Triple
T33086861
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kington, Herefordshire, England |
E846663
|
entity |
| Predicate | hasHillNearby |
P140464
|
FINISHED |
| Object | Hergest Ridge |
—
|
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: Hergest Ridge | Statement: [Kington, Herefordshire, England, hasHillNearby, Hergest Ridge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHillNearby Context triple: [Kington, Herefordshire, England, hasHillNearby, Hergest Ridge]
-
A.
hasNearbyHills
chosen
Indicates that one location or area is situated close to one or more hills.
-
B.
hasNearbyHillRange
Indicates that one entity is located close to or within the vicinity of a range of hills associated with the other entity.
-
C.
containsHill
Indicates that one entity geographically includes or encompasses a hill within its area or boundaries.
-
D.
hasHillHeight
Indicates that an entity (such as a hill or location) possesses a specific height value.
-
E.
isHill
Indicates that the subject entity is classified as a hill, i.e., a naturally raised area of land lower and less steep than a mountain.
- 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_69f34954d46c8190a04a159cc5f99efd |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69feb342994081909481ec8ec5d44928 |
completed | May 9, 2026, 4:08 a.m. |
| PD | Predicate disambiguation | batch_69feb046e4e48190b96649aa28529cc9 |
completed | May 9, 2026, 3:55 a.m. |
Created at: May 1, 2026, 1:26 a.m.