Triple
T10124772
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Het Behouden Huys |
E226181
|
entity |
| Predicate | crewDepartedFrom |
P46825
|
FINISHED |
| Object | the hut in open boats in 1597 |
—
|
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: the hut in open boats in 1597 | Statement: [Het Behouden Huys, crewDepartedFrom, the hut in open boats in 1597]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crewDepartedFrom Context triple: [Het Behouden Huys, crewDepartedFrom, the hut in open boats in 1597]
-
A.
crewOnReturn
Indicates that a crew member is assigned to be on board a specific vehicle, mission, or vessel for its return journey.
-
B.
crewLandingStatus
Indicates the status or outcome of a crew’s landing event, such as whether and how the crew has successfully landed.
-
C.
hasEmbarkedPersonnel
Indicates that one entity has taken personnel on board or loaded them for transport or deployment.
-
D.
crewTransportSegment
Indicates a segment of a journey during which crew members are transported from one location to another.
-
E.
departsFrom
chosen
Indicates that an entity (such as a vehicle, person, or process) begins its movement, journey, or operation starting from a specified location or point of origin.
- 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_69ca843057b48190a86730167f5d6b98 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cdd2ebe4548190a484c145639d92f0 |
completed | April 2, 2026, 2:22 a.m. |
| PD | Predicate disambiguation | batch_69cd4ba1d360819087698d04a53cc87e |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:05 p.m.