Triple

T18737050
Position Surface form Disambiguated ID Type / Status
Subject Kaaterskill Creek E458190 entity
Predicate hasTributary P415 FINISHED
Object Huckleberry Brook
Huckleberry Brook is a small stream in New York’s Catskill Mountains that feeds into Kaaterskill Creek.
E1341448 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: Huckleberry Brook | Statement: [Kaaterskill Creek, hasTributary, Huckleberry Brook]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Huckleberry Brook
Context triple: [Kaaterskill Creek, hasTributary, Huckleberry Brook]
  • A. Quaker Brook
    Quaker Brook is a small stream in Michigan that serves as a tributary to the Thornapple River within the Grand River watershed.
  • B. Harriman Brook
    Harriman Brook is a small stream in New Hampshire that feeds into the Ellis River within the Saco River watershed.
  • C. Canistear Brook
    Canistear Brook is a stream in New Jersey that serves as a tributary feeding into the Canistear Reservoir within the state's water supply system.
  • D. Hoo Brook
    Hoo Brook is a small watercourse in Worcestershire, England, that serves as a minor tributary within the River Stour catchment.
  • E. Sherman Brook
    Sherman Brook is a small tributary stream that joins with other waterways to form part of the Yantic River system in Connecticut.
  • 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: Huckleberry Brook
Triple: [Kaaterskill Creek, hasTributary, Huckleberry Brook]
Generated description
Huckleberry Brook is a small stream in New York’s Catskill Mountains that feeds into Kaaterskill Creek.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Huckleberry Brook
Target entity description: Huckleberry Brook is a small stream in New York’s Catskill Mountains that feeds into Kaaterskill Creek.
  • A. Quaker Brook
    Quaker Brook is a small stream in Michigan that serves as a tributary to the Thornapple River within the Grand River watershed.
  • B. Harriman Brook
    Harriman Brook is a small stream in New Hampshire that feeds into the Ellis River within the Saco River watershed.
  • C. Canistear Brook
    Canistear Brook is a stream in New Jersey that serves as a tributary feeding into the Canistear Reservoir within the state's water supply system.
  • D. Hoo Brook
    Hoo Brook is a small watercourse in Worcestershire, England, that serves as a minor tributary within the River Stour catchment.
  • E. Sherman Brook
    Sherman Brook is a small tributary stream that joins with other waterways to form part of the Yantic River system in Connecticut.
  • 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_69d8d394dc308190b6725073f5db324c completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e57689fa508190ad821d361cba9edf completed April 20, 2026, 12:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a053d2f42d8819093fd6de6639afd06 completed May 14, 2026, 3:10 a.m.
NEDg Description generation batch_6a053e61f6148190915f8e63d0aa6ac0 completed May 14, 2026, 3:15 a.m.
NED2 Entity disambiguation (via description) batch_6a053ea94058819090144743376cf68f completed May 14, 2026, 3:16 a.m.
Created at: April 10, 2026, 11:51 a.m.