Triple

T33155601

Position	Surface form	Disambiguated ID	Type / Status
Subject	Battle of the Modder River	`E848564`	entity
Predicate	artilleryUsedByBoers	`P34720`	FINISHED
Object	Creusot guns Creusot guns were large, long-range French-manufactured artillery pieces used by the Boers during the Second Boer War, noted for their powerful impact on several key battles.	`E2038059`	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: Creusot guns | Statement: [Battle of the Modder River, artilleryUsedByBoers, Creusot guns]

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: Creusot guns
Triple: [Battle of the Modder River, artilleryUsedByBoers, Creusot guns]

Generated description

Creusot guns were large, long-range French-manufactured artillery pieces used by the Boers during the Second Boer War, noted for their powerful impact on several key battles.

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

Target predicate: artilleryUsedByBoers
Context triple: [Battle of the Modder River, artilleryUsedByBoers, Creusot guns]

A. artilleryUsedIn
Indicates that a particular piece or type of artillery is employed or deployed in a specific event, operation, or context.
B. artilleryUsedBy chosen
Indicates that a particular artillery asset is operated or employed by a specified user, such as a military unit, organization, or country.
C. artilleryPiecesUsed
Indicates that certain artillery pieces were employed or deployed in a particular action, event, or context.
D. artilleryUsedFor
Indicates that artillery is employed or utilized for a particular purpose, function, or objective.
E. artillerySource
Indicates that one entity serves as the origin or launching point from which artillery fire or munitions are deployed toward another entity or location.
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_69f3495b02d08190bb3d366823dffc21`	completed	April 30, 2026, 12:21 p.m.
NER	Named-entity recognition	`batch_69f6e02ba6b881908dfafc52d3b75f1c`	completed	May 3, 2026, 5:42 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a3516311cf88190a07046f42600f690`	completed	June 19, 2026, 10:13 a.m.
NEDg	Description generation	`batch_6a3517ce00dc8190864201444c73b72e`	completed	June 19, 2026, 10:19 a.m.
NED2	Entity disambiguation (via description)	`batch_6a35189d08208190a922663bbc89c8dc`	completed	June 19, 2026, 10:23 a.m.
PD	Predicate disambiguation	`batch_69f6de09c2f481909f8b2545d3208c9f`	completed	May 3, 2026, 5:32 a.m.

Created at: May 1, 2026, 1:28 a.m.