Triple

T20540757
Position Surface form Disambiguated ID Type / Status
Subject Little Androscoggin River E504323 entity
Predicate flowsThrough P225 FINISHED
Object South Paris, 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: South Paris, Maine | Statement: [Little Androscoggin River, flowsThrough, South Paris, Maine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: South Paris, Maine
Context triple: [Little Androscoggin River, flowsThrough, South Paris, Maine]
  • A. Paris, Maine chosen
    Paris, Maine is a small town in western Maine that serves as the administrative and commercial center of Oxford County.
  • B. Springfield, Maine
    Springfield, Maine is a small rural town located in Penobscot County in eastern Maine, known for its forested landscape and quiet, sparsely populated setting.
  • C. South Portland, Maine
    South Portland, Maine is a coastal city in Cumberland County known for its industrial base, retail centers, and proximity to Portland Harbor.
  • D. Buckfield, Maine
    Buckfield, Maine is a small rural town in western Maine known for its historic village center and location within Androscoggin County.
  • E. Roxbury, Maine
    Roxbury, Maine is a small rural town in Oxford County known for its forested landscapes, lakes, and outdoor recreation opportunities in western Maine.
  • 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_69e0b4b476648190bc6019622ae54d3c completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a29224f081908298d104161c5bb9 completed April 20, 2026, 10:02 p.m.
Created at: April 16, 2026, 11:37 a.m.