Triple

T17823455
Position Surface form Disambiguated ID Type / Status
Subject Loch nEathach E445046 entity
Predicate hasShoreSettlement P16159 FINISHED
Object Toome 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: Toome | Statement: [Loch nEathach, hasShoreSettlement, Toome]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Toome
Context triple: [Loch nEathach, hasShoreSettlement, Toome]
  • A. Toome chosen
    Toome is a small village in County Antrim, Northern Ireland, known for its location at the northern end of Lough Neagh and its historic bridge and eel fishing industry.
  • B. Valga
    Valga is a small border town in southern Estonia known for forming a twin city with Valka in Latvia.
  • C. Tammneeme
    Tammneeme is a coastal village in northern Estonia known for its seaside location on the Viimsi Peninsula near Tallinn.
  • D. Heltermaa
    Heltermaa is a small port village on the eastern coast of Hiiumaa Island in Estonia, serving as a key ferry connection to the mainland.
  • E. Kraainem
    Kraainem is a Dutch- and French-speaking suburban municipality on the eastern edge of Brussels in the Flemish Brabant province of Belgium.
  • 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_69d8b9f0de78819099395b14db75a8a6 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4891282a081908d384d45bf444baf completed April 19, 2026, 7:49 a.m.
Created at: April 10, 2026, 10:15 a.m.