Triple
T15770919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kendari Bay |
E382354
|
entity |
| Predicate | marineUse |
P7788
|
FINISHED |
| Object | inshore navigation |
—
|
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: inshore navigation | Statement: [Kendari Bay, marineUse, inshore navigation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marineUse Context triple: [Kendari Bay, marineUse, inshore navigation]
-
A.
maritimeUsage
chosen
Indicates the extent to which something is used for or involved in maritime activities, such as sea transport, navigation, or ocean-related operations.
-
B.
marineComponent
Indicates a relationship where something is a part, subsystem, or element of a marine or sea-related system, structure, or environment.
-
C.
maritimeActivity
Indicates activities, operations, or behaviors that take place at sea or are directly related to maritime environments and navigation.
-
D.
maritimeDomain
Indicates a relationship or activity that occurs within, affects, or is specifically associated with the maritime domain (seas, oceans, and related maritime operations).
-
E.
marineArea
Indicates a relationship where an entity is located in, associated with, or relevant to a specific marine or oceanic area.
- 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_69d86da09a10819082fe9797b23e4664 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e051962fe08190a6201dd48196a9ee |
completed | April 16, 2026, 3:03 a.m. |
| PD | Predicate disambiguation | batch_69e00531e7ac8190a4190cce4f7fab4c |
completed | April 15, 2026, 9:37 p.m. |
Created at: April 10, 2026, 4:47 a.m.