Triple

T5852578
Position Surface form Disambiguated ID Type / Status
Subject Sandown, New Hampshire E130070 entity
Predicate hasRecreationArea P5383 FINISHED
Object Showell Pond
Showell Pond is a small recreational lake in Sandown, New Hampshire, used for outdoor activities such as fishing and boating.
E562883 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: Showell Pond | Statement: [Sandown, New Hampshire, hasRecreationArea, Showell Pond]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Showell Pond
Context triple: [Sandown, New Hampshire, hasRecreationArea, Showell Pond]
  • A. Pillings Pond
    Pillings Pond is a small recreational and scenic pond located in the town of Lynnfield, Massachusetts.
  • B. Shaw Pond
    Shaw Pond is a small natural lake located in the town of Becket in western Massachusetts, known for its quiet, rural setting and recreational use.
  • C. Osgood Pond
    Osgood Pond is a scenic lake in New York’s Adirondack region known for its historic great camps, boating, and natural beauty.
  • D. Parchers Pond
    Parchers Pond is a small alpine lake in the eastern Sierra Nevada of California, popular as a scenic spot for fishing and hiking near Bishop Creek.
  • E. Leverett Pond
    Leverett Pond is a scenic urban pond in Boston, Massachusetts, that forms part of the Emerald Necklace park system designed by Frederick Law Olmsted.
  • 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: Showell Pond
Triple: [Sandown, New Hampshire, hasRecreationArea, Showell Pond]
Generated description
Showell Pond is a small recreational lake in Sandown, New Hampshire, used for outdoor activities such as fishing and boating.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Showell Pond
Target entity description: Showell Pond is a small recreational lake in Sandown, New Hampshire, used for outdoor activities such as fishing and boating.
  • A. Pillings Pond
    Pillings Pond is a small recreational and scenic pond located in the town of Lynnfield, Massachusetts.
  • B. Shaw Pond
    Shaw Pond is a small natural lake located in the town of Becket in western Massachusetts, known for its quiet, rural setting and recreational use.
  • C. Osgood Pond
    Osgood Pond is a scenic lake in New York’s Adirondack region known for its historic great camps, boating, and natural beauty.
  • D. Parchers Pond
    Parchers Pond is a small alpine lake in the eastern Sierra Nevada of California, popular as a scenic spot for fishing and hiking near Bishop Creek.
  • E. Leverett Pond
    Leverett Pond is a scenic urban pond in Boston, Massachusetts, that forms part of the Emerald Necklace park system designed by Frederick Law Olmsted.
  • 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_69c0084de39081909eb34e6bed74215a completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0355038008190bf38980349b533e2 completed March 22, 2026, 6:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69c107f608c48190b613741bf2686af7 completed March 23, 2026, 9:29 a.m.
NEDg Description generation batch_69c1090a7bac8190b5b9e003659b4b34 completed March 23, 2026, 9:34 a.m.
NED2 Entity disambiguation (via description) batch_69c10d5102348190a9ec7421b1410a99 completed March 23, 2026, 9:52 a.m.
Created at: March 22, 2026, 3:55 p.m.