Triple
T18335709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wellness Olympia |
E439264
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | Figure Olympia |
—
|
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: Figure Olympia | Statement: [Wellness Olympia, relatedTo, Figure Olympia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Figure Olympia Context triple: [Wellness Olympia, relatedTo, Figure Olympia]
-
A.
Figure Olympia
chosen
Figure Olympia is a prestigious professional women’s bodybuilding and physique competition held as part of Joe Weider’s Olympia Fitness & Performance Weekend.
-
B.
Metroon of Olympia
The Metroon of Olympia is an ancient Greek temple at the sanctuary of Olympia dedicated to the mother goddess Rhea or Cybele, notable for its religious significance and role in the ceremonial life of the site.
-
C.
Olympiada
Olympiada is a coastal village in northern Greece known for its proximity to the ancient city of Stagira, birthplace of the philosopher Aristotle.
-
D.
Olimp
Olimp is a seaside resort town on Romania’s Black Sea coast, known for its beaches and holiday accommodations.
-
E.
Colossos
Colossos is a massive wooden roller coaster in Germany renowned for its height, speed, and airtime-filled layout.
- 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_69d8b9175fec8190af865699b4e64d8c |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50ecd759481909703ed2d0d68199f |
completed | April 19, 2026, 5:20 p.m. |
Created at: April 10, 2026, 10:37 a.m.