Triple

T1568108
Position Surface form Disambiguated ID Type / Status
Subject National Capital Parks-East E33477 entity
Predicate hasPart P35 FINISHED
Object Greenbelt Park
Greenbelt Park is a wooded national park in Greenbelt, Maryland, offering camping, hiking, and other outdoor recreation just outside Washington, D.C.
E179622 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: Greenbelt Park | Statement: [National Capital Parks-East, hasPart, Greenbelt Park]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Greenbelt Park
Context triple: [National Capital Parks-East, hasPart, Greenbelt Park]
  • A. Fairbridge Park
    Fairbridge Park is a residential suburb of the city of Mutare in eastern Zimbabwe.
  • B. Topstone Park
    Topstone Park is a natural recreational area in Redding, Connecticut, known for its wooded trails, swimming pond, and outdoor activities.
  • C. Green Hill Park
    Green Hill Park is a large public park in Worcester, Massachusetts, known for its open green spaces, recreational facilities, and scenic views.
  • D. Wilacre Park
    Wilacre Park is a popular urban park and hiking area in the Studio City neighborhood of Los Angeles, known for its scenic trails and views of the San Fernando Valley.
  • E. Glyndon Park
    Glyndon Park is a local public park in Vienna, Virginia, offering recreational green space and community amenities for residents and visitors.
  • 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: Greenbelt Park
Triple: [National Capital Parks-East, hasPart, Greenbelt Park]
Generated description
Greenbelt Park is a wooded national park in Greenbelt, Maryland, offering camping, hiking, and other outdoor recreation just outside Washington, D.C.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Greenbelt Park
Target entity description: Greenbelt Park is a wooded national park in Greenbelt, Maryland, offering camping, hiking, and other outdoor recreation just outside Washington, D.C.
  • A. Fairbridge Park
    Fairbridge Park is a residential suburb of the city of Mutare in eastern Zimbabwe.
  • B. Topstone Park
    Topstone Park is a natural recreational area in Redding, Connecticut, known for its wooded trails, swimming pond, and outdoor activities.
  • C. Green Hill Park
    Green Hill Park is a large public park in Worcester, Massachusetts, known for its open green spaces, recreational facilities, and scenic views.
  • D. Wilacre Park
    Wilacre Park is a popular urban park and hiking area in the Studio City neighborhood of Los Angeles, known for its scenic trails and views of the San Fernando Valley.
  • E. Glyndon Park
    Glyndon Park is a local public park in Vienna, Virginia, offering recreational green space and community amenities for residents and visitors.
  • 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_69a885f11b048190935025a035302715 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a908a15e308190b8bec55d1712812a completed March 5, 2026, 4:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad4023da008190a947cf0d2983df2e completed March 8, 2026, 9:23 a.m.
NEDg Description generation batch_69ad410ba7f881909dcee6e6fd56490f completed March 8, 2026, 9:27 a.m.
NED2 Entity disambiguation (via description) batch_69ad41ff0b0c8190b5429ed6952a0ce6 completed March 8, 2026, 9:31 a.m.
Created at: March 4, 2026, 7:27 p.m.