Triple
T9335708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sablon district |
E224636
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Mont des Arts |
E223208
|
NE FINISHED |
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: Mont des Arts | Statement: [Sablon district, near, Mont des Arts]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mont des Arts Context triple: [Sablon district, near, Mont des Arts]
-
A.
Mont des Arts
chosen
Mont des Arts is a historic urban complex and elevated garden in central Brussels, Belgium, known for its panoramic views, cultural institutions, and landmark architecture.
-
B.
Place des Arts
Place des Arts is a major performing arts complex in downtown Montreal known for hosting concerts, theater, dance, and large cultural festivals.
-
C.
Chaillot
Chaillot is a historic district in Paris, France, known for its 19th-century urban development and later incorporation into the city’s 16th arrondissement.
-
D.
Notre-Dame du Raincy
Notre-Dame du Raincy is a pioneering early 20th-century reinforced-concrete church near Paris, celebrated as a landmark of modernist religious architecture.
-
E.
Parc Meissonier
Parc Meissonier is a public park in Poissy, France, known for its landscaped green spaces, walking paths, and recreational areas along the Seine.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca84286fcc81909f6e7fd7a7e862a2 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd37f031888190a90d263d225d163c |
completed | April 1, 2026, 3:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0f3b37b408190957c371233d8a3bd |
completed | April 4, 2026, 11:19 a.m. |
Created at: March 30, 2026, 7:40 p.m.