Triple

T4875591
Position Surface form Disambiguated ID Type / Status
Subject Tisa River E109194 entity
Predicate tributary P415 FINISHED
Object Maros River E245148 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: Maros River | Statement: [Tisa River, tributary, Maros River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maros River
Context triple: [Tisa River, tributary, Maros River]
  • A. Maros River chosen
    The Maros River is a significant Central European waterway that flows through present-day Romania and Hungary before joining the Tisza River.
  • B. Sei River
    The Sei River is a smaller watercourse in western India that feeds into the Sabarmati River within the arid and semi-arid landscape of Rajasthan and Gujarat.
  • C. Daule River
    The Daule River is a major river in western Ecuador that flows through agricultural regions and urban areas before joining other waterways to form the Guayas River system.
  • D. Agno River
    The Agno River is one of the largest river systems in the Philippines, flowing through the Cordillera and Central Luzon regions before emptying into the Lingayen Gulf.
  • E. Palu River
    The Palu River is a waterway in Central Sulawesi, Indonesia, that flows through the city of Palu before emptying into Palu Bay.
  • 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_69bd440e9d64819083e82cf33b4d9570 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6dba3efc8190adcf8b30490b4984 completed March 20, 2026, 3:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69be6fb5da2c8190aeec7d6d11b12b11 completed March 21, 2026, 10:15 a.m.
Created at: March 20, 2026, 1:27 p.m.