Triple

T16671352
Position Surface form Disambiguated ID Type / Status
Subject Walden Woods Project E405111 entity
Predicate operates P24 FINISHED
Object Thoreau Institute at Walden Woods
The Thoreau Institute at Walden Woods is a research and education center dedicated to the life, writings, and environmental legacy of Henry David Thoreau, located near Walden Pond in Massachusetts.
E1227260 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: Thoreau Institute at Walden Woods | Statement: [Walden Woods Project, operates, Thoreau Institute at Walden Woods]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thoreau Institute at Walden Woods
Context triple: [Walden Woods Project, operates, Thoreau Institute at Walden Woods]
  • A. Walden Woods Project
    Walden Woods Project is a nonprofit organization dedicated to preserving the land, legacy, and literary heritage associated with Henry David Thoreau’s Walden Woods in Massachusetts.
  • B. George Perkins Marsh Institute
    The George Perkins Marsh Institute is a prominent interdisciplinary research center at Clark University focused on human-environment interactions, sustainability, and global environmental change.
  • C. Pocumtuck Valley Memorial Association
    The Pocumtuck Valley Memorial Association is a regional historical and cultural organization in Deerfield, Massachusetts, dedicated to preserving and interpreting the history, art, and material culture of the Connecticut River Valley.
  • D. The Trustees of Reservations
    The Trustees of Reservations is a Massachusetts-based nonprofit land conservation and historic preservation organization that protects and maintains numerous natural and cultural sites across the state for public use and enjoyment.
  • E. Fruitlands Museum
    Fruitlands Museum is a historic museum complex in Harvard, Massachusetts, featuring collections and sites related to Transcendentalism, Shaker life, Native American history, and early American art.
  • 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: Thoreau Institute at Walden Woods
Triple: [Walden Woods Project, operates, Thoreau Institute at Walden Woods]
Generated description
The Thoreau Institute at Walden Woods is a research and education center dedicated to the life, writings, and environmental legacy of Henry David Thoreau, located near Walden Pond in Massachusetts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Thoreau Institute at Walden Woods
Target entity description: The Thoreau Institute at Walden Woods is a research and education center dedicated to the life, writings, and environmental legacy of Henry David Thoreau, located near Walden Pond in Massachusetts.
  • A. Walden Woods Project
    Walden Woods Project is a nonprofit organization dedicated to preserving the land, legacy, and literary heritage associated with Henry David Thoreau’s Walden Woods in Massachusetts.
  • B. George Perkins Marsh Institute
    The George Perkins Marsh Institute is a prominent interdisciplinary research center at Clark University focused on human-environment interactions, sustainability, and global environmental change.
  • C. Pocumtuck Valley Memorial Association
    The Pocumtuck Valley Memorial Association is a regional historical and cultural organization in Deerfield, Massachusetts, dedicated to preserving and interpreting the history, art, and material culture of the Connecticut River Valley.
  • D. The Trustees of Reservations
    The Trustees of Reservations is a Massachusetts-based nonprofit land conservation and historic preservation organization that protects and maintains numerous natural and cultural sites across the state for public use and enjoyment.
  • E. Fruitlands Museum
    Fruitlands Museum is a historic museum complex in Harvard, Massachusetts, featuring collections and sites related to Transcendentalism, Shaker life, Native American history, and early American art.
  • 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_69d8838b5fbc81908c6575c132b82e80 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e37ca175088190a0435422e13278c2 completed April 18, 2026, 12:44 p.m.
NED1 Entity disambiguation (via context triple) batch_6a008a3692588190a94d349cb63d9749 completed May 10, 2026, 1:37 p.m.
NEDg Description generation batch_6a008ad087b08190b725382c68687a15 completed May 10, 2026, 1:40 p.m.
NED2 Entity disambiguation (via description) batch_6a008ba8227881908b1ac6e30d2e7c32 completed May 10, 2026, 1:44 p.m.
Created at: April 10, 2026, 5:18 a.m.