Triple

T21715395

Position	Surface form	Disambiguated ID	Type / Status
Subject	Battle of Harpers Ferry	`E536013`	entity
Predicate	commander	`P1061`	FINISHED
Object	Dixon S. Miles Dixon S. Miles was a U.S. Army officer and Civil War Union colonel best known for his controversial surrender of Harpers Ferry to Confederate forces in 1862.	`E2289859`	NE FINISHED

How this triple was built (2 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: Dixon S. Miles | Statement: [Battle of Harpers Ferry, commander, Dixon S. Miles]

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: Dixon S. Miles
Triple: [Battle of Harpers Ferry, commander, Dixon S. Miles]

Generated description

Dixon S. Miles was a U.S. Army officer and Civil War Union colonel best known for his controversial surrender of Harpers Ferry to Confederate forces in 1862.

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_69e0c46c6dd88190a595375fa6ebd701`	completed	April 16, 2026, 11:13 a.m.
NER	Named-entity recognition	`batch_69efb53761b48190954a46e8155a84f0`	completed	April 27, 2026, 7:12 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a5b753daca48190a12a3efdd62c3992`	completed	July 18, 2026, 12:44 p.m.
NEDg	Description generation	`batch_6a5b75a6bd788190bc723d6abd3e9950`	completed	July 18, 2026, 12:46 p.m.
NED2	Entity disambiguation (via description)	`batch_6a5b7661845c8190ab5672c776bd38ac`	completed	July 18, 2026, 12:49 p.m.

Created at: April 16, 2026, 6:47 p.m.