Triple

T19518860
Position Surface form Disambiguated ID Type / Status
Subject Southwest Harbor, Maine E488350 entity
Predicate hasNearbyTown P3883 FINISHED
Object Mount Desert, 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: Mount Desert, Maine | Statement: [Southwest Harbor, Maine, hasNearbyTown, Mount Desert, Maine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mount Desert, Maine
Context triple: [Southwest Harbor, Maine, hasNearbyTown, Mount Desert, Maine]
  • A. Mount Desert, Maine chosen
    Mount Desert, Maine is a coastal town on Mount Desert Island known for its proximity to Acadia National Park and its scenic natural landscapes.
  • B. Blue Hill, Maine
    Blue Hill, Maine is a small coastal town in Downeast Maine known for its scenic harbor, vibrant arts community, and historic New England charm.
  • C. Owls Head, Maine
    Owls Head, Maine is a small coastal town in Knox County known for its scenic shoreline, historic lighthouse, and maritime character.
  • D. Damariscotta, Maine
    Damariscotta, Maine is a small coastal town in Lincoln County known for its historic waterfront, oyster farming, and scenic location along the Damariscotta River.
  • E. Rangeley, Maine
    Rangeley, Maine is a small resort town in western Maine known for its lakes, outdoor recreation, and scenic mountain surroundings.
  • 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_69d8e8da8bec819081f400199491ccc3 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6359edd508190afd68739de676ed7 completed April 20, 2026, 2:18 p.m.
Created at: April 10, 2026, 1:40 p.m.