Triple
T12837834
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wigtown Bay |
E306964
|
entity |
| Predicate | hasRiverMouth |
P4359
|
FINISHED |
| Object | River Fleet |
E431045
|
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 Fleet | Statement: [Wigtown Bay, hasRiverMouth, River Fleet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: River Fleet Context triple: [Wigtown Bay, hasRiverMouth, River Fleet]
-
A.
River Fleet
chosen
The River Fleet is one of London's historic subterranean rivers, now largely culverted and flowing unseen beneath the city into the River Thames.
-
B.
River Arrow
The River Arrow is a small river in the Welsh Marches of the United Kingdom, flowing through Herefordshire and Powys and joining the River Lugg.
-
C.
River Rat
The River Rat is a small river in Suffolk, England, that flows through villages such as Rattlesden before joining the River Gipping.
-
D.
River Aire
The River Aire is a major river in Yorkshire, England, flowing through industrial and urban centers such as Leeds and contributing significantly to the region’s navigation and waterways network.
-
E.
Riverbed
Riverbed is a large-scale immersive installation by artist Olafur Eliasson that transforms a gallery space into a rocky, river-like landscape, inviting viewers to experience a constructed natural environment indoors.
- 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_69d7bdf52b94819096d6f0ba4ab50a98 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96ff015f4819090070a01f3938acc |
completed | April 10, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f68edd30e881909062e8f91f614990 |
completed | May 2, 2026, 11:55 p.m. |
Created at: April 9, 2026, 5:35 p.m.