Triple

T13581892
Position Surface form Disambiguated ID Type / Status
Subject Little Bay de Noc E324438 entity
Predicate hasInflow P967 FINISHED
Object Rapid River
Rapid River is a watercourse in Michigan’s Upper Peninsula that flows into Little Bay de Noc on Lake Michigan.
 E1502506 NE FINISHED

How this triple was built (4 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: Rapid River | Statement: [Little Bay de Noc, hasInflow, Rapid River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Rapid River
Context triple: [Little Bay de Noc, hasInflow, Rapid River]
  • A. Rapid River
    Rapid River is a watercourse that serves as one of the tributary rivers flowing into Lake of the Woods in North America.
  • B. Eerste River
    Eerste River is a prominent waterway in South Africa’s Western Cape that flows through the Stellenbosch region and supports its agriculture and ecosystems.
  • C. Selbe River
    The Selbe River is a smaller river in central Mongolia that feeds into the Tuul River, contributing to the watershed of the region around Ulaanbaatar.
  • D. Youngs River
    Youngs River is a coastal river in northwestern Oregon that flows into Youngs Bay near the mouth of the Columbia River.
  • E. Todd River
    Todd River is an ephemeral watercourse in Australia's Northern Territory that runs through the town of Alice Springs and is known for often being dry.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Rapid River
Triple: [Little Bay de Noc, hasInflow, Rapid River]
Generated description
Rapid River is a watercourse in Michigan’s Upper Peninsula that flows into Little Bay de Noc on Lake Michigan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Rapid River
Target entity description: Rapid River is a watercourse in Michigan’s Upper Peninsula that flows into Little Bay de Noc on Lake Michigan.
  • A. Rapid River
    Rapid River is a watercourse that serves as one of the tributary rivers flowing into Lake of the Woods in North America.
  • B. Eerste River
    Eerste River is a prominent waterway in South Africa’s Western Cape that flows through the Stellenbosch region and supports its agriculture and ecosystems.
  • C. Selbe River
    The Selbe River is a smaller river in central Mongolia that feeds into the Tuul River, contributing to the watershed of the region around Ulaanbaatar.
  • D. Youngs River
    Youngs River is a coastal river in northwestern Oregon that flows into Youngs Bay near the mouth of the Columbia River.
  • E. Todd River
    Todd River is an ephemeral watercourse in Australia's Northern Territory that runs through the town of Alice Springs and is known for often being dry.
  • F. None of above. chosen

Provenance (5 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_69d80769100c819099111274614f5ed2 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbb031e8048190a5f2ea934308036c completed April 12, 2026, 2:46 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a3e55d7bc8190b23ad38c77f65ec5 completed May 17, 2026, 10:16 p.m.
NEDg Description generation batch_6a0a3faec8948190a8e813e776a4bbb4 completed May 17, 2026, 10:22 p.m.
NED2 Entity disambiguation (via description) batch_6a0a40652c3081909f765ff48b2e0041 completed May 17, 2026, 10:25 p.m.
Created at: April 9, 2026, 9:48 p.m.