Triple

T15728293
Position Surface form Disambiguated ID Type / Status
Subject Dubois County E381273 entity
Predicate hasSettlement P1068 FINISHED
Object Ferdinand, Indiana E1199088 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: Ferdinand, Indiana | Statement: [Dubois County, hasSettlement, Ferdinand, Indiana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ferdinand, Indiana
Context triple: [Dubois County, hasSettlement, Ferdinand, Indiana]
  • A. Ferdinand, Indiana chosen
    Ferdinand, Indiana is a small town in southern Indiana known for its strong German heritage and the historic Monastery of Immaculate Conception.
  • B. Fayette, Indiana
    Fayette, Indiana is a small unincorporated community located within Boone County in the U.S. state of Indiana.
  • C. Winfield, Indiana
    Winfield, Indiana is a small suburban town in northwest Indiana known for its residential communities and proximity to the Chicago metropolitan area.
  • D. Mishawaka, Indiana
    Mishawaka, Indiana is a city in northern Indiana near South Bend, known for its manufacturing history and as the longtime base of vehicle maker AM General.
  • E. Madison, Indiana
    Madison, Indiana is a historic river town on the Ohio River known for its well-preserved 19th-century architecture and vibrant small-town cultural life.
  • 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_69d86d9cdb648190bf3171be0bd7d872 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04fb4cc0081909efe330339474017 completed April 16, 2026, 2:55 a.m.
NED1 Entity disambiguation (via context triple) batch_6a000ec1091c8190a8e4c4db6180129a completed May 10, 2026, 4:51 a.m.
Created at: April 10, 2026, 4:46 a.m.