Triple

T7378681
Position Surface form Disambiguated ID Type / Status
Subject Isle of Harris E170190 entity
Predicate hasSettlement P1068 FINISHED
Object Seilebost E545111 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: Seilebost | Statement: [Isle of Harris, hasSettlement, Seilebost]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Seilebost
Context triple: [Isle of Harris, hasSettlement, Seilebost]
  • A. Seilebost chosen
    Seilebost is a small, scenic village on the Isle of Harris in Scotland’s Outer Hebrides, known for its white-sand beaches and views over turquoise waters.
  • B. Skibotn
    Skibotn is a small village in northern Norway known for its clear skies and role as a center for astronomical observations.
  • C. Seiskari
    Seiskari is an island located in the Gulf of Finland, historically known as a fishing community and part of the outer archipelago in the eastern Baltic Sea.
  • D. Seiling
    Seiling is a small rural city in Dewey County, northwestern Oklahoma, known historically as a farming and ranching community.
  • E. Seille
    Seille is a river in eastern France that flows through the regions of Jura and Saône-et-Loire before joining the Saône.
  • 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_69c68a5d0ed08190b6d361e68f813330 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f1c4ad0081909386fbef9f61ae4c completed March 27, 2026, 9:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69c802d57ae88190840442621d8bef35 completed March 28, 2026, 4:33 p.m.
Created at: March 27, 2026, 3:08 p.m.