Triple
T17629649
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Drac |
E429940
|
entity |
| Predicate | hasTributary |
P415
|
FINISHED |
| Object | Romanche |
—
|
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: Romanche | Statement: [Drac, hasTributary, Romanche]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Romanche Context triple: [Drac, hasTributary, Romanche]
-
A.
Romanche
chosen
Romanche is a river in southeastern France that flows through the French Alps before joining the Drac near Grenoble.
-
B.
Lesches
Lesches is a small French commune located in the Seine-et-Marne department in the Île-de-France region, near Paris.
-
C.
Rocoux
Rocoux is a district of the city of Liège in eastern Belgium, known historically as the site of the 1746 Battle of Rocoux during the War of the Austrian Succession.
-
D.
Roure
Roure is a small mountain commune in southeastern France, located in the Alpes-Maritimes department within the Provence-Alpes-Côte d’Azur region.
-
E.
Cesariny
Cesariny is the surname of Mário Cesariny de Vasconcelos Tavares, a prominent Portuguese surrealist poet and painter.
- 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_69d889e37f308190a6aa0a69daff86c7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46dbf59dc8190a56aa4a2449b2e2e |
completed | April 19, 2026, 5:53 a.m. |
Created at: April 10, 2026, 5:52 a.m.