Triple
T12363025
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | developing the bastioned trace system known as the "pré carré" |
E294788
|
entity |
| Predicate | hasNotableExample |
P1259
|
FINISHED |
| Object |
fortifications of Valenciennes
The fortifications of Valenciennes are a major example of the 17th-century French defensive works engineered by Sébastien Le Prestre de Vauban as part of the double line of strongholds protecting France’s northern frontier.
|
E978581
|
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: fortifications of Valenciennes | Statement: [developing the bastioned trace system known as the "pré carré", hasNotableExample, fortifications of Valenciennes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: fortifications of Valenciennes Context triple: [developing the bastioned trace system known as the "pré carré", hasNotableExample, fortifications of Valenciennes]
-
A.
Fortifications of Arras
The Fortifications of Arras are a historic French defensive complex renowned as part of the network of military works engineered by the famed 17th-century military architect Vauban.
-
B.
Médiane fortifications
The Médiane fortifications are a historic defensive complex within the Citadel of Namur in Belgium, reflecting the city’s strategic military architecture and layered fortification history.
-
C.
Fort of Huy
Fort of Huy is a historic military fortress overlooking the Meuse River in the Belgian city of Huy, known for its role in regional defense and as a World War II prison camp.
-
D.
fortifications of Lille
The fortifications of Lille are a major 17th-century defensive complex in northern France, renowned as one of military engineer Vauban’s most significant and innovative stronghold designs.
-
E.
Fortifications of Auxonne
The Fortifications of Auxonne are historic military defenses in the town of Auxonne, France, notable for their well-preserved bastions and strategic role in regional border protection.
- 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: fortifications of Valenciennes Triple: [developing the bastioned trace system known as the "pré carré", hasNotableExample, fortifications of Valenciennes]
Generated description
The fortifications of Valenciennes are a major example of the 17th-century French defensive works engineered by Sébastien Le Prestre de Vauban as part of the double line of strongholds protecting France’s northern frontier.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: fortifications of Valenciennes Target entity description: The fortifications of Valenciennes are a major example of the 17th-century French defensive works engineered by Sébastien Le Prestre de Vauban as part of the double line of strongholds protecting France’s northern frontier.
-
A.
Fortifications of Arras
The Fortifications of Arras are a historic French defensive complex renowned as part of the network of military works engineered by the famed 17th-century military architect Vauban.
-
B.
Médiane fortifications
The Médiane fortifications are a historic defensive complex within the Citadel of Namur in Belgium, reflecting the city’s strategic military architecture and layered fortification history.
-
C.
Fort of Huy
Fort of Huy is a historic military fortress overlooking the Meuse River in the Belgian city of Huy, known for its role in regional defense and as a World War II prison camp.
-
D.
fortifications of Lille
The fortifications of Lille are a major 17th-century defensive complex in northern France, renowned as one of military engineer Vauban’s most significant and innovative stronghold designs.
-
E.
Fortifications of Auxonne
The Fortifications of Auxonne are historic military defenses in the town of Auxonne, France, notable for their well-preserved bastions and strategic role in regional border protection.
- 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_69d6ab6d8a4081908636601e69ddf262 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f91a1908190a8a4fa9da3b47933 |
completed | April 10, 2026, 6:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f62ab9ea4c81908313b11716ad7c43 |
completed | May 2, 2026, 4:47 p.m. |
| NEDg | Description generation | batch_69f62c569a6c8190aecf8a4c627d8893 |
completed | May 2, 2026, 4:54 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f62d13237881908b7c2dca173e20cf |
completed | May 2, 2026, 4:57 p.m. |
Created at: April 8, 2026, 9:54 p.m.