Triple

T1862390
Position Surface form Disambiguated ID Type / Status
Subject Ems E34843 entity
Predicate region P40 FINISHED
Object East Frisia E32998 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: East Frisia | Statement: [Ems, region, East Frisia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: East Frisia
Context triple: [Ems, region, East Frisia]
  • A. East Frisia chosen
    East Frisia is a coastal cultural and historical region in northwestern Germany known for its North Sea islands, distinctive Frisian heritage, and strong tea-drinking tradition.
  • B. Friesland
    Friesland is a northern province of the Netherlands known for its distinct Frisian language, rich maritime history, and unique cultural traditions.
  • C. Flevoland
    Flevoland is the youngest Dutch province, largely created through land reclamation from the IJsselmeer in the central Netherlands.
  • D. Frisia
    Frisia is a coastal cultural and historical region along the southeastern North Sea, traditionally inhabited by the Frisian people and spanning parts of the modern Netherlands and Germany.
  • E. Zeeland
    Zeeland is a coastal province in the southwest of the Netherlands, known for its islands, peninsulas, and extensive dike and flood defense systems.
  • 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_69a88600b2f88190bc09303e68ab517e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abb09e714881909cef0f7e77b5b3b9 completed March 7, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69add1d026748190a507872de85c908d completed March 8, 2026, 7:45 p.m.
Created at: March 4, 2026, 7:34 p.m.