Triple
T27483415
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kingdom of Powys |
E693662
|
entity |
| Predicate | hadBorder |
P162434
|
FINISHED |
| Object | Offa's Dyke |
—
|
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: Offa's Dyke | Statement: [Kingdom of Powys, hadBorder, Offa's Dyke]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadBorder Context triple: [Kingdom of Powys, hadBorder, Offa's Dyke]
-
A.
hadBorderType
Indicates that a boundary between two entities existed and specifies the nature or classification of that border (e.g., land, maritime, disputed).
-
B.
hasBorderThrough
Indicates that a border between two regions or entities passes through or along a specified intermediate area, feature, or object.
-
C.
hasBorderMaterial
Indicates that one entity uses or is composed of a specified material for its border or edge.
-
D.
guardedBorderWith
Indicates a relationship where a shared border between two entities is actively protected or monitored, typically for security or control purposes.
-
E.
hasBorderSignificance
Indicates that a border between entities holds particular importance, impact, or relevance in a given context.
- 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_69ef5381f2648190a2392d0fab833095 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62e494fc88190bbbaff22bab99623 |
completed | May 2, 2026, 5:03 p.m. |
| PD | Predicate disambiguation | batch_69f623aaf40081909f947431424a1d55 |
completed | May 2, 2026, 4:17 p.m. |
| PDg | Predicate description generation | batch_69f624c006788190a2f4d5015c96463f |
completed | May 2, 2026, 4:22 p.m. |
Created at: April 27, 2026, 1:01 p.m.