Triple
T330321
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eton College |
E6610
|
entity |
| Predicate | alumnus |
P51
|
FINISHED |
| Object | Ian Fleming |
E3433
|
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: Ian Fleming | Statement: [Eton College, alumnus, Ian Fleming]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ian Fleming Context triple: [Eton College, alumnus, Ian Fleming]
-
A.
Ian Fleming
chosen
Ian Fleming was a British author and journalist best known as the creator of the James Bond spy novels.
-
B.
Peter Fleming
Peter Fleming was a British travel writer, journalist, and adventurer, best known for his travel books and for his work as a wartime intelligence officer.
-
C.
Edgar Wallace
Edgar Wallace was a prolific British writer best known for his crime novels and for contributing to the original story that inspired the 1933 film "King Kong."
-
D.
Arthur Conan Doyle
Arthur Conan Doyle was a British writer best known as the creator of the iconic detective Sherlock Holmes and a foundational figure in modern crime fiction.
-
E.
Charles Foster
Charles Foster is one of the children of acclaimed American actress and filmmaker Jodie Foster.
- 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_69a2e79434908190a9d5afe415153ad9 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2eaaeb64881909c7ab9bca3378e2b |
completed | Feb. 28, 2026, 1:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a3cff160788190a49faad3c011965e |
completed | March 1, 2026, 5:34 a.m. |
Created at: Feb. 28, 2026, 1:08 p.m.