Triple
T20508731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pirates of Nassau |
E503501
|
entity |
| Predicate | hasTopic |
P531
|
FINISHED |
| Object | Mary Read |
—
|
NE NERFINISHED |
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: Mary Read | Statement: [Pirates of Nassau, hasTopic, Mary Read]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Read Context triple: [Pirates of Nassau, hasTopic, Mary Read]
-
A.
Mary Read
chosen
Mary Read was an early 18th-century English pirate, famed for disguising herself as a man and sailing alongside Anne Bonny during the Golden Age of Piracy.
-
B.
Anne Bonny
Anne Bonny was an infamous early 18th-century Irish pirate known for her fierce temperament, cross-dressing in battle, and partnership with fellow pirate Calico Jack during the Golden Age of Piracy.
-
C.
Betsy Drake
Betsy Drake was an American actress and writer best known for her film work in the late 1940s and 1950s and for her influential role in the life and career of Cary Grant.
-
D.
Mary Ann Savage
Mary Ann Savage was the wife of American politician and Supreme Court Justice Ward Hunt.
-
E.
Mary Davis
Mary Davis is the wife of American country music singer Randy Travis and has been closely involved in managing his career and health in recent years.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4b1e52c8190894281cf7e3283ab |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69dc9de788190882ce471966ef2b4 |
completed | April 20, 2026, 9:42 p.m. |
Created at: April 16, 2026, 11:36 a.m.