Triple

T5097406
Position Surface form Disambiguated ID Type / Status
Subject DeKalb County, Alabama E114900 entity
Predicate hasTown P847 FINISHED
Object Mentone, Alabama E451174 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: Mentone, Alabama | Statement: [DeKalb County, Alabama, hasTown, Mentone, Alabama]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mentone, Alabama
Context triple: [DeKalb County, Alabama, hasTown, Mentone, Alabama]
  • A. Mentone, Alabama chosen
    Mentone, Alabama is a small mountain resort town on Lookout Mountain known for its scenic beauty, waterfalls, and arts-oriented community.
  • B. Shorterville, Alabama
    Shorterville, Alabama is a small unincorporated community and rural locality in eastern Henry County near the Chattahoochee River.
  • C. Malvern, Alabama
    Malvern, Alabama is a small rural town located in southeastern Alabama within Geneva County.
  • D. Sumiton, Alabama
    Sumiton, Alabama is a small city in north-central Alabama known as a former coal-mining community within the Birmingham–Hoover metropolitan area.
  • E. Townley, Alabama
    Townley, Alabama is a small unincorporated community located in Walker County in the north-central part of the state.
  • 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_69bd443fc49c819089629c00e311310c completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd75669afc81908a8db897fe56eccd completed March 20, 2026, 4:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69beba80aee081908498cbe9d4f2eaa7 completed March 21, 2026, 3:34 p.m.
Created at: March 20, 2026, 1:40 p.m.