Triple
T17551996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yew Maze |
E427487
|
entity |
| Predicate | hasName |
P744
|
FINISHED |
| Object | Yew Maze |
—
|
NE NERFINISHED |
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: Yew Maze | Statement: [Yew Maze, hasName, Yew Maze]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yew Maze Context triple: [Yew Maze, hasName, Yew Maze]
-
A.
Yew Maze
chosen
Yew Maze is a historic hedge maze made of yew trees located within the grounds of Hever Castle in Kent, England.
-
B.
Snake Holme
Snake Holme is a small island located near Belle Isle in the English Lake District’s Windermere lake.
-
C.
Maze Hill
Maze Hill is a suburban railway station in southeast London serving the Greenwich area on the North Kent Line.
-
D.
Bisham Woods
Bisham Woods is an ancient woodland and nature reserve in Berkshire, England, known for its rich biodiversity, historic landscapes, and extensive network of walking trails.
-
E.
Moss Nook
Moss Nook is a locality in Greater Manchester, England, historically associated with the former Manchester (Moss Nook) Airport site and surrounding residential areas.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d889df6dc081908f67dbadc03c07ee |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e454664b348190aea3ad59954b2c91 |
completed | April 19, 2026, 4:04 a.m. |
Created at: April 10, 2026, 5:50 a.m.