Triple

T5030547
Position Surface form Disambiguated ID Type / Status
Subject Bridge at Grave E113288 entity
Predicate river P165 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: [Bridge at Grave, river, Maas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maas
Context triple: [Bridge at Grave, river, 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. Alle River
    The Alle River, now known as the Łyna, is a river in northeastern Poland and Russia’s Kaliningrad Oblast that historically formed part of East Prussia and was the site of significant Napoleonic-era military actions.
  • C. Jukun
    The Jukun are an ethnic group of central Nigeria, historically associated with the Kwararafa confederacy and primarily found in present-day Taraba and surrounding states.
  • D. Nera River
    The Nera River is a central Italian waterway flowing through the regions of Umbria and Lazio before joining the Tiber River.
  • E. Addalam River
    The Addalam River is a significant waterway in the Cagayan Valley region of the Philippines, contributing to local agriculture, ecosystems, and communities.
  • 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_69bf9535f8008190b91cf823e9484b4e completed March 22, 2026, 7:07 a.m.
Created at: March 20, 2026, 1:36 p.m.