Triple

T7508048
Position Surface form Disambiguated ID Type / Status
Subject Nesoddtangen peninsula E177442 entity
Predicate hasFrequentServiceTo P6787 FINISHED
Object Oslo E3654 NE FINISHED

How this triple was built (3 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: Oslo | Statement: [Nesoddtangen peninsula, hasFrequentServiceTo, Oslo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oslo
Context triple: [Nesoddtangen peninsula, hasFrequentServiceTo, Oslo]
  • A. Oslo chosen
    Oslo is the capital and largest city of Norway, known as a major cultural, economic, and governmental center.
  • B. Trondheim
    Trondheim is a historic Norwegian city in Trøndelag county, known for its medieval Nidaros Cathedral and role as a former capital of Norway.
  • C. Bergen
    Bergen is a city in western Germany, historically notable as the site of the 1759 Battle of Bergen during the Seven Years' War.
  • D. Bergen
    Bergen is Norway's second-largest city, renowned for its historic harbor, surrounding mountains and fjords, and role as a former Hanseatic trading hub.
  • E. Bergens
    The Bergens are a race of gloomy, troll-eating creatures who serve as the primary villains in the animated film "Trolls."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasFrequentServiceTo
Context triple: [Nesoddtangen peninsula, hasFrequentServiceTo, Oslo]
  • A. hasServiceTo chosen
    Indicates that one entity provides, offers, or operates a service for or directed toward another entity.
  • B. hasFrequentActivity
    Indicates that an entity regularly engages in or exhibits a high level of a particular activity over a given period.
  • C. isFrequently
    Indicates that an action, state, or relationship occurs often or with high regularity between the related entities.
  • D. hasConstituentServicesIn
    Indicates that an entity provides constituent services within a specified geographic or jurisdictional area.
  • E. serviceFrequencyContext
    Indicates the contextual conditions or circumstances under which a service’s frequency is defined, applied, or interpreted.
  • F. None of above.

Provenance (4 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_69c69f276b108190af2cc790b6554544 completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f5b8ab5c8190828ee8d144068828 completed March 27, 2026, 9:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8569b932481909d41130303e21518 completed March 28, 2026, 10:30 p.m.
PD Predicate disambiguation batch_69c6f4d44e9481909813e073b194f6f4 completed March 27, 2026, 9:21 p.m.
Created at: March 27, 2026, 3:45 p.m.