Triple

T18501918
Position Surface form Disambiguated ID Type / Status
Subject Fulton County, Indiana E452094 entity
Predicate countySeat P383 FINISHED
Object Rochester
Rochester is a small city in northern Indiana that serves as the administrative and commercial hub of Fulton County.
 E1333902 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: Rochester | Statement: [Fulton County, Indiana, countySeat, Rochester]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Rochester
Context triple: [Fulton County, Indiana, countySeat, Rochester]
  • A. Rochester
    Rochester is a major city in western New York State known historically for its role in industry, photography, and social reform movements.
  • B. Rochester
    Rochester is a small historic town in southeastern Massachusetts known for its rural character and New England charm.
  • C. Rochester
    Rochester is a major city in southeastern Minnesota known for being the home of the world-renowned Mayo Clinic.
  • D. Rochester
    Rochester is a rural town in northern Victoria, Australia, known for its agricultural community and location near the Campaspe River.
  • E. Rochester
    Rochester is a fictional English surname most famously borne by Mr. Edward Rochester, the brooding Byronic hero in Charlotte Brontë’s novel "Jane Eyre."
  • 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: Rochester
Triple: [Fulton County, Indiana, countySeat, Rochester]
Generated description
Rochester is a small city in northern Indiana that serves as the administrative and commercial hub of Fulton County.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Rochester
Target entity description: Rochester is a small city in northern Indiana that serves as the administrative and commercial hub of Fulton County.
  • A. Rochester
    Rochester is a small village located in Lorain County in the U.S. state of Ohio.
  • B. Rochester
    Rochester is a small borough in western Pennsylvania situated along the Ohio River in Beaver County.
  • C. Rochester
    Rochester is a major city in western New York State known historically for its role in industry, photography, and social reform movements.
  • D. Rochester
    Rochester is a small historic town in southeastern Massachusetts known for its rural character and New England charm.
  • E. Rochester
    Rochester is a major city in southeastern Minnesota known for being the home of the world-renowned Mayo Clinic.
  • 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_69d8d3855d50819097fc8561b0299dd9 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e532c535908190bdc90c58fc5bdaf7 completed April 19, 2026, 7:53 p.m.
NED1 Entity disambiguation (via context triple) batch_6a05036a457481909ee7e4b1b8246797 completed May 13, 2026, 11:04 p.m.
NEDg Description generation batch_6a05076aaaf08190a1412e1801b65a77 completed May 13, 2026, 11:21 p.m.
NED2 Entity disambiguation (via description) batch_6a05080e38488190aa619ec1f38f77de completed May 13, 2026, 11:23 p.m.
Created at: April 10, 2026, 11:36 a.m.