Triple
T3827000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Broket Hall |
E88713
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Welwyn |
E381106
|
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: Welwyn | Statement: [Broket Hall, locatedNear, Welwyn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Welwyn Context triple: [Broket Hall, locatedNear, Welwyn]
-
A.
Welwyn
chosen
Welwyn is a historic village and civil parish in Hertfordshire, England, known for its Roman heritage and picturesque rural character.
-
B.
Welwyn Hatfield
Welwyn Hatfield is a local government district and borough in Hertfordshire, England, that includes the towns of Welwyn Garden City and Hatfield.
-
C.
Hoddesdon
Hoddesdon is a historic market town in southern England known for its traditional high street, commuter links to London, and proximity to the River Lea.
-
D.
Welwyn Garden City
Welwyn Garden City is a planned English town in Hertfordshire, founded by Ebenezer Howard in the early 20th century as a model community combining the benefits of city and countryside.
-
E.
Rickmansworth
Rickmansworth is a small town in south-west Hertfordshire, England, known for its canals, lakes, and role as a commuter suburb of London.
- 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_69aed9538cf881909d9ce8ca4ac7c18c |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeeb64c72c8190b5f3d376aa4ee933 |
completed | March 9, 2026, 3:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c07d33a65481908c7ab4473bed1320 |
completed | March 22, 2026, 11:37 p.m. |
Created at: March 9, 2026, 3:17 p.m.