Triple

T20105227
Position Surface form Disambiguated ID Type / Status
Subject Halistra E490149 entity
Predicate hasNearbySettlement P4647 FINISHED
Object Lusta 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: Lusta | Statement: [Halistra, hasNearbySettlement, Lusta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lusta
Context triple: [Halistra, hasNearbySettlement, Lusta]
  • A. Lusta chosen
    Lusta is a small crofting settlement on the Waternish peninsula of the Isle of Skye in Scotland.
  • B. Lusei
    Lusei are a major clan of the Mizo people of Northeast India, historically influential in shaping Mizo culture, language, and social organization.
  • C. Vindelicia
    Vindelicia was an ancient region in Central Europe inhabited by the Vindelici, roughly corresponding to parts of modern southern Germany and Austria.
  • D. Allerona
    Allerona is a small historic hill town in the Umbria region of central Italy, known for its medieval architecture and scenic countryside.
  • E. Lumarzo
    Lumarzo is a small municipality in the Liguria region of northwestern Italy, located in the hilly inland area near Genoa.
  • 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_69da62636cc08190982cc71733a17b8d completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e666dbad30819082454f360f358131 completed April 20, 2026, 5:48 p.m.
Created at: April 11, 2026, 11:28 p.m.