Triple

T5030438
Position Surface form Disambiguated ID Type / Status
Subject Middelaar E113285 entity
Predicate hasBorder P224 FINISHED
Object river Maas E516582 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: river Maas | Statement: [Middelaar, hasBorder, river Maas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: river Maas
Context triple: [Middelaar, hasBorder, river Maas]
  • A. river Maas chosen
    The river Maas, also known as the Meuse, is a major European waterway flowing through France, Belgium, and the Netherlands before emptying into the North Sea.
  • B. Rijn
    Rijn is the Dutch name for the major European river known in English as the Rhine.
  • C. Oude Maas
    The Oude Maas is a major distributary river in the western Netherlands that forms part of the complex Rhine–Meuse–Scheldt delta system.
  • D. Nederrijn
    The Nederrijn is a major distributary branch of the Rhine River in the Netherlands, flowing through cities such as Arnhem and forming an important part of the Dutch river system.
  • E. Vaartsche Rijn
    Vaartsche Rijn is a historic canal in the Dutch province of Utrecht that connects the city of Utrecht with the Lower Rhine and forms part of its inland waterway network.
  • 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_69bd443775e48190a646ffbfc4334723 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd739099a0819099c6201d4e1c5ee2 completed March 20, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf410eb03c81909aca9aca27cc82c1 completed March 22, 2026, 1:08 a.m.
Created at: March 20, 2026, 1:36 p.m.