Triple
T33068630
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sapperton summit level |
E846170
|
entity |
| Predicate | highestSectionOf |
P43775
|
FINISHED |
| Object | Thames and Severn Canal |
—
|
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: Thames and Severn Canal | Statement: [Sapperton summit level, highestSectionOf, Thames and Severn Canal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: highestSectionOf Context triple: [Sapperton summit level, highestSectionOf, Thames and Severn Canal]
-
A.
highestSectionsLocatedIn
Indicates that the highest parts or sections of an entity are situated within a specified location or area.
-
B.
highestPart
chosen
Indicates that one entity is the topmost or uppermost portion of another entity.
-
C.
outermostSectionOf
Indicates that one entity is the furthest external or boundary-forming section that contains or encloses another entity within a layered or nested structure.
-
D.
highestElement
Indicates that one element in a set or collection has a value greater than or equal to all other elements according to a specified ordering.
-
E.
hasHighest
Indicates that one entity possesses the greatest value, rank, or level in a specified attribute or set compared to all others.
- 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_69f3495405b88190967af2157b43b896 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fce7671f108190bf3ebf54339068b5 |
completed | May 7, 2026, 7:26 p.m. |
| PD | Predicate disambiguation | batch_69fce5b5a84c81908ac1b5b9f08d48d0 |
completed | May 7, 2026, 7:19 p.m. |
Created at: May 1, 2026, 1:25 a.m.