Triple

T3364943
Position Surface form Disambiguated ID Type / Status
Subject Saint John River E70812 entity
Predicate borderSectionBetween P39423 FINISHED
Object Maine E29256 NE FINISHED

How this triple was built (3 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: Maine | Statement: [Saint John River, borderSectionBetween, Maine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maine
Context triple: [Saint John River, borderSectionBetween, Maine]
  • A. Maine chosen
    Maine is a northeastern U.S. state known for its rugged coastline, maritime history, and vast forested interior.
  • B. Maine
    Maine is a historical region in northwestern France that played a significant role in the medieval power struggles between the English and French crowns.
  • C. New Hampshire
    New Hampshire is a small New England state in the northeastern United States known for its mountainous landscapes, early presidential primary, and “Live Free or Die” motto.
  • D. Vermont
    Vermont is a small, rural New England state in the northeastern United States, known for its Green Mountains, maple syrup production, and picturesque towns.
  • E. Vermont
    Vermont is a small rural town located in Dane County, Wisconsin, known for its scenic landscapes and agricultural character.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: borderSectionBetween
Context triple: [Saint John River, borderSectionBetween, Maine]
  • A. borderSectionName
    Indicates the specific named segment or portion of a border that is associated with or applies to an entity.
  • B. boundaryBetween chosen
    Indicates that something serves as a dividing line or limit separating two distinct regions, areas, or entities.
  • C. borderRegion
    Indicates a region that lies along or near the boundary separating two distinct geographic or political areas.
  • D. borderStraddling
    Indicates that something (such as a feature, structure, or area) extends across and occupies territory on both sides of a border between two regions or jurisdictions.
  • E. borderPoint
    Indicates a point that lies on the boundary between two regions or entities.
  • F. None of above.

Provenance (4 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_69ad85a729d48190afd789cd8417f289 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb28643f48190b78b0222f8323344 completed March 8, 2026, 5:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69b533595bb88190814ea2ebe3495525 completed March 14, 2026, 10:07 a.m.
PD Predicate disambiguation batch_69ada4317e288190ab7d0f66e9dba65f completed March 8, 2026, 4:30 p.m.
Created at: March 8, 2026, 3:13 p.m.