Triple

T18304028

Position	Surface form	Disambiguated ID	Type / Status
Subject	Penobscot River watershed	`E438434`	entity
Predicate	includesProtectedArea	`P855`	FINISHED
Object	Katahdin Woods and Waters National Monument Katahdin Woods and Waters National Monument is a federally protected wilderness area in north-central Maine known for its forests, rivers, wildlife habitat, and views of Mount Katahdin.	`E1317390`	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: Katahdin Woods and Waters National Monument | Statement: [Penobscot River watershed, includesProtectedArea, Katahdin Woods and Waters National Monument]

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07

Target entity: Katahdin Woods and Waters National Monument
Context triple: [Penobscot River watershed, includesProtectedArea, Katahdin Woods and Waters National Monument]

A. White Mountains National Recreation Area
White Mountains National Recreation Area is a vast, remote public land unit in central Alaska known for its rugged mountains, boreal forests, and extensive opportunities for backcountry recreation such as hiking, skiing, and dog mushing.
B. Green Mountain National Park
Green Mountain National Park is a protected natural area on Ascension Island known for its unique cloud forest, rich biodiversity, and network of hiking trails centered around the island’s highest peak.
C. Camel's Hump State Park
Camel's Hump State Park is a protected natural area in Vermont centered around the iconic Camel's Hump mountain, known for its rugged hiking, scenic vistas, and extensive backcountry trails.
D. Katahdin summit area
The Katahdin summit area is the high, exposed alpine plateau and collection of peaks at the top of Maine’s tallest mountain, known for its rugged terrain, dramatic cliffs, and panoramic views.
E. Rangeley Lake State Park
Rangeley Lake State Park is a public recreation area in western Maine known for its lakeside camping, boating, fishing, and scenic mountain views.
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: Katahdin Woods and Waters National Monument
Triple: [Penobscot River watershed, includesProtectedArea, Katahdin Woods and Waters National Monument]

Generated description

Katahdin Woods and Waters National Monument is a federally protected wilderness area in north-central Maine known for its forests, rivers, wildlife habitat, and views of Mount Katahdin.

NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07

Target entity: Katahdin Woods and Waters National Monument
Target entity description: Katahdin Woods and Waters National Monument is a federally protected wilderness area in north-central Maine known for its forests, rivers, wildlife habitat, and views of Mount Katahdin.

A. White Mountains National Recreation Area
White Mountains National Recreation Area is a vast, remote public land unit in central Alaska known for its rugged mountains, boreal forests, and extensive opportunities for backcountry recreation such as hiking, skiing, and dog mushing.
B. Green Mountain National Park
Green Mountain National Park is a protected natural area on Ascension Island known for its unique cloud forest, rich biodiversity, and network of hiking trails centered around the island’s highest peak.
C. Camel's Hump State Park
Camel's Hump State Park is a protected natural area in Vermont centered around the iconic Camel's Hump mountain, known for its rugged hiking, scenic vistas, and extensive backcountry trails.
D. Katahdin summit area
The Katahdin summit area is the high, exposed alpine plateau and collection of peaks at the top of Maine’s tallest mountain, known for its rugged terrain, dramatic cliffs, and panoramic views.
E. Rangeley Lake State Park
Rangeley Lake State Park is a public recreation area in western Maine known for its lakeside camping, boating, fishing, and scenic mountain views.
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_69d8b915e3e881909125d760c15d0c29`	completed	April 10, 2026, 8:47 a.m.
NER	Named-entity recognition	`batch_69e5018256508190b024980e3a4a3ae9`	completed	April 19, 2026, 4:23 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a03bb5ff1e0819089602e4a0942582d`	completed	May 12, 2026, 11:44 p.m.
NEDg	Description generation	`batch_6a03bd7388f48190bc4248b999053a21`	completed	May 12, 2026, 11:53 p.m.
NED2	Entity disambiguation (via description)	`batch_6a03be6ec6208190858af9401f33ead6`	completed	May 12, 2026, 11:57 p.m.

Created at: April 10, 2026, 10:35 a.m.