Triple
T30503196
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adventure Galley |
E776193
|
entity |
| Predicate | legalStatusDuringVoyages |
P196213
|
FINISHED |
| Object | commissioned privateer under English letters of marque |
—
|
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: commissioned privateer under English letters of marque | Statement: [Adventure Galley, legalStatusDuringVoyages, commissioned privateer under English letters of marque]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legalStatusDuringVoyages Context triple: [Adventure Galley, legalStatusDuringVoyages, commissioned privateer under English letters of marque]
-
A.
legalStatusAtTimeOfSinking
Indicates the legal status or condition that applied to an entity at the specific time it sank.
-
B.
seaVoyages
Indicates that one entity undertakes or is associated with journeys or travel by sea to or involving another entity.
-
C.
laterOutcomeOfVoyage
Indicates that one event, state, or outcome occurs as a subsequent result or later phase of a specified voyage.
-
D.
purposeOfVoyages
Indicates the intended goals, reasons, or objectives motivating or justifying specific voyages.
-
E.
workStatus_OnTheCatalogueOfShips
Indicates that a work’s status is determined by whether it appears in the Catalogue of Ships section of the text.
- 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_69f22498c5d481908aaea89e6fab8280 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fe163a41a0819098403b470e327d29 |
completed | May 8, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69fe1358db5c819092570814a37ef5bd |
completed | May 8, 2026, 4:46 p.m. |
| PDg | Predicate description generation | batch_69fe1639613c8190aaf1b4c8e2d861ba |
completed | May 8, 2026, 4:58 p.m. |
Created at: April 29, 2026, 8:15 p.m.