Triple

T7341128
Position Surface form Disambiguated ID Type / Status
Subject Sandisfield, Massachusetts E169248 entity
Predicate hasWaterBody P165 FINISHED
Object Sandy Brook
Sandy Brook is a stream in Sandisfield, Massachusetts, that forms part of the town’s local freshwater system and natural landscape.
 E660517 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: Sandy Brook | Statement: [Sandisfield, Massachusetts, hasWaterBody, Sandy Brook]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sandy Brook
Context triple: [Sandisfield, Massachusetts, hasWaterBody, Sandy Brook]
  • A. Sandy Brook
    Sandy Brook is a small stream that serves as one of the natural water sources feeding Upper Mystic Lake in Massachusetts.
  • B. Porter Brook
    Porter Brook is a small urban river running through Sheffield, England, historically important for powering the city’s early industry.
  • C. Lincoln Brook
    Lincoln Brook is a small mountain stream located within the McKenzie Mountain Wilderness area of the Adirondack Park in New York State.
  • D. Tibbetts Brook
    Tibbetts Brook is a small natural waterway in the Bronx, New York City, that flows through Van Cortlandt Park and plays a key role in the park’s wetland and watershed system.
  • E. Mutton Brook
    Mutton Brook is a small stream in north London that forms part of the upper reaches of the River Brent and runs through several urban green spaces.
  • 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: Sandy Brook
Triple: [Sandisfield, Massachusetts, hasWaterBody, Sandy Brook]
Generated description
Sandy Brook is a stream in Sandisfield, Massachusetts, that forms part of the town’s local freshwater system and natural landscape.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sandy Brook
Target entity description: Sandy Brook is a stream in Sandisfield, Massachusetts, that forms part of the town’s local freshwater system and natural landscape.
  • A. Sandy Brook
    Sandy Brook is a small stream that serves as one of the natural water sources feeding Upper Mystic Lake in Massachusetts.
  • B. Porter Brook
    Porter Brook is a small urban river running through Sheffield, England, historically important for powering the city’s early industry.
  • C. Lincoln Brook
    Lincoln Brook is a small mountain stream located within the McKenzie Mountain Wilderness area of the Adirondack Park in New York State.
  • D. Tibbetts Brook
    Tibbetts Brook is a small natural waterway in the Bronx, New York City, that flows through Van Cortlandt Park and plays a key role in the park’s wetland and watershed system.
  • E. Mutton Brook
    Mutton Brook is a small stream in north London that forms part of the upper reaches of the River Brent and runs through several urban green spaces.
  • 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_69c68a57710481909f0c1f3c6ebdb6f2 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f0da176081909a40552c6f22087c completed March 27, 2026, 9:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69c802b032308190875b82c3ad169829 completed March 28, 2026, 4:32 p.m.
NEDg Description generation batch_69c806ea37308190983e3e216bba07d2 completed March 28, 2026, 4:50 p.m.
NED2 Entity disambiguation (via description) batch_69c80748a4d8819094e8e1b9994a1b5a completed March 28, 2026, 4:52 p.m.
Created at: March 27, 2026, 3:04 p.m.