Triple
T15916868
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mansfield Lovell |
E385991
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Lovell |
E320588
|
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: Lovell | Statement: [Mansfield Lovell, familyName, Lovell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lovell Context triple: [Mansfield Lovell, familyName, Lovell]
-
A.
Lovell
chosen
Lovell is an English surname most prominently associated with Sir Bernard Lovell, a pioneering radio astronomer and founder of the Jodrell Bank Observatory.
-
B.
Marford
Marford is a village in Wrexham County Borough, Wales, known for its distinctive Gothic-style architecture and historic character.
-
C.
Southworth
Southworth is a surname most notably associated with Lucinda Southworth, an American researcher and the wife of Google co-founder Larry Page.
-
D.
Kelling
Kelling is a small coastal village in Norfolk, England, known for its scenic heathland, wildlife, and proximity to the North Sea.
-
E.
Holwood
Holwood is a historic country estate in Kent, England, best known as the former residence of British Prime Minister William Pitt the Younger.
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1567ef7f881908862eaf5bf2e98fd |
completed | April 16, 2026, 9:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb05b15e8819083b67afa52f46283 |
completed | May 9, 2026, 10:08 p.m. |
Created at: April 10, 2026, 4:52 a.m.