Scotland and parts of northern Britain.
  • D. Boneland
    Boneland is a 2012 fantasy novel by Alan Garner that concludes the trilogy begun with The Weirdstone of Brisingamen and The Moon of Gomrath, blending myth, memory, and modern psychological themes.
  • E. Snow Island
    Snow Island is a remote, ice-covered island in Antarctica’s South Shetland Islands archipelago, known for its harsh polar climate and largely untouched environment.
  • 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_69bd4434acb8819086679dbeccc2fe54 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd730f12a481908a27c15dc73987c6 completed March 20, 2026, 4:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69be926e5ef481909df3a4b9d793300a completed March 21, 2026, 12:43 p.m.
Created at: March 20, 2026, 1:35 p.m.