Triple

T10243386
Position Surface form Disambiguated ID Type / Status
Subject Kooser State Park E243654 entity
Predicate hasWaterbody P19308 FINISHED
Object Kooser Lake
Kooser Lake is a small recreational lake in Pennsylvania known for fishing, picnicking, and scenic woodland surroundings within Kooser State Park.
E1048066 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: Kooser Lake | Statement: [Kooser State Park, hasWaterbody, Kooser Lake]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kooser Lake
Context triple: [Kooser State Park, hasWaterbody, Kooser Lake]
  • A. Korsman Lake
    Korsman Lake is a small urban lake and bird sanctuary located in the suburb of Benoni in Gauteng, South Africa.
  • B. Niven Lake
    Niven Lake is a residential neighbourhood in Yellowknife, Northwest Territories, known for its proximity to the lake of the same name and access to local trails and natural scenery.
  • C. Inks Lake
    Inks Lake is a scenic Highland Lakes reservoir in the Texas Hill Country, popular for boating, fishing, and camping.
  • D. Sisko Lake
    Sisko Lake is a mountain lake located within Montenegro’s Biogradska Gora National Park, an area known for its primeval forests and glacial lakes.
  • E. Mason Lake
    Mason Lake is a freshwater lake in western Washington State known for recreational activities such as boating, fishing, and lakeside cabin retreats.
  • 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: Kooser Lake
Triple: [Kooser State Park, hasWaterbody, Kooser Lake]
Generated description
Kooser Lake is a small recreational lake in Pennsylvania known for fishing, picnicking, and scenic woodland surroundings within Kooser State Park.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kooser Lake
Target entity description: Kooser Lake is a small recreational lake in Pennsylvania known for fishing, picnicking, and scenic woodland surroundings within Kooser State Park.
  • A. Korsman Lake
    Korsman Lake is a small urban lake and bird sanctuary located in the suburb of Benoni in Gauteng, South Africa.
  • B. Niven Lake
    Niven Lake is a residential neighbourhood in Yellowknife, Northwest Territories, known for its proximity to the lake of the same name and access to local trails and natural scenery.
  • C. Inks Lake
    Inks Lake is a scenic Highland Lakes reservoir in the Texas Hill Country, popular for boating, fishing, and camping.
  • D. Sisko Lake
    Sisko Lake is a mountain lake located within Montenegro’s Biogradska Gora National Park, an area known for its primeval forests and glacial lakes.
  • E. Mason Lake
    Mason Lake is a freshwater lake in western Washington State known for recreational activities such as boating, fishing, and lakeside cabin retreats.
  • 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_69d381b0f97c819085c9b45799a5fb7c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d22a76188190a73df23bfb08eb3d completed April 7, 2026, 9:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69f76b9112948190a0dd747a67f8206a completed May 3, 2026, 3:36 p.m.
NEDg Description generation batch_69f7763fc23c819098d46ab0906b8764 completed May 3, 2026, 4:22 p.m.
NED2 Entity disambiguation (via description) batch_69f7791add908190af69b23a54eb7560 completed May 3, 2026, 4:34 p.m.
Created at: April 6, 2026, 11:25 a.m.