Triple

T17657862
Position Surface form Disambiguated ID Type / Status
Subject Hurum E440171 entity
Predicate contains P35 FINISHED
Object Tofte E862677 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: Tofte | Statement: [Hurum, contains, Tofte]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tofte
Context triple: [Hurum, contains, Tofte]
  • A. Tofte chosen
    Tofte is a village in the former Hurum municipality in Norway, known for its coastal location along the Oslofjord and industrial history.
  • B. Toft
    Toft is a location that serves as one end of the Yell Sound ferry connection in the Shetland Islands, Scotland.
  • C. Toft
    Toft is a rural estate and small settlement in Cheshire, England, known for its historic hall and proximity to the town of Knutsford.
  • D. Toft
    Toft is a small village in South Cambridgeshire, England, situated just west of Cambridge and known for its rural character and close-knit community.
  • E. Knudshoved
    Knudshoved is a coastal area on the Danish island of Funen that serves as a key transport hub and former ferry terminal at the western end of the Great Belt crossing.
  • 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_69d8b9e87e18819087104a44dc4dc5b1 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e46ea3b4cc81908eec7032cf221d49 completed April 19, 2026, 5:56 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0216584eb88190afa898efae284934 completed May 11, 2026, 5:48 p.m.
Created at: April 10, 2026, 9:28 a.m.