Triple
T18964628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nantes metropolitan area |
E464001
|
entity |
| Predicate | traversedByRiver |
P165
|
FINISHED |
| Object | Erdre |
—
|
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: Erdre | Statement: [Nantes metropolitan area, traversedByRiver, Erdre]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Erdre Context triple: [Nantes metropolitan area, traversedByRiver, Erdre]
-
A.
Drau
Drau is the German name for the Drava, a major river in Central and Southeastern Europe that flows through countries including Italy, Austria, Slovenia, and Croatia.
-
B.
Erdre basin
chosen
The Erdre basin is a river basin in western France associated with the Erdre River, a tributary of the Loire, encompassing parts of the Nantes metropolitan area.
-
C.
Bregava
Bregava is a river in Bosnia and Herzegovina known for flowing through the town of Stolac before joining the Neretva River.
-
D.
Erna
Erna is the given name of Erna Schneider Hoover, an American mathematician and pioneering computer scientist known for revolutionizing telephone switching systems.
-
E.
Eri
Eri is a given name shared by various individuals, including the Israeli politician and Revisionist Zionist leader Eri Jabotinsky.
- 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_69d8dcffc278819086792a4ebfddfafa |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d5d5365881909dcbb4988d273b24 |
completed | April 20, 2026, 7:29 a.m. |
Created at: April 10, 2026, noon