Triple
T312027
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arabian Peninsula |
E7627
|
entity |
| Predicate | seaSeparatedFrom |
P11835
|
FINISHED |
| Object | Africa by Red 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: Africa by Red Sea | Statement: [Arabian Peninsula, seaSeparatedFrom, Africa by Red Sea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seaSeparatedFrom Context triple: [Arabian Peninsula, seaSeparatedFrom, Africa by Red Sea]
-
A.
hasCoastlineOn
Indicates that one entity’s coastline borders or is directly adjacent to a specified body of water.
-
B.
neighboringCountryBySea
Indicates that one country is adjacent to another with their territories touching via a shared sea boundary rather than solely by land.
-
C.
hasNotableSea
Indicates that an entity is associated with or contains a sea that is considered notable or significant.
-
D.
hasCoastline
Indicates that a geographic entity is bordered by and directly touches a sea or ocean along part of its boundary.
-
E.
separatedFromCubaBy
Indicates that one entity is divided or kept apart from Cuba by a specified physical or conceptual boundary.
- F. None of above. chosen
Provenance (4 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_69a2e7e7af7881908890039d6be4e9b8 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ea4aa16881909b2c8404b85992df |
completed | Feb. 28, 2026, 1:14 p.m. |
| PD | Predicate disambiguation | batch_69a2e940b9e8819092b821ff17ed026b |
completed | Feb. 28, 2026, 1:10 p.m. |
| PDg | Predicate description generation | batch_69a2ea08878c8190a5e8a90f620a3888 |
completed | Feb. 28, 2026, 1:13 p.m. |
Created at: Feb. 28, 2026, 1:07 p.m.