Triple

T4963089
Position Surface form Disambiguated ID Type / Status
Subject Serengeti National Park E111455 entity
Predicate majorRiver P165 FINISHED
Object Mara River E376213 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: Mara River | Statement: [Serengeti National Park, majorRiver, Mara River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mara River
Context triple: [Serengeti National Park, majorRiver, Mara River]
  • A. Mara River chosen
    The Mara River is a major waterway in East Africa that flows through Kenya and Tanzania, supporting rich wildlife ecosystems and the famed wildebeest migration.
  • B. Bua River
    The Bua River is a major river in Malawi that drains part of the country’s central region before emptying into Lake Malawi.
  • C. Bandia River
    The Bandia River is a lesser-known river in India that serves as a tributary of the Indravati River within the Godavari basin.
  • D. Ngadda River
    The Ngadda River is a waterway in northeastern Nigeria that flows through the city of Maiduguri and contributes to the region’s drainage into Lake Chad.
  • E. Muchukunda River
    Muchukunda River is the historical name of the Musi River, a significant tributary of the Krishna River flowing through Hyderabad in the Indian state of Telangana.
  • 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_69bd4419393c819086319a6fe4bf8542 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd71f3e6148190b99f35734220ffc3 completed March 20, 2026, 4:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69bfba1e755081909649e0dd8c4d2270 completed March 22, 2026, 9:45 a.m.
Created at: March 20, 2026, 1:32 p.m.