Triple

T11521240
Position Surface form Disambiguated ID Type / Status
Subject Greene County, Indiana E273165 entity
Predicate hasRiver P165 FINISHED
Object White River NE NERFINISHED

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: White River | Statement: [Greene County, Indiana, hasRiver, White River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: White River
Context triple: [Greene County, Indiana, hasRiver, White River]
  • A. White River chosen
    White River is a major waterway in central Indiana that flows through Indianapolis and plays a key role in the region’s ecology and recreation.
  • B. White River
    The White River is a major river in the central United States that flows through the Ozark region, known for its clear waters, scenic landscapes, and popular fishing and recreation areas.
  • C. White River
    White River is a river in Michigan known for its scenic natural surroundings and recreational opportunities such as fishing and boating.
  • D. White River
    The White River is a significant river in central Vermont that flows through rural valleys and towns before joining the Connecticut River.
  • E. White River
    White River is a scenic Jamaican river near Ocho Rios known for activities like rafting, tubing, and swimming in its clear, refreshing waters.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d6aae3fbec8190a14632a5df2538b6 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d87fd129c88190893b95222480e04a completed April 10, 2026, 4:42 a.m.
Created at: April 8, 2026, 9:36 p.m.