Triple

T3902555

Position	Surface form	Disambiguated ID	Type / Status
Subject	Princess Margaret of Connaught	`E90528`	entity
Predicate	mother	`P120`	FINISHED
Object	Princess Louise Margaret of Prussia Princess Louise Margaret of Prussia was a German-born princess who became Duchess of Connaught and Strathearn through marriage into the British royal family and was the mother of Princess Margaret of Connaught.	`E551389`	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: Princess Louise Margaret of Prussia | Statement: [Princess Margaret of Connaught, mother, Princess Louise Margaret of Prussia]

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

Target entity: Princess Louise Margaret of Prussia
Context triple: [Princess Margaret of Connaught, mother, Princess Louise Margaret of Prussia]

A. Princess Louise of Prussia
Princess Louise of Prussia was a 19th-century Prussian royal and member of the House of Hohenzollern who became a Dutch princess through her marriage into the Dutch royal family.
B. Princess Louise of Saxe-Hildburghausen
Princess Louise of Saxe-Hildburghausen was a German duchess of the House of Saxe-Hildburghausen and the mother of Adolphe, who became Grand Duke of Luxembourg.
C. Princess Louise of Saxe-Gotha-Altenburg
Princess Louise of Saxe-Gotha-Altenburg was a German duchess of the early 19th century, best known as the first wife of Ernest I, Duke of Saxe-Coburg and Gotha, and the mother of Prince Albert, consort of Queen Victoria.
D. Princess Marie Louise of Hanover and Cumberland
Princess Marie Louise of Hanover and Cumberland was a German princess of the House of Hanover, notable as a granddaughter of King Christian IX of Denmark and a member of several interconnected European royal families.
E. Sophia Louise of Mecklenburg-Schwerin
Sophia Louise of Mecklenburg-Schwerin was a German duchess who became Queen consort in Prussia through her marriage into the Hohenzollern dynasty in the early 18th century.
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: Princess Louise Margaret of Prussia
Triple: [Princess Margaret of Connaught, mother, Princess Louise Margaret of Prussia]

Generated description

Princess Louise Margaret of Prussia was a German-born princess who became Duchess of Connaught and Strathearn through marriage into the British royal family and was the mother of Princess Margaret of Connaught.

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

Target entity: Princess Louise Margaret of Prussia
Target entity description: Princess Louise Margaret of Prussia was a German-born princess who became Duchess of Connaught and Strathearn through marriage into the British royal family and was the mother of Princess Margaret of Connaught.

A. Princess Louise of Prussia
Princess Louise of Prussia was a 19th-century Prussian royal and member of the House of Hohenzollern who became a Dutch princess through her marriage into the Dutch royal family.
B. Princess Louise of Saxe-Hildburghausen
Princess Louise of Saxe-Hildburghausen was a German duchess of the House of Saxe-Hildburghausen and the mother of Adolphe, who became Grand Duke of Luxembourg.
C. Princess Louise of Saxe-Gotha-Altenburg
Princess Louise of Saxe-Gotha-Altenburg was a German duchess of the early 19th century, best known as the first wife of Ernest I, Duke of Saxe-Coburg and Gotha, and the mother of Prince Albert, consort of Queen Victoria.
D. Princess Marie Louise of Hanover and Cumberland
Princess Marie Louise of Hanover and Cumberland was a German princess of the House of Hanover, notable as a granddaughter of King Christian IX of Denmark and a member of several interconnected European royal families.
E. Sophia Louise of Mecklenburg-Schwerin
Sophia Louise of Mecklenburg-Schwerin was a German duchess who became Queen consort in Prussia through her marriage into the Hohenzollern dynasty in the early 18th century.
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_69aed95d315881908cbf1bf4a7215fbf`	completed	March 9, 2026, 2:29 p.m.
NER	Named-entity recognition	`batch_69aeecf481648190b70b7acd9c1cf687`	completed	March 9, 2026, 3:53 p.m.
NED1	Entity disambiguation (via context triple)	`batch_69c0a127b0e48190880ee84f45bed359`	completed	March 23, 2026, 2:10 a.m.
NEDg	Description generation	`batch_69c0a1faf7d48190ad2d5f43ef37da82`	completed	March 23, 2026, 2:14 a.m.
NED2	Entity disambiguation (via description)	`batch_69c0a2e17cd88190a54f5166fe5c654a`	completed	March 23, 2026, 2:18 a.m.

Created at: March 9, 2026, 3:21 p.m.