Triple
T17581895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cherbourg Harbour |
E428223
|
entity |
| Predicate | hasBreakwaterType |
P34503
|
FINISHED |
| Object | artificial breakwater |
—
|
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: artificial breakwater | Statement: [Cherbourg Harbour, hasBreakwaterType, artificial breakwater]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBreakwaterType Context triple: [Cherbourg Harbour, hasBreakwaterType, artificial breakwater]
-
A.
hasBreakwater
chosen
Indicates that a structure or location is equipped with or associated with a breakwater that provides protection from waves or erosion.
-
B.
hasWaterfrontType
Indicates that an entity is associated with a specific type or category of waterfront (e.g., oceanfront, lakefront, riverfront).
-
C.
isWaterfrontBuilding
Indicates that a building is located directly adjacent to a body of water, such as a river, lake, or ocean.
-
D.
hasSubmersibleBridge
Indicates that one entity possesses or includes a bridge structure designed to be lowered or submerged, typically to allow passage over or through water.
-
E.
hasSurfBreak
Indicates a relationship where a location or area contains or is associated with a specific surf break suitable for surfing.
- 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_69d889e1030481909950e140c63255b9 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e463ce8eb081909257be47d150aa04 |
completed | April 19, 2026, 5:10 a.m. |
| PD | Predicate disambiguation | batch_69e3b4fff0348190b899a32da537eaca |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:50 a.m.