Triple
T5850040
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kosi Bay |
E130004
|
entity |
| Predicate | hasMarineComponent |
P48518
|
FINISHED |
| Object | Kosi Bay mouth |
—
|
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: Kosi Bay mouth | Statement: [Kosi Bay, hasMarineComponent, Kosi Bay mouth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMarineComponent Context triple: [Kosi Bay, hasMarineComponent, Kosi Bay mouth]
-
A.
hasNavalComponent
Indicates that something includes, involves, or is associated with a naval or maritime element as part of its composition or structure.
-
B.
hasMarineSpecies
Indicates that an entity contains, supports, or is associated with one or more marine species.
-
C.
isMarine
Indicates that an entity lives in, is adapted to, or is primarily associated with the marine (ocean or sea) environment.
-
D.
hasSeaArmType
chosen
Indicates that an entity is associated with or characterized by a specific type of sea arm (such as a bay, gulf, fjord, or similar marine inlet).
-
E.
hasAmphibiousCapability
Indicates that an entity possesses the ability to operate effectively in both water and land environments.
- 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_69c0084de39081909eb34e6bed74215a |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c044ab0a048190b84be40fb13c0f50 |
completed | March 22, 2026, 7:36 p.m. |
| PD | Predicate disambiguation | batch_69c03345ca0c819081c81148d054fed2 |
completed | March 22, 2026, 6:21 p.m. |
Created at: March 22, 2026, 3:55 p.m.