Triple
T19542096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Malaita Island |
E488930
|
entity |
| Predicate | marineResources |
P136712
|
FINISHED |
| Object | reef fish |
—
|
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: reef fish | Statement: [South Malaita Island, marineResources, reef fish]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marineResources Context triple: [South Malaita Island, marineResources, reef fish]
-
A.
marineComponent
Indicates a relationship where something is a part, subsystem, or element of a marine or sea-related system, structure, or environment.
-
B.
marine
Indicates that an entity is related to, associated with, or located in the sea or ocean environment.
-
C.
marineArea
Indicates a relationship where an entity is located in, associated with, or relevant to a specific marine or oceanic area.
-
D.
maritimeInfrastructure
Indicates the existence, presence, or involvement of facilities, structures, or systems that support maritime activities such as shipping, ports, and coastal operations between the related entities.
-
E.
maritimeDomain
Indicates a relationship or activity that occurs within, affects, or is specifically associated with the maritime domain (seas, oceans, and related maritime operations).
- F. None of above. chosen
Provenance (4 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6387442588190a2cdae60a6a940d6 |
completed | April 20, 2026, 2:30 p.m. |
| PD | Predicate disambiguation | batch_69e514c9c00481909b76bda67957e58b |
completed | April 19, 2026, 5:45 p.m. |
| PDg | Predicate description generation | batch_69e51a23300c8190988552491d9783d7 |
completed | April 19, 2026, 6:08 p.m. |
Created at: April 10, 2026, 1:41 p.m.