Triple

T5355565
Position Surface form Disambiguated ID Type / Status
Subject Chapel Point State Park E102680 entity
Predicate partOf P40 FINISHED
Object Maryland state park system
The Maryland state park system is a network of publicly managed natural, recreational, and historic areas across Maryland that provide outdoor recreation, conservation, and educational opportunities.
 E514509 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: Maryland state park system | Statement: [Chapel Point State Park, partOf, Maryland state park system]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Maryland state park system
Context triple: [Chapel Point State Park, partOf, Maryland state park system]
  • A. Pennsylvania state park system
    The Pennsylvania state park system is a network of publicly owned parks across Pennsylvania that preserves natural, cultural, and recreational resources while providing outdoor activities such as hiking, camping, and boating.
  • B. West Virginia State Parks
    West Virginia State Parks is the state-managed system of public parks and recreational areas in West Virginia, encompassing natural, historical, and cultural sites across the state.
  • C. Connecticut state park system
    The Connecticut state park system is a network of publicly managed parks and natural areas across Connecticut that preserve the state’s landscapes, history, and recreational resources for residents and visitors.
  • D. Massachusetts state park system
    The Massachusetts state park system is a network of publicly managed parks, reservations, forests, and historic sites across the state that provide recreation, conservation, and cultural preservation.
  • E. New Jersey State Park System
    The New Jersey State Park System is the statewide network of public parks, forests, recreation areas, and historic sites managed by the state of New Jersey for conservation and outdoor recreation.
  • 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: Maryland state park system
Triple: [Chapel Point State Park, partOf, Maryland state park system]
Generated description
The Maryland state park system is a network of publicly managed natural, recreational, and historic areas across Maryland that provide outdoor recreation, conservation, and educational opportunities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Maryland state park system
Target entity description: The Maryland state park system is a network of publicly managed natural, recreational, and historic areas across Maryland that provide outdoor recreation, conservation, and educational opportunities.
  • A. Pennsylvania state park system
    The Pennsylvania state park system is a network of publicly owned parks across Pennsylvania that preserves natural, cultural, and recreational resources while providing outdoor activities such as hiking, camping, and boating.
  • B. West Virginia State Parks
    West Virginia State Parks is the state-managed system of public parks and recreational areas in West Virginia, encompassing natural, historical, and cultural sites across the state.
  • C. Connecticut state park system
    The Connecticut state park system is a network of publicly managed parks and natural areas across Connecticut that preserve the state’s landscapes, history, and recreational resources for residents and visitors.
  • D. Massachusetts state park system
    The Massachusetts state park system is a network of publicly managed parks, reservations, forests, and historic sites across the state that provide recreation, conservation, and cultural preservation.
  • E. New Jersey State Park System
    The New Jersey State Park System is the statewide network of public parks, forests, recreation areas, and historic sites managed by the state of New Jersey for conservation and outdoor recreation.
  • 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_69bd43d8f7248190b64c140734b5c9a8 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd862f0ea48190bec78690ab3bee51 completed March 20, 2026, 5:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf21df856c819099cf9047b87d6db8 completed March 21, 2026, 10:55 p.m.
NEDg Description generation batch_69bf22a6e3c081908a18bd370f924d39 completed March 21, 2026, 10:58 p.m.
NED2 Entity disambiguation (via description) batch_69bf22fb8db48190b7ce94e5df8ed37f completed March 21, 2026, 11 p.m.
Created at: March 20, 2026, 2:01 p.m.