Triple
T12623431
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orwell Estuary |
E301447
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Harwich Haven |
E143824
|
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: Harwich Haven | Statement: [Orwell Estuary, near, Harwich Haven]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harwich Haven Context triple: [Orwell Estuary, near, Harwich Haven]
-
A.
Harwich
chosen
Harwich is a historic port town in Essex, England, which once served as a parliamentary borough represented in the British House of Commons.
-
B.
Harwich
Harwich is a coastal town on southeastern Cape Cod in Massachusetts known for its beaches, harbors, and summer tourism.
-
C.
Newhaven
Newhaven is a historic coastal district of Edinburgh, Scotland, known for its former fishing village, harbor, and maritime heritage.
-
D.
Newhaven
Newhaven is a small coastal town on Phillip Island in Victoria, Australia, known as a gateway to the island and its popular tourist attractions.
-
E.
Felixstowe
Felixstowe is a coastal town in Suffolk, England, best known for its major container port—one of the busiest in Europe—and its seaside resort.
- 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_69d7bdeaf49c8190b13800111fa77ea3 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d960c8671881909a102d28b0e7f603 |
completed | April 10, 2026, 8:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f78ac916748190821c0cdabe54fcbc |
completed | May 3, 2026, 5:50 p.m. |
Created at: April 9, 2026, 5:14 p.m.