Triple
T22453928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jane Rolfe |
E555062
|
entity |
| Predicate | mother |
P120
|
FINISHED |
| Object | Thomas Rolfe |
—
|
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: Thomas Rolfe | Statement: [Jane Rolfe, mother, Thomas Rolfe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thomas Rolfe Context triple: [Jane Rolfe, mother, Thomas Rolfe]
-
A.
Thomas Rolfe
chosen
Thomas Rolfe was the son of English colonist John Rolfe and Pocahontas, notable as a figure linking early English settlers and Native American leadership in colonial Virginia.
-
B.
John Rolfe
John Rolfe was an early English settler in Virginia best known for developing the profitable cultivation of tobacco and for his marriage to Pocahontas.
-
C.
Mary Rolfe
Mary Rolfe was the wife of American film and television actor Lyle Bettger.
-
D.
John Wayles
John Wayles was an 18th-century Virginia planter, lawyer, and slave trader best known as the father of Martha Wayles Skelton Jefferson and the father-in-law of Thomas Jefferson.
-
E.
John Alden
John Alden was an English cooper and early settler of Plymouth Colony, best known as one of the original Mayflower passengers and a prominent figure in early New England history.
- 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_69e11e5113208190ab58c6b595f9d1d0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b4d6368819082cafbbd83339fbf |
completed | April 29, 2026, 1:13 a.m. |
Created at: April 16, 2026, 8:48 p.m.