Triple
T24443898
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duffield Castle |
E616345
|
entity |
| Predicate | wasOneOfLargest |
P30645
|
FINISHED |
| Object | stone castles in Derbyshire |
—
|
LITERAL 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: stone castles in Derbyshire | Statement: [Duffield Castle, wasOneOfLargest, stone castles in Derbyshire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasOneOfLargest Context triple: [Duffield Castle, wasOneOfLargest, stone castles in Derbyshire]
-
A.
madeStateOneOfLargestIn
Indicates that an entity caused a state to become one of the largest within a specified group, category, or region.
-
B.
oneOfLargest
chosen
Indicates that the subject is among the largest members within a specified group or set, but not necessarily the single largest.
-
C.
wasLargestOfItsType
Indicates that an entity held the greatest size, extent, or magnitude among all entities of the same type or category during a given time period.
-
D.
wouldHaveBeenLargest
Indicates that something would have been the largest among a set of entities or options under certain hypothetical or unrealized conditions.
-
E.
isOneOfLargestTownsIn
Indicates that a town is among the largest towns within a specified region or area.
- F. None of above.
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_69e2d7edca608190aafefc8877a1b4da |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f29851e6cc8190a8f160cbed4e9ab0 |
completed | April 29, 2026, 11:46 p.m. |
| PD | Predicate disambiguation | batch_69f287d3237c819099559c00f83131d8 |
completed | April 29, 2026, 10:36 p.m. |
Created at: April 18, 2026, 2:17 a.m.