Triple
T5042890
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Blue and the Gray |
E113586
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | John Jakes |
E489013
|
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: John Jakes | Statement: [The Blue and the Gray, writer, John Jakes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Jakes Context triple: [The Blue and the Gray, writer, John Jakes]
-
A.
John Jakes
chosen
John Jakes was an American author best known for his historical novels, particularly his popular Civil War and American history sagas.
-
B.
Nathan Furst
Nathan Furst is an American composer best known for scoring films and television series, particularly in the action and adventure genres.
-
C.
Louis Bayard
Louis Bayard is an American novelist known for his historical mysteries and literary thrillers, including the novel that inspired "The Pale Blue Eye."
-
D.
C.J. Sansom
C.J. Sansom was a British historical crime novelist best known for his bestselling Shardlake series set in Tudor England.
-
E.
A. J. Baime
A. J. Baime is an American author and journalist best known for his narrative nonfiction books on automotive history and high-stakes real-world dramas.
- 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_69bd44391fc48190a311ce9c826c209b |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd73df8f7481909a8b86c4ae69aab9 |
completed | March 20, 2026, 4:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bea47c5f808190821d7f708003a07d |
completed | March 21, 2026, 2 p.m. |
Created at: March 20, 2026, 1:37 p.m.