Triple
T8688698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris Expo Porte de Versailles |
E206230
|
entity |
| Predicate | operator |
P179
|
FINISHED |
| Object | Viparis |
E752231
|
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: Viparis | Statement: [Paris Expo Porte de Versailles, operator, Viparis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Viparis Context triple: [Paris Expo Porte de Versailles, operator, Viparis]
-
A.
Viparis
chosen
Viparis is a major French company that manages and operates leading convention and exhibition centers in the Paris region.
-
B.
Livadeia
Livadeia is a town in central Greece, near Mount Parnassus, known historically for the ancient oracle of Trophonius and today as the capital of the regional unit of Boeotia.
-
C.
Juvisiens
Juvisiens are the inhabitants of the French commune of Juvisy-sur-Orge, located in the southern suburbs of Paris.
-
D.
Agenais
Agenais refers to the inhabitants or natives of Agen, a historic town in southwestern France.
-
E.
Vianen
Vianen is a historic Dutch town known for its medieval city center and location near major rivers in the western Netherlands.
- 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_69ca835481fc819084e33d3bc883bfa6 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc57334b0c8190903a5a1784e74791 |
completed | March 31, 2026, 11:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf288acb348190829e149a9089a0a1 |
completed | April 3, 2026, 2:40 a.m. |
Created at: March 30, 2026, 6:33 p.m.