Triple
T19557114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Neos Panteleimonas |
E489343
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | Olympus Riviera |
—
|
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: Olympus Riviera | Statement: [Neos Panteleimonas, partOf, Olympus Riviera]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Olympus Riviera Context triple: [Neos Panteleimonas, partOf, Olympus Riviera]
-
A.
Olympus Riviera
chosen
Olympus Riviera is a coastal tourist region in northern Greece known for its beaches along the Aegean Sea and its proximity to Mount Olympus.
-
B.
Olympus
Olympus is a Japanese manufacturer best known for its optical and imaging products, including cameras, lenses, and medical endoscopes.
-
C.
Olympus
Olympus is the highest and most famous mountain in Greece, revered in Greek mythology as the home of the Olympian gods.
-
D.
Olympus 104
Olympus 104 is a specific variant of the Rolls-Royce Olympus turbojet engine, developed for improved performance in military and aviation applications.
-
E.
Olympus 593
The Olympus 593 is a turbojet engine developed jointly by Rolls-Royce and Snecma, best known for powering the supersonic Concorde airliner.
- 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_69d8e8dc5d8c8190a6d7bd8864f43ca0 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63d34d1bc81908e5e10f069655866 |
completed | April 20, 2026, 2:50 p.m. |
Created at: April 10, 2026, 1:42 p.m.