Triple

T16142901
Position Surface form Disambiguated ID Type / Status
Subject Pottawatomie massacre E391706 entity
Predicate locatedIn P40 FINISHED
Object Pottawatomie Creek 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: Pottawatomie Creek | Statement: [Pottawatomie massacre, locatedIn, Pottawatomie Creek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pottawatomie Creek
Context triple: [Pottawatomie massacre, locatedIn, Pottawatomie Creek]
  • A. Pottawatomie Creek chosen
    Pottawatomie Creek is a stream in eastern Kansas known for flowing through Miami County and its role in the region’s local watershed and history.
  • B. Yockanookany River
    The Yockanookany River is a tributary waterway in central Mississippi that flows through largely rural areas before joining the Pearl River.
  • C. Portage Creek
    Portage Creek is a small waterway in Kalamazoo County, Michigan, that serves as a local tributary within the region’s river system.
  • D. Oatka Creek
    Oatka Creek is a significant stream in western New York known for its trout fishing and scenic, rural landscapes as it flows through several counties before joining the Genesee River.
  • E. Buffalo Creek
    Buffalo Creek is a waterway whose name inspired that of the city of Buffalo in New York.
  • 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_69d87f1c65e48190aa2b4c472e9bafc4 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21d9082588190bc7e6ff491f0d94e completed April 17, 2026, 11:46 a.m.
Created at: April 10, 2026, 5:01 a.m.