Triple

T958537
Position Surface form Disambiguated ID Type / Status
Subject John S. Thompsonbrug E20678 entity
Predicate crosses P416 FINISHED
Object Maas E25262 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: Maas | Statement: [John S. Thompsonbrug, crosses, Maas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maas
Context triple: [John S. Thompsonbrug, crosses, Maas]
  • A. Maas chosen
    The Maas, also known as the Meuse, is a major European river flowing through France, Belgium, and the Netherlands before emptying into the North Sea.
  • B. Kama River
    The Kama River is a major waterway in western Russia that serves as one of the largest and most significant tributaries of the Volga River.
  • C. Tajo River
    The Tajo River is the longest river on the Iberian Peninsula, flowing from eastern Spain through central regions into Portugal before emptying into the Atlantic Ocean.
  • D. Donga River
    The Donga River is a significant river in West Africa that flows through Nigeria and Cameroon before joining the Benue River.
  • E. Kosi
    Kosi is a major Himalayan river in northern India and Nepal, often called the "Sorrow of Bihar" for its frequent and devastating floods before joining the Ganges.
  • 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_69a493b21f2881908132dcf45dcd2f36 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b3fc94ec8190b55c6cdf3a37d6b5 completed March 1, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69acbf0949c481908868bd27eeb964b4 completed March 8, 2026, 12:12 a.m.
Created at: March 1, 2026, 7:40 p.m.