Triple
T22329695
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thor Heyerdahl |
E551989
|
entity |
| Predicate | TigrisVesselType |
P8971
|
FINISHED |
| Object | reed boat |
—
|
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: reed boat | Statement: [Thor Heyerdahl, TigrisVesselType, reed boat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: TigrisVesselType Context triple: [Thor Heyerdahl, TigrisVesselType, reed boat]
-
A.
shipTypeInvolved
chosen
Indicates that a particular type or class of ship is involved or participates in a specified event, situation, or relationship.
-
B.
tanker
Indicates that an entity functions as or is classified as a tanker, typically a vehicle or vessel designed to transport bulk liquids or gases.
-
C.
vesselTypeServedOn
Indicates the type of vessel on which an entity has served or performed duty.
-
D.
naveType
Indicates the architectural or structural type or style of a building’s nave in relation to that nave.
-
E.
typeOfMediumship
Indicates a relationship where one entity specifies the particular form or method of mediumship practiced or involved in relation to another 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.