Triple
T21489541
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Norman Davies |
E530200
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Norman Davies |
—
|
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: Norman Davies | Statement: [Norman Davies, name, Norman Davies]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Norman Davies Context triple: [Norman Davies, name, Norman Davies]
-
A.
Norman Davies
chosen
Norman Davies is a British historian renowned for his influential works on Polish and European history, including detailed studies of key events such as the 1920 Battle of Warsaw.
-
B.
Norman Stone
Norman Stone was a prominent British historian known for his work on modern European history and his controversial conservative views.
-
C.
Orlando Figes
Orlando Figes is a British historian and author renowned for his influential works on Russian and European history.
-
D.
Michael Holroyd
Michael Holroyd is a renowned British biographer best known for his definitive lives of figures such as Lytton Strachey, Bernard Shaw, and Augustus John.
-
E.
Eugene Rogan
Eugene Rogan is a British historian and professor at the University of Oxford, best known for his influential works on the modern history of the Middle East.
- 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea39e73081908e8d14118f9d1e03 |
completed | April 23, 2026, 9:45 a.m. |
Created at: April 16, 2026, 6:22 p.m.