Triple

T11926879
Position Surface form Disambiguated ID Type / Status
Subject Kennebec River watershed E283805 entity
Predicate containsTown P847 FINISHED
Object Madison, Maine 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: Madison, Maine | Statement: [Kennebec River watershed, containsTown, Madison, Maine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Madison, Maine
Context triple: [Kennebec River watershed, containsTown, Madison, Maine]
  • A. Madison, Maine chosen
    Madison, Maine is a small town in central Maine known for its rural character, historic mill industry, and location along the Kennebec River.
  • B. Fairfield, Maine
    Fairfield, Maine is a small town in Somerset County known for its rural character, proximity to the Kennebec River, and role as part of the greater Waterville area in central Maine.
  • C. Monroe, Maine
    Monroe, Maine is a small rural town in Waldo County known for its quiet countryside and close-knit community in central coastal Maine.
  • D. Oakland, Maine
    Oakland, Maine is a small town in central Maine known for its lakeside setting, residential character, and proximity to the city of Waterville.
  • E. Knox, Maine
    Knox, Maine is a small rural town located in Waldo County in the state of Maine, United States.
  • 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_69d6ab2ce9c48190b5d39511b524f666 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8e8e3ff308190851ce656286bc67e completed April 10, 2026, 12:11 p.m.
Created at: April 8, 2026, 9:45 p.m.