Triple

T18442141
Position Surface form Disambiguated ID Type / Status
Subject Kosciusko County, Indiana E450556 entity
Predicate contains P35 FINISHED
Object Milford, Indiana
Milford, Indiana is a small town in northern Indiana known for its agricultural surroundings and close-knit community.
E1326463 NE FINISHED

How this triple was built (4 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: Milford, Indiana | Statement: [Kosciusko County, Indiana, contains, Milford, Indiana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Milford, Indiana
Context triple: [Kosciusko County, Indiana, contains, Milford, Indiana]
  • A. Milton, Indiana
    Milton, Indiana is a small rural town located in eastern Indiana within Wayne County.
  • B. Millville, Indiana
    Millville, Indiana is a small unincorporated community in Henry County best known as the birthplace of aviation pioneer Wilbur Wright.
  • C. Milltown, Indiana
    Milltown, Indiana is a small town in southern Indiana known for its rural character and proximity to outdoor recreation areas like the Blue River.
  • D. Milo, Indiana
    Milo, Indiana is an unincorporated rural community located in Huntington County in the U.S. state of Indiana.
  • E. Markleville, Indiana
    Markleville, Indiana is a small rural town in central Indiana known for its close-knit community and location within the Indianapolis metropolitan area.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Milford, Indiana
Triple: [Kosciusko County, Indiana, contains, Milford, Indiana]
Generated description
Milford, Indiana is a small town in northern Indiana known for its agricultural surroundings and close-knit community.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Milford, Indiana
Target entity description: Milford, Indiana is a small town in northern Indiana known for its agricultural surroundings and close-knit community.
  • A. Milton, Indiana
    Milton, Indiana is a small rural town located in eastern Indiana within Wayne County.
  • B. Millville, Indiana
    Millville, Indiana is a small unincorporated community in Henry County best known as the birthplace of aviation pioneer Wilbur Wright.
  • C. Milltown, Indiana
    Milltown, Indiana is a small town in southern Indiana known for its rural character and proximity to outdoor recreation areas like the Blue River.
  • D. Milo, Indiana
    Milo, Indiana is an unincorporated rural community located in Huntington County in the U.S. state of Indiana.
  • E. Markleville, Indiana
    Markleville, Indiana is a small rural town in central Indiana known for its close-knit community and location within the Indianapolis metropolitan area.
  • F. None of above. chosen

Provenance (5 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_69d8d381d6388190a9e94e9c658174e4 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e51c11b1288190b9ed4497751197d1 completed April 19, 2026, 6:16 p.m.
NED1 Entity disambiguation (via context triple) batch_6a043f1ccc088190a65ca927243a7d01 completed May 13, 2026, 9:06 a.m.
NEDg Description generation batch_6a043f8fe6c08190b08f57b26a6862e3 completed May 13, 2026, 9:08 a.m.
NED2 Entity disambiguation (via description) batch_6a0441fd73d88190959e72208ec2da3c completed May 13, 2026, 9:18 a.m.
Created at: April 10, 2026, 11:30 a.m.