Triple
T4202222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joseph Dudley |
E86092
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Paul Dudley |
E94501
|
NE 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: Paul Dudley | Statement: [Joseph Dudley, child, Paul Dudley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Dudley Context triple: [Joseph Dudley, child, Paul Dudley]
-
A.
Paul Dudley
chosen
Paul Dudley was a prominent early 18th-century Massachusetts jurist and attorney general known for his influential role in the legal and political life of colonial New England.
-
B.
William Fell
William Fell was an early landowner and shipbuilder in Baltimore, Maryland, after whom the historic waterfront neighborhood Fells Point is named.
-
C.
Christian Van Dyke
Christian Van Dyke is one of the children of legendary American actor and entertainer Dick Van Dyke.
-
D.
William Erasmus
William Erasmus is the eldest son of naturalist Charles Darwin and his wife Emma, known for his close involvement with his father's work and the broader Darwin family circle.
-
E.
William Markham
William Markham was a historical figure significant enough in Canadian or local history that the city of Markham, Ontario, was named in his honor.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69aed93b89f48190a31f6d57c760e42f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af037f1de4819088d6bf544317a694 |
completed | March 9, 2026, 5:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b58a173a78819094915f63c8411602 |
completed | March 14, 2026, 4:17 p.m. |
Created at: March 9, 2026, 3:49 p.m.