Triple

T21177306
Position Surface form Disambiguated ID Type / Status
Subject Rochester, New Hampshire E521845 entity
Predicate adjacentTo P224 FINISHED
Object Lebanon, 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: Lebanon, Maine | Statement: [Rochester, New Hampshire, adjacentTo, Lebanon, Maine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lebanon, Maine
Context triple: [Rochester, New Hampshire, adjacentTo, Lebanon, Maine]
  • A. Lebanon, Maine chosen
    Lebanon, Maine is a small rural town in southwestern Maine known for its forests, lakes, and proximity to the New Hampshire border.
  • B. Levant, Maine
    Levant, Maine is a small rural town located in Penobscot County in central Maine, known for its agricultural character and close proximity to the city of Bangor.
  • C. Warren, Maine
    Warren, Maine is a small town in Knox County known for its rural character and location along the St. George River in midcoast Maine.
  • D. Hope, Maine
    Hope, Maine is a small rural town in coastal Knox County known for its scenic lakes, rolling hills, and quiet New England character.
  • E. Gray, Maine
    Gray, Maine is a small New England town in southern Maine known for its rural character, proximity to Portland, and the Maine Wildlife Park.
  • 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_69e0b50ef1d48190b063aa342667df22 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7301a8198819092daa1c847889a88 completed April 21, 2026, 8:06 a.m.
Created at: April 16, 2026, 3 p.m.