Triple
T3151888
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antibes |
E65894
|
entity |
| Predicate | hasPort |
P35
|
FINISHED |
| Object | Port Vauban |
E330938
|
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: Port Vauban | Statement: [Antibes, hasPort, Port Vauban]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Port Vauban Context triple: [Antibes, hasPort, Port Vauban]
-
A.
Port Vauban
chosen
Port Vauban is a major Mediterranean marina in Antibes, France, renowned as one of Europe’s largest harbours for luxury yachts and pleasure boats.
-
B.
Vauban
Vauban was a renowned 17th-century French military engineer and Marshal of France, famous for revolutionizing fortification design and siege warfare under Louis XIV.
-
C.
Plainpalais
Plainpalais is a central district of Geneva, Switzerland, known for its large public square, markets, and cultural and historical significance.
-
D.
Cimiez
Cimiez is a historic and upscale residential district in Nice, France, known for its Roman ruins, Belle Époque architecture, and cultural institutions.
-
E.
Lacanau
Lacanau is a coastal resort town in southwestern France known for its Atlantic beaches, surfing, and large freshwater lake.
- 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_69ad8584485081909ed529e890cadc4a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada5c27258819099c46a657779780b |
completed | March 8, 2026, 4:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b235bf4a008190ba6264103a9d67b7 |
completed | March 12, 2026, 3:40 a.m. |
Created at: March 8, 2026, 3:05 p.m.