Triple
T18314697
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Refaluwasch |
E438724
|
entity |
| Predicate | usesTraditionalVesselType |
P11945
|
FINISHED |
| Object | outrigger canoe |
—
|
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: outrigger canoe | Statement: [Refaluwasch, usesTraditionalVesselType, outrigger canoe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesTraditionalVesselType Context triple: [Refaluwasch, usesTraditionalVesselType, outrigger canoe]
-
A.
traditionalVessel
Indicates that one entity is a vessel or container that follows traditional, customary, or historically established forms, designs, or uses in relation to another entity.
-
B.
usesVesselType
chosen
Indicates that an entity performs an activity or operation by employing a specific type or category of vessel.
-
C.
servingVessel
Indicates that one entity functions as the container or vessel used to serve another entity (such as food or drink).
-
D.
servesVessels
Indicates that one entity provides or supplies vessels (such as containers, ships, or similar items) for the use or benefit of another entity.
-
E.
possibleFermentationVessel
Indicates that something can serve as a suitable container or environment in which fermentation may take place.
- 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_69d8b916a2d081909e249e4902f6aad9 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e5021cc70c8190bf43bd75e4af7381 |
completed | April 19, 2026, 4:26 p.m. |
| PD | Predicate disambiguation | batch_69e44fe4ee10819086b4142444fca1f5 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:36 a.m.