Triple
T23064802
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George W. Frye |
E575003
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | George |
—
|
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: George | Statement: [George W. Frye, givenName, George]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: George Context triple: [George W. Frye, givenName, George]
-
A.
George
George is the given name of George W. McLaurin, the first African American student admitted to the University of Oklahoma.
-
B.
George
George is the given name of Lord George Gordon, an 18th-century British politician best known for inciting the anti-Catholic Gordon Riots of 1780.
-
C.
George
George is the given name of George K. Zipf, the American linguist and philologist known for formulating Zipf's law about word frequency distributions.
-
D.
George
George is the given name of George Spencer, 4th Duke of Marlborough, an 18th-century British nobleman and politician.
-
E.
George
George is the given name of George Keith, 10th Earl Marischal, a prominent Scottish nobleman and statesman of the 17th century.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69e245bd6e4c8190bb8942245b68cad5 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f189a2eb5c81908a90e22ff2a56430 |
completed | April 29, 2026, 4:31 a.m. |
Created at: April 17, 2026, 3:55 p.m.