Triple
T26727443
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arab-Swahili traders |
E673870
|
entity |
| Predicate | usedNavigation |
P11421
|
FINISHED |
| Object | monsoon wind system |
—
|
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: monsoon wind system | Statement: [Arab-Swahili traders, usedNavigation, monsoon wind system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedNavigation Context triple: [Arab-Swahili traders, usedNavigation, monsoon wind system]
-
A.
usedToNavigate
chosen
Indicates that one entity served as a means or tool for another entity to find or follow a route or direction.
-
B.
hasNavigationUse
Indicates that something is used for navigation or serves a navigational function in relation to another entity.
-
C.
navigatesUsing
Indicates that one entity moves or travels through an environment by relying on another entity as its means, tool, or method of navigation.
-
D.
navigatedIn
Indicates that an entity moved or steered through or within a particular medium, environment, or space.
-
E.
hasNavigationPurpose
Indicates that something exists or is designed specifically to serve a navigational function or goal.
- 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_69eecda481d08190aea69f2f7c745f56 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f6180c6ba081908b82e0a76fdb94e8 |
completed | May 2, 2026, 3:28 p.m. |
| PD | Predicate disambiguation | batch_69f60b8dfa0c8190864e1a940024d0a0 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 27, 2026, 3:43 a.m.