Triple
T9664677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Beach, Aberystwyth |
E233672
|
entity |
| Predicate | hasShoreComposition |
P85723
|
FINISHED |
| Object | sand and shingle |
—
|
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: sand and shingle | Statement: [South Beach, Aberystwyth, hasShoreComposition, sand and shingle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasShoreComposition Context triple: [South Beach, Aberystwyth, hasShoreComposition, sand and shingle]
-
A.
hasShoreOn
Indicates that one geographic entity borders or is directly adjacent to the shore of another body of water.
-
B.
hasShoreFeature
Indicates that a shore or coastline possesses a specific physical or environmental feature.
-
C.
hasShoreLengthOn
Indicates that an entity has a specified length of shoreline along or bordering another geographic feature (such as a body of water or coast).
-
D.
hasShorelineUse
Indicates that a geographic area or property is used for a particular type of activity or purpose along its shoreline.
-
E.
shoreHas
chosen
Indicates that a shore possesses, contains, or is characterized by a particular feature, object, or attribute.
- 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_69ca848d3b6c8190ae98ea554dea58df |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9c0e1ef481909c50a4ba5fd94583 |
completed | April 1, 2026, 10:28 p.m. |
| PD | Predicate disambiguation | batch_69ccd5b3239c8190b3ae3b9bd121e4bd |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:14 p.m.