Triple
T23469410
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | hill of Bourlémont |
E569185
|
entity |
| Predicate | hasViewOf |
P854
|
FINISHED |
| Object | Ronchamp |
—
|
NE NERFINISHED |
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: Ronchamp | Statement: [hill of Bourlémont, hasViewOf, Ronchamp]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ronchamp Context triple: [hill of Bourlémont, hasViewOf, Ronchamp]
-
A.
Ronchamp
chosen
Ronchamp is a commune in eastern France best known for Le Corbusier’s modernist pilgrimage chapel, Notre-Dame du Haut.
-
B.
Maison de la Paix
Maison de la Paix is a modern academic and conference complex in Geneva that serves as the main campus of institutions focused on international relations, development, and global governance.
-
C.
Trianon Tower
Trianon Tower is a prominent postmodern skyscraper in Frankfurt, Germany, known for its distinctive triangular footprint and rooftop pyramid.
-
D.
Couffé
Couffé is a small commune in western France’s Loire-Atlantique department, known as the birthplace of the royalist military leader François de Charette.
-
E.
Maison Jeanneret
Maison Jeanneret is a modernist residential house in France designed by the renowned architect Le Corbusier.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2458ebd808190b3298163132cfb0b |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a6feb5688190ad4ce42fc9590adb |
completed | April 29, 2026, 6:36 a.m. |
Created at: April 17, 2026, 5:54 p.m.