Triple

T18459442
Position Surface form Disambiguated ID Type / Status
Subject Erpeler Ley E450991 entity
Predicate nearbySettlement P350 FINISHED
Object Erpel 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: Erpel | Statement: [Erpeler Ley, nearbySettlement, Erpel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Erpel
Context triple: [Erpeler Ley, nearbySettlement, Erpel]
  • A. Erpel chosen
    Erpel is a small municipality in the district of Neuwied in Rhineland-Palatinate, Germany, situated on the right bank of the Rhine River.
  • B. Nijverdal
    Nijverdal is a town in the Dutch province of Overijssel known as a gateway to the Sallandse Heuvelrug National Park and its surrounding natural landscapes.
  • C. Scharendijke
    Scharendijke is a village in the Dutch province of Zeeland, known as a popular base for water sports and diving in the Grevelingen and North Sea area.
  • D. Eeklo
    Eeklo is a small city and municipality in northwestern Belgium known for its historic town center and location in the Flemish region.
  • E. Land van Heusden
    Land van Heusden is a historic region in the northern part of the Dutch province of North Brabant, centered around the town of Heusden and known for its medieval fortifications and river landscapes.
  • 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_69d8d38345688190b565eac2e4cd7935 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e52a7cdb5c8190a399f0e4052f7d1f completed April 19, 2026, 7:18 p.m.
Created at: April 10, 2026, 11:33 a.m.