Triple

T20604554
Position Surface form Disambiguated ID Type / Status
Subject East Lake station E506268 entity
Predicate servesCity P82 FINISHED
Object Decatur 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: Decatur | Statement: [East Lake station, servesCity, Decatur]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Decatur
Context triple: [East Lake station, servesCity, Decatur]
  • A. Decatur chosen
    Decatur is a historic, densely populated small city in DeKalb County, Georgia, known for its walkable downtown, vibrant arts and dining scene, and close proximity to Atlanta.
  • B. Decatur
    Decatur is a surname of English origin borne by various notable individuals and families.
  • C. Decatur
    Decatur is a city in northern Alabama known for its location along the Tennessee River and its role as an industrial and transportation hub.
  • D. Decatur
    Decatur is a small town located within Otsego County in the state of New York, United States.
  • E. Decatur, Illinois
    Decatur, Illinois is a mid-sized industrial and agricultural city in central Illinois known historically for manufacturing, agribusiness, and its location along Lake Decatur.
  • 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_69e0b4bb2b4081908fa4a72444120f35 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6aa233e1881908749d2f29c2946e4 completed April 20, 2026, 10:35 p.m.
Created at: April 16, 2026, 11:41 a.m.