Triple

T15714484
Position Surface form Disambiguated ID Type / Status
Subject Town of Lenox E380924 entity
Predicate hasAttraction P105 FINISHED
Object Kennedy Park
Kennedy Park is a popular forested recreation area in Lenox, Massachusetts, known for its hiking and cross-country skiing trails and scenic Berkshire views.
E1445585 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: Kennedy Park | Statement: [Town of Lenox, hasAttraction, Kennedy Park]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kennedy Park
Context triple: [Town of Lenox, hasAttraction, Kennedy Park]
  • A. Kennedy Park
    Kennedy Park is a residential neighbourhood in the Scarborough district of Toronto, Ontario, Canada.
  • B. Kennedy Park
    Kennedy Park is a public recreational park located in Sayreville, New Jersey, offering outdoor spaces and facilities for community activities and leisure.
  • C. Kennedy Park
    Kennedy Park is a public recreational park located in the city of El Cajon, California.
  • D. Clum-Kennedy Park
    Clum-Kennedy Park is a small community park in Kensington, Maryland, offering local residents green space and recreational amenities.
  • E. Sheehan Park
    Sheehan Park is a public recreational park in Sun Prairie, Wisconsin, featuring open green spaces, sports facilities, and community amenities for local 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: Kennedy Park
Triple: [Town of Lenox, hasAttraction, Kennedy Park]
Generated description
Kennedy Park is a popular forested recreation area in Lenox, Massachusetts, known for its hiking and cross-country skiing trails and scenic Berkshire views.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kennedy Park
Target entity description: Kennedy Park is a popular forested recreation area in Lenox, Massachusetts, known for its hiking and cross-country skiing trails and scenic Berkshire views.
  • A. Kennedy Park
    Kennedy Park is a residential neighbourhood in the Scarborough district of Toronto, Ontario, Canada.
  • B. Kennedy Park
    Kennedy Park is a public recreational park located in Sayreville, New Jersey, offering outdoor spaces and facilities for community activities and leisure.
  • C. Kennedy Park
    Kennedy Park is a public recreational park located in the city of El Cajon, California.
  • D. Clum-Kennedy Park
    Clum-Kennedy Park is a small community park in Kensington, Maryland, offering local residents green space and recreational amenities.
  • E. Sheehan Park
    Sheehan Park is a public recreational park in Sun Prairie, Wisconsin, featuring open green spaces, sports facilities, and community amenities for local 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_69d86d9bf930819082b30cf6d169297c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f90aea0819082a9e9fe0f7780b0 completed April 16, 2026, 2:55 a.m.
NED1 Entity disambiguation (via context triple) batch_6a08d7c569a481909b595b0517fbee7d completed May 16, 2026, 8:47 p.m.
NEDg Description generation batch_6a08d902cab481908d0a7b28699a2031 completed May 16, 2026, 8:52 p.m.
NED2 Entity disambiguation (via description) batch_6a08d9693acc8190acc75cbbf06b62da completed May 16, 2026, 8:54 p.m.
Created at: April 10, 2026, 4:45 a.m.