Triple
T726063
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orlyval |
E14727
|
entity |
| Predicate | cityServed |
P82
|
FINISHED |
| Object | Paray-Vieille-Poste |
E15057
|
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: Paray-Vieille-Poste | Statement: [Orlyval, cityServed, Paray-Vieille-Poste]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paray-Vieille-Poste Context triple: [Orlyval, cityServed, Paray-Vieille-Poste]
-
A.
Paray-Vieille-Poste
chosen
Paray-Vieille-Poste is a commune in the southern suburbs of Paris, France, known for encompassing much of Orly Airport.
-
B.
Chêne-Bourg
Chêne-Bourg is a municipality in western Switzerland located in the canton of Geneva, forming part of the Geneva metropolitan area near the French border.
-
C.
Vallauris
Vallauris is a town in the French Riviera renowned for its pottery tradition and its association with Pablo Picasso, who lived and worked there for several years.
-
D.
Boncourt
Boncourt is a locality known for its historic Château de Boncourt, reflecting its cultural and architectural heritage.
-
E.
Santenay
Santenay is a wine-producing village in Burgundy, France, known for its predominantly red wines made from Pinot Noir and its location at the southern end of the Côte de Beaune.
- 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_69a4934c753c81909b309027e48b9b3a |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a5a7fb7c819096db848fe2ba246a |
completed | March 1, 2026, 8:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a6375c16488190a8509e1e2b5c6a7d |
completed | March 3, 2026, 1:20 a.m. |
Created at: March 1, 2026, 7:37 p.m.