Triple

T20796167
Position Surface form Disambiguated ID Type / Status
Subject Daegu E511913 entity
Predicate sisterCity P1072 FINISHED
Object Atlanta 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: Atlanta | Statement: [Daegu, sisterCity, Atlanta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Atlanta
Context triple: [Daegu, sisterCity, Atlanta]
  • A. Atlanta chosen
    Atlanta is the capital and largest city of the U.S. state of Georgia, known as a major cultural, economic, and transportation hub of the southeastern United States.
  • B. Atlanta
    Atlanta is a critically acclaimed American television comedy-drama series created by and starring Donald Glover, following an aspiring music manager navigating the Atlanta rap scene and complex social issues.
  • C. Statlanta
    "Statlanta" is the debut studio album by Atlanta rapper Stat Quo, showcasing his Southern hip-hop style and lyrical storytelling.
  • D. Macon
    Macon is a small town located in Warren County, North Carolina, known for its rural character and proximity to Lake Gaston.
  • E. Macon
    "Macon" is a country music album by American singer Jason Aldean, named after his hometown in Georgia and featuring a mix of new tracks and live recordings.
  • 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_69e0b4cb83948190bd57bec21d78ed53 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2ad6f0481909e0bab7119f10f9c completed April 21, 2026, 12:19 a.m.
Created at: April 16, 2026, 12:39 p.m.