Triple
T10904615
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brighthelmstone |
E257533
|
entity |
| Predicate | toponymyContainsElement |
P96333
|
FINISHED |
| Object | Old English "tūn" (farm or settlement) |
—
|
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: Old English "tūn" (farm or settlement) | Statement: [Brighthelmstone, toponymyContainsElement, Old English "tūn" (farm or settlement)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: toponymyContainsElement Context triple: [Brighthelmstone, toponymyContainsElement, Old English "tūn" (farm or settlement)]
-
A.
toponymContains
Indicates that one geographic place name spatially includes or encompasses another place name within its boundaries.
-
B.
hasToponymy
Indicates a relationship where one entity possesses or is associated with the system, study, or set of place names (toponyms) of another entity.
-
C.
hasTypeOfToponym
Indicates that one entity is classified as a specific type or category of toponym (place name) in relation to another entity.
-
D.
hasToponymicForm
Indicates that one entity is a toponymic (place-name-based) form or variant derived from another entity.
-
E.
isToponymic
Indicates that something is related to or derived from a place name (a toponym).
- F. None of above. chosen
Provenance (4 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_69d6aa8550c8819095508a2ed9acf3db |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d770656c288190828e71600bb0acd4 |
completed | April 9, 2026, 9:24 a.m. |
| PD | Predicate disambiguation | batch_69d70d3d69e08190bb369e9a7927142c |
completed | April 9, 2026, 2:21 a.m. |
| PDg | Predicate description generation | batch_69d7101de31c819090707635f6790559 |
completed | April 9, 2026, 2:34 a.m. |
Created at: April 8, 2026, 9:22 p.m.