Triple

T18793901
Position Surface form Disambiguated ID Type / Status
Subject Spaarne River E459582 entity
Predicate hasBridge P386 FINISHED
Object Langebrug 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: Langebrug | Statement: [Spaarne River, hasBridge, Langebrug]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Langebrug
Context triple: [Spaarne River, hasBridge, Langebrug]
  • A. Langebrug chosen
    Langebrug is a historic bridge spanning the Spaarne River in the Dutch city of Haarlem.
  • B. Lange Poten
    Lange Poten is a central street in The Hague, Netherlands, known for its shops, offices, and proximity to key government buildings.
  • C. Langesund
    Langesund is a coastal town in southern Norway known historically as a shipping and timber port and now as a popular summer and ferry destination.
  • D. Lange
    Lange is a German surname borne by numerous notable individuals across fields such as science, politics, arts, and sports.
  • E. Langevåg
    Langevåg is a village in western Norway known for its coastal setting and proximity to the city of Ålesund.
  • 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_69d8d396f54c8190ba49db31e8743842 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5a01cc0c0819098ef4326e82ff524 completed April 20, 2026, 3:40 a.m.
Created at: April 10, 2026, 11:53 a.m.