Triple

T19429365
Position Surface form Disambiguated ID Type / Status
Subject Dunmore E486068 entity
Predicate adjacentTo P224 FINISHED
Object Old Forge 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: Old Forge | Statement: [Dunmore, adjacentTo, Old Forge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Old Forge
Context triple: [Dunmore, adjacentTo, Old Forge]
  • A. Old Forge chosen
    Old Forge is a small borough in northeastern Pennsylvania known historically for its coal-mining roots and locally famous Old Forge-style pizza.
  • B. Old Forge
    Old Forge is a small resort hamlet in upstate New York known as a popular gateway to the Adirondack Mountains, offering outdoor recreation, lakeside activities, and access to wilderness areas.
  • C. Woodhatch
    Woodhatch is a residential area in the town of Reigate in Surrey, England.
  • D. Knightsridge
    Knightsridge is a residential area and housing estate located within the town of Livingston in West Lothian, Scotland.
  • E. Mill Burn
    Mill Burn is a small tributary stream in West Dunbartonshire, Scotland, that feeds into the River Leven.
  • 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_69d8e8d688f881909c85104a62e09d8a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6321b78d08190b86cef7c60cbb61c completed April 20, 2026, 2:03 p.m.
Created at: April 10, 2026, 1:37 p.m.