Triple
T172361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Halve Maen |
E3502
|
entity |
| Predicate | sailingRoute |
P7985
|
FINISHED |
| Object | from the Dutch Republic to the North Atlantic |
—
|
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: from the Dutch Republic to the North Atlantic | Statement: [Halve Maen, sailingRoute, from the Dutch Republic to the North Atlantic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sailingRoute Context triple: [Halve Maen, sailingRoute, from the Dutch Republic to the North Atlantic]
-
A.
followsCoast
Indicates that one entity’s path or boundary runs alongside and generally conforms to the shape of a coastline.
-
B.
shipUsed
Indicates that a particular ship was employed or utilized in carrying out an event, activity, or operation.
-
C.
followsRouteOf
Indicates that one entity travels along the same path or route that another entity takes or has taken.
-
D.
climbingRoute
Indicates a relationship where a path or sequence of holds is designated for ascending a surface, typically in rock climbing or similar activities.
-
E.
setAdriftWith
Indicates that one entity causes another to be left floating or drifting without control or guidance, typically in a body of water or space.
- F. None of above. chosen
Provenance (4 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_69a25374990081909766d30c79a18e0e |
completed | Feb. 28, 2026, 2:31 a.m. |
| NER | Named-entity recognition | batch_69a25a3f9d188190aacf5791273e2c65 |
completed | Feb. 28, 2026, 3 a.m. |
| PD | Predicate disambiguation | batch_69a25667717c8190bac5108366e2178d |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a25a3ee6d08190a451ddba7504ce9b |
completed | Feb. 28, 2026, 3 a.m. |
Created at: Feb. 28, 2026, 2:39 a.m.