Triple

T20835275
Position Surface form Disambiguated ID Type / Status
Subject Potawatomi Park E512942 entity
Predicate ownedBy P347 FINISHED
Object City of South Bend 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: City of South Bend | Statement: [Potawatomi Park, ownedBy, City of South Bend]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: City of South Bend
Context triple: [Potawatomi Park, ownedBy, City of South Bend]
  • A. South Bend, Indiana chosen
    South Bend, Indiana is a mid-sized city in northern Indiana known for its manufacturing heritage, proximity to the University of Notre Dame, and role as an economic and cultural hub of the region.
  • B. South Bend
    South Bend is a small coastal city in southwestern Washington State that serves as the county seat of Pacific County.
  • C. town of South Bend
    The town of South Bend is a small coastal community in Pacific County, Washington, known historically for its oyster industry and location along the Willapa River.
  • D. Columbus, Indiana
    Columbus, Indiana is a small Midwestern city renowned for its exceptional collection of modernist architecture and public art.
  • E. Kokomo, Indiana
    Kokomo, Indiana is a mid-sized industrial city in central Indiana known historically for its automotive manufacturing and technological innovation.
  • 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_69e0b4cf62a88190bbf92351e9e57259 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c32622c481908b8d2159bd5bb0ad completed April 21, 2026, 12:21 a.m.
Created at: April 16, 2026, 12:42 p.m.