Triple
T371848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Indian Ocean |
E8285
|
entity |
| Predicate | connectedToSea |
P6307
|
FINISHED |
| Object | Red Sea via Bab-el-Mandeb |
—
|
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: Red Sea via Bab-el-Mandeb | Statement: [Indian Ocean, connectedToSea, Red Sea via Bab-el-Mandeb]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectedToSea Context triple: [Indian Ocean, connectedToSea, Red Sea via Bab-el-Mandeb]
-
A.
hasNotableSea
Indicates that an entity is associated with or contains a sea that is considered notable or significant.
-
B.
hasCityOnShore
Indicates that a city is located on or directly adjacent to the shore of a body of water.
-
C.
flowsAlongCoastOf
Indicates that something, typically a body of water or current, moves in a path that follows and runs adjacent to a coastline.
-
D.
connectsBodyOfWater
chosen
Indicates a relationship where one entity serves as a link or passage between two bodies of water, allowing them to be joined or interact.
-
E.
hasCoastlineOn
Indicates that one entity’s coastline borders or is directly adjacent to a specified body of water.
- 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_69a2e7f2ec648190b42bc7db424f8109 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ec00785481908551fc3571fcca47 |
completed | Feb. 28, 2026, 1:22 p.m. |
| PD | Predicate disambiguation | batch_69a2e960d880819084b3df4e5137a1e2 |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.