Triple
T20119049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Samuel Dylan |
E490548
|
entity |
| Predicate | childOf |
P120
|
FINISHED |
| Object | Sara Lowndes |
—
|
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: Sara Lowndes | Statement: [Samuel Dylan, childOf, Sara Lowndes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sara Lowndes Context triple: [Samuel Dylan, childOf, Sara Lowndes]
-
A.
Sara Lowndes
chosen
Sara Lowndes is an American former model and artist best known as the first wife of musician Bob Dylan and the mother of several of his children.
-
B.
Mary Ludlum
Mary Ludlum was the wife of American thriller novelist Robert Ludlum, known for supporting him throughout his writing career.
-
C.
Catherine Ryan Hyde
Catherine Ryan Hyde is an American author best known for her novel "Pay It Forward," which inspired the popular film of the same name.
-
D.
Margaret McTague
Margaret McTague was the wife of New York politician and long-serving U.S. Senator Robert F. Wagner.
-
E.
Amanda Cross
Amanda Cross is the pen name of American literary scholar Carolyn Gold Heilbrun, best known for her feminist academic work and her Kate Fansler mystery novels.
- 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_69da62636cc08190982cc71733a17b8d |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6673c32bc8190a52875961fbcc5e2 |
completed | April 20, 2026, 5:49 p.m. |
Created at: April 11, 2026, 11:30 p.m.