Triple

T3508648
Position Surface form Disambiguated ID Type / Status
Subject Souhegan River E74141 entity
Predicate crossesTown P27425 FINISHED
Object Wilton
Wilton is a small New Hampshire town known for its rural character, historic mill village, and location along the Souhegan River.
 E362827 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: Wilton | Statement: [Souhegan River, crossesTown, Wilton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Wilton
Context triple: [Souhegan River, crossesTown, Wilton]
  • A. Wilton
    Wilton is a town in Saratoga County, New York, known for its suburban communities, commercial development, and proximity to Saratoga Springs.
  • B. Wilton
    Wilton was a former UK parliamentary constituency in Wiltshire, historically represented in the House of Commons before its abolition in the 19th century.
  • C. Marlborough
    Marlborough is a renowned wine-producing region in New Zealand, celebrated especially for its high-quality cool-climate varietals.
  • D. Marlborough
    Marlborough is a historic market town in Wiltshire, England, known for its broad High Street and well-preserved architecture.
  • E. Marlborough
    Marlborough is a small New England town in central Connecticut known for its rural character and residential communities.
  • 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: Wilton
Triple: [Souhegan River, crossesTown, Wilton]
Generated description
Wilton is a small New Hampshire town known for its rural character, historic mill village, and location along the Souhegan River.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Wilton
Target entity description: Wilton is a small New Hampshire town known for its rural character, historic mill village, and location along the Souhegan River.
  • A. Wilton
    Wilton is a town in Saratoga County, New York, known for its suburban communities, commercial development, and proximity to Saratoga Springs.
  • B. Wilton
    Wilton was a former UK parliamentary constituency in Wiltshire, historically represented in the House of Commons before its abolition in the 19th century.
  • C. Marlborough
    Marlborough is a renowned wine-producing region in New Zealand, celebrated especially for its high-quality cool-climate varietals.
  • D. Marlborough
    Marlborough is a historic market town in Wiltshire, England, known for its broad High Street and well-preserved architecture.
  • E. Marlborough
    Marlborough is a small New England town in central Connecticut known for its rural character and residential communities.
  • 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_69ad85ce7a9c81909ddc5cf0cb67a6e3 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adbc0cc394819087a9b598023f4f93 completed March 8, 2026, 6:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69b373e3cd808190807d4acae2942a9d completed March 13, 2026, 2:18 a.m.
NEDg Description generation batch_69b3746f1de4819091c5bcbf8a988ef1 completed March 13, 2026, 2:20 a.m.
NED2 Entity disambiguation (via description) batch_69b374f5999c8190ae48570a412dc6dc completed March 13, 2026, 2:22 a.m.
Created at: March 8, 2026, 3:18 p.m.