Triple
T10922574
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swahili people |
E257982
|
entity |
| Predicate | maritimeTechnology |
P24305
|
FINISHED |
| Object | dhow |
—
|
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: dhow | Statement: [Swahili people, maritimeTechnology, dhow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maritimeTechnology Context triple: [Swahili people, maritimeTechnology, dhow]
-
A.
maritimeDomain
Indicates a relationship or activity that occurs within, affects, or is specifically associated with the maritime domain (seas, oceans, and related maritime operations).
-
B.
sailingTechnology
chosen
Indicates the use or involvement of specific methods, tools, or innovations related to the practice or process of sailing.
-
C.
marineComponent
Indicates a relationship where something is a part, subsystem, or element of a marine or sea-related system, structure, or environment.
-
D.
maritimeFunction
Indicates a relationship where an entity serves a role, purpose, or operational function specifically within maritime contexts such as sea transport, navigation, or marine activities.
-
E.
navalArchitecture
Indicates the design, engineering, and construction-related relationship between entities involved in ships or other marine vessels.
- 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_69d6aa864ed88190818280ab6791d065 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7708d1fb88190bb33b72d4330ce11 |
completed | April 9, 2026, 9:25 a.m. |
| PD | Predicate disambiguation | batch_69d72e799f808190b6ab64fc7586a303 |
completed | April 9, 2026, 4:43 a.m. |
Created at: April 8, 2026, 9:22 p.m.