Triple
T2715817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cuba (maritime boundary) |
E59963
|
entity |
| Predicate | definesZoneType |
P36294
|
FINISHED |
| Object | territorial sea |
—
|
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: territorial sea | Statement: [Cuba (maritime boundary), definesZoneType, territorial sea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: definesZoneType Context triple: [Cuba (maritime boundary), definesZoneType, territorial sea]
-
A.
zoneType
chosen
Indicates the classification or category of a zone that specifies its type or functional designation.
-
B.
definesRegionAs
Indicates that one entity specifies or designates another entity as a particular region or regional scope.
-
C.
zone
Indicates that an entity is located within, associated with, or assigned to a particular geographic or conceptual area or zone.
-
D.
ticketingZoneType
Indicates the type or category of ticketing zone that applies within a given area or context.
-
E.
exampleZoneName
Indicates that an entity is associated with a zone identified by a specific example or placeholder name.
- 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_69ab4ac92a088190bc74bca14038e3de |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abda94d3288190bd60bc886e2106c7 |
completed | March 7, 2026, 7:58 a.m. |
| PD | Predicate disambiguation | batch_69abd8240920819087a812d816a55edb |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:55 p.m.