Triple

T3874237
Position Surface form Disambiguated ID Type / Status
Subject Rumford Falls E92458 entity
Predicate locatedIn P40 FINISHED
Object Rumford, Maine E14369 NE FINISHED

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: Rumford, Maine | Statement: [Rumford Falls, locatedIn, Rumford, Maine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rumford, Maine
Context triple: [Rumford Falls, locatedIn, Rumford, Maine]
  • A. Rumford, Maine chosen
    Rumford, Maine is a small mill town in western Maine known for its paper industry heritage and proximity to outdoor recreation in the surrounding mountains and rivers.
  • B. Lovell, Maine
    Lovell, Maine is a small rural town in Oxford County known for its scenic lakes and mountains in western Maine.
  • C. Morrill, Maine
    Morrill, Maine is a small rural town in Waldo County known for its quiet residential character and forested, hilly landscape in central coastal Maine.
  • D. Randolph, Maine
    Randolph, Maine is a small town in central Maine located along the Kennebec River, just across from the city of Gardiner.
  • E. Van Buren, Maine
    Van Buren, Maine is a small town in northern Maine along the Saint John River, directly across from New Brunswick, Canada, known for its French-Acadian heritage and rural character.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69aed967448c819086c4b358d37b25aa completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeec59bea08190b1e193f34944a2ee completed March 9, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69e215ac56248190a75ad5ceb8152d5a completed April 17, 2026, 11:12 a.m.
Created at: March 9, 2026, 3:20 p.m.