Triple

T31065985

Position	Surface form	Disambiguated ID	Type / Status
Subject	D. H. Hill's Division (Army of Northern Virginia)	`E791668`	entity
Predicate	garrisonOrAreaOfOperation	`P19869`	FINISHED
Object	Virginia Virginia is a U.S. state in the Mid-Atlantic and Southeastern regions, historically significant as a key battleground of the American Civil War and home to numerous early American colonial and Revolutionary War sites.	`E5410`	NE FINISHED

How this triple was built (3 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: Virginia | Statement: [D. H. Hill's Division (Army of Northern Virginia), garrisonOrAreaOfOperation, Virginia]

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: Virginia
Triple: [D. H. Hill's Division (Army of Northern Virginia), garrisonOrAreaOfOperation, Virginia]

Generated description

Virginia is a U.S. state in the Mid-Atlantic and Southeastern regions, historically significant as a key battleground of the American Civil War and home to numerous early American colonial and Revolutionary War sites.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: garrisonOrAreaOfOperation
Context triple: [D. H. Hill's Division (Army of Northern Virginia), garrisonOrAreaOfOperation, Virginia]

A. garrisonOrRecruitmentArea
Indicates an area designated for stationing military forces or for recruiting personnel into those forces.
B. garrisonOrAssemblyArea chosen
Indicates a location where military forces are stationed, housed, or gathered for organization, preparation, or deployment.
C. garrisonRegion
Indicates that a military force is stationed in and responsible for defending a specific region.
D. garrisonOrTheater
Indicates that one entity serves as a military garrison or theater of operations for another entity.
E. garrisonOrMobilizationPoint
Indicates a location where military forces are stationed, assembled, or prepared for deployment or mobilization.
F. None of above.

Provenance (6 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_69f224cc0c5c81908404f087bff92997`	completed	April 29, 2026, 3:33 p.m.
NER	Named-entity recognition	`batch_69f6957aee008190a04d15daf49d5f08`	completed	May 3, 2026, 12:23 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a293895fd348190ac766f445d81f966`	completed	June 10, 2026, 10:12 a.m.
NEDg	Description generation	`batch_6a293c7e72f4819090260ad1d80770b7`	completed	June 10, 2026, 10:29 a.m.
NED2	Entity disambiguation (via description)	`batch_6a293d3b720c8190afd50e5e7c2a0997`	completed	June 10, 2026, 10:32 a.m.
PD	Predicate disambiguation	`batch_69f690f13d7481908ddfefe95df2a1c2`	completed	May 3, 2026, 12:04 a.m.

Created at: April 29, 2026, 9:01 p.m.