Triple
T26596393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marovo people |
E667501
|
entity |
| Predicate | marineKnowledge |
P161589
|
FINISHED |
| Object | fish behavior |
—
|
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: fish behavior | Statement: [Marovo people, marineKnowledge, fish behavior]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marineKnowledge Context triple: [Marovo people, marineKnowledge, fish behavior]
-
A.
marineKnowledge
chosen
Indicates that an entity possesses knowledge, information, or expertise related to marine environments, organisms, or activities.
-
B.
marineResources
Indicates a relationship where one entity possesses, provides, or is associated with marine-based resources (such as fish, minerals, or other ocean-derived materials) used or managed by another entity.
-
C.
marineComponent
Indicates a relationship where something is a part, subsystem, or element of a marine or sea-related system, structure, or environment.
-
D.
marine
Indicates that an entity is related to, associated with, or located in the sea or ocean environment.
-
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.
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_69ee9cfc385081909ac9ae178030a06e |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f621fcea1481909b6f8b3af1ee6820 |
completed | May 2, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69f620debeb48190b7db395fb86cf8d9 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 2:10 a.m.