Triple
T4045424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lent |
E84053
|
entity |
| Predicate | locatedAcross |
P382
|
FINISHED |
| Object | River Waal from Nijmegen |
E328453
|
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: River Waal from Nijmegen | Statement: [Lent, locatedAcross, River Waal from Nijmegen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: River Waal from Nijmegen Context triple: [Lent, locatedAcross, River Waal from Nijmegen]
-
A.
River Waal
chosen
River Waal is a major distributary branch of the Rhine in the Netherlands, serving as an important waterway for transport and trade.
-
B.
river Vecht
The river Vecht is a Dutch waterway in the province of Utrecht, known for its scenic, historic towns and country estates along its banks.
-
C.
Beneden Merwede
Beneden Merwede is a major distributary branch of the Rhine–Meuse river system in the western Netherlands, important for inland shipping and regional water management.
-
D.
Amstel River
The Amstel River is a historic waterway in the Netherlands that flows through and gives its name to the city of Amsterdam.
-
E.
Gelderse IJssel
Gelderse IJssel is the Dutch name for the branch of the River IJssel that flows through the province of Gelderland in the 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_69aed930bd5c819083e7dcc14fc44f69 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefb5f85d48190ba80a0a24fbe438a |
completed | March 9, 2026, 4:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b55652228c8190a9f301676deb0055 |
completed | March 14, 2026, 12:36 p.m. |
Created at: March 9, 2026, 3:37 p.m.