Triple

T19777273
Position Surface form Disambiguated ID Type / Status
Subject Ellisville E475033 entity
Predicate hasName P744 FINISHED
Object Ellisville 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: Ellisville | Statement: [Ellisville, hasName, Ellisville]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ellisville
Context triple: [Ellisville, hasName, Ellisville]
  • A. Ellisville
    Ellisville is a small unincorporated community located in Columbia County in northern Florida, United States.
  • B. Ellisville, Mississippi
    Ellisville, Mississippi is a small city in southeastern Mississippi that serves as the county seat of Jones County and is part of the Hattiesburg metropolitan area.
  • C. Labbeville
    Labbeville is a small French commune located in the Val-d'Oise department in the Île-de-France region of northern France.
  • D. Rayville
    Rayville is a small village located in Ray County, Missouri, in the United States.
  • E. Springfield, Louisiana
    Springfield, Louisiana is a small town in Livingston Parish known historically as one of the places where future U.S. President Zachary Taylor once lived.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

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_69d8e51a43a08190956bc6df13c91a77 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65360cca08190957c36b1a440542c completed April 20, 2026, 4:25 p.m.
Created at: April 10, 2026, 1:48 p.m.