Triple
T22329691
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thor Heyerdahl |
E551989
|
entity |
| Predicate | Kon-TikiVesselType |
P24983
|
FINISHED |
| Object | balsa wood raft |
—
|
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: balsa wood raft | Statement: [Thor Heyerdahl, Kon-TikiVesselType, balsa wood raft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Kon-TikiVesselType Context triple: [Thor Heyerdahl, Kon-TikiVesselType, balsa wood raft]
-
A.
vesselTypeServedOn
Indicates the type of vessel on which an entity has served or performed duty.
-
B.
namedVesselOf
Indicates that one entity is the specific named vessel (e.g., ship, boat, or craft) associated with or belonging to another entity.
-
C.
hullType
Indicates the specific structural design or configuration of an object's hull, typically classifying how its outer body or shell is shaped or constructed.
-
D.
shipwreckType
Indicates the specific kind or classification of a shipwreck associated with an entity.
-
E.
craftType
chosen
Indicates the specific kind or category of craft or vessel associated with an entity.
- 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_69e11e482f788190b78d1588fc26d606 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1576ab52c819087563cd778d6bc5e |
completed | April 29, 2026, 12:57 a.m. |
| PD | Predicate disambiguation | batch_69e73004d9e88190bb862319a5aea06b |
completed | April 21, 2026, 8:06 a.m. |
Created at: April 16, 2026, 8:43 p.m.