Triple

T9522871

Position	Surface form	Disambiguated ID	Type / Status
Subject	Jesuit chapel of Saint-Omer	`E229685`	entity
Predicate	locatedIn	`P40`	FINISHED
Object	historic center of Saint-Omer The historic center of Saint-Omer is the old urban core of the French town of Saint-Omer, known for its rich architectural heritage, including religious buildings like the Jesuit chapel, and its well-preserved medieval and early modern streetscapes.	`E803992`	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: historic center of Saint-Omer | Statement: [Jesuit chapel of Saint-Omer, locatedIn, historic center of Saint-Omer]

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

Target entity: historic center of Saint-Omer
Context triple: [Jesuit chapel of Saint-Omer, locatedIn, historic center of Saint-Omer]

A. Town hall of Saint-Omer
The Town Hall of Saint-Omer is a historic municipal building in the French town of Saint-Omer, noted for its architectural significance and role as the seat of local government.
B. historic center of Caen
The historic center of Caen is the medieval heart of the Norman city, known for its ancient abbeys, castle, and stone architecture largely rebuilt after World War II.
C. historic center of Dunkirk
The historic center of Dunkirk is the old urban core of the French port city, characterized by its traditional streets, historic buildings, and landmarks such as the Saint-Éloi church.
D. historic center of Calais
The historic center of Calais is the old urban core of the French port city, characterized by its traditional architecture, historic churches, and civic buildings that reflect its long maritime and border-town history.
E. Grand-Place of Béthune
The Grand-Place of Béthune is the historic central square of the northern French town of Béthune, known for its distinctive belfry, traditional Flemish-style architecture, and role as the town’s social and commercial hub.
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: historic center of Saint-Omer
Triple: [Jesuit chapel of Saint-Omer, locatedIn, historic center of Saint-Omer]

Generated description

The historic center of Saint-Omer is the old urban core of the French town of Saint-Omer, known for its rich architectural heritage, including religious buildings like the Jesuit chapel, and its well-preserved medieval and early modern streetscapes.

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

Target entity: historic center of Saint-Omer
Target entity description: The historic center of Saint-Omer is the old urban core of the French town of Saint-Omer, known for its rich architectural heritage, including religious buildings like the Jesuit chapel, and its well-preserved medieval and early modern streetscapes.

A. Town hall of Saint-Omer
The Town Hall of Saint-Omer is a historic municipal building in the French town of Saint-Omer, noted for its architectural significance and role as the seat of local government.
B. historic center of Caen
The historic center of Caen is the medieval heart of the Norman city, known for its ancient abbeys, castle, and stone architecture largely rebuilt after World War II.
C. historic center of Dunkirk
The historic center of Dunkirk is the old urban core of the French port city, characterized by its traditional streets, historic buildings, and landmarks such as the Saint-Éloi church.
D. historic center of Calais
The historic center of Calais is the old urban core of the French port city, characterized by its traditional architecture, historic churches, and civic buildings that reflect its long maritime and border-town history.
E. Grand-Place of Béthune
The Grand-Place of Béthune is the historic central square of the northern French town of Béthune, known for its distinctive belfry, traditional Flemish-style architecture, and role as the town’s social and commercial hub.
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_69ca847870a881909d8d751a7d29da39`	completed	March 30, 2026, 2:11 p.m.
NER	Named-entity recognition	`batch_69cd989788e4819086c235bf37a56b04`	completed	April 1, 2026, 10:13 p.m.
NED1	Entity disambiguation (via context triple)	`batch_69d13a61fbd08190bb68ffe29da3a34a`	completed	April 4, 2026, 4:20 p.m.
NEDg	Description generation	`batch_69d13c0344388190aefc18936b17b9f0`	completed	April 4, 2026, 4:27 p.m.
NED2	Entity disambiguation (via description)	`batch_69d13c7b2954819096a276e083d4fed1`	completed	April 4, 2026, 4:29 p.m.

Created at: March 30, 2026, 7:59 p.m.