Triple
T3389388
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dieppe |
E71380
|
entity |
| Predicate | mouthOf |
P1008
|
FINISHED |
| Object | Arques |
E353340
|
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: Arques | Statement: [Dieppe, mouthOf, Arques]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arques Context triple: [Dieppe, mouthOf, Arques]
-
A.
Arques
chosen
Arques is a river in northern France that flows through the Normandy region and reaches the English Channel at the port city of Dieppe.
-
B.
Montlhéry
Montlhéry is a commune in northern France best known for its historic motor racing circuit, the Autodrome de Linas-Montlhéry.
-
C.
Deauzya
Deauzya is the given first name of American professional basketball player DiDi Richards.
-
D.
Gressy
Gressy is a small French commune located in the Île-de-France region, known for its residential character and proximity to Paris and Charles de Gaulle Airport.
-
E.
Orgeval
Orgeval is a district in the city of Reims, France, known in part for serving as a terminus of the Reims tramway network.
- 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_69ad85a8fd9c819095ecedf838d2bf1b |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb666e514819090560d43bfaf55b8 |
completed | March 8, 2026, 5:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b34bc62c788190b6097e02601df386 |
completed | March 12, 2026, 11:27 p.m. |
Created at: March 8, 2026, 3:14 p.m.