Triple
T4260113
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hever Castle |
E96083
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Kent |
E5977
|
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: Kent | Statement: [Hever Castle, locatedIn, Kent]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kent Context triple: [Hever Castle, locatedIn, Kent]
-
A.
Kent
Kent is a suburban city in King County, Washington, known as a residential and industrial hub within the greater Seattle metropolitan area.
-
B.
Kent
chosen
Kent is a county in southeastern England known for its historic towns, coastal landscapes, and nickname "the Garden of England."
-
C.
Kent
Kent is a brand of filtered cigarettes historically marketed as a "safer" smoking option and produced by the Lorillard Tobacco Company.
-
D.
Kent, England
Kent, England is a historic county in southeastern England known for its coastal towns, rich agricultural land, and nickname "the Garden of England."
-
E.
KentON
KentON is a character created by the Devs, likely serving as a fictional persona or avatar within their projects or community.
- 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_69b3454095ac81909c2494f7ff294af1 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34f7fe7348190baed8d214268b756 |
completed | March 12, 2026, 11:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5b78825508190b2b6ca46c8e1b27c |
completed | March 14, 2026, 7:31 p.m. |
Created at: March 12, 2026, 11:06 p.m.