Triple
T21576305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crete and Cyrenaica |
E532401
|
entity |
| Predicate | borderedBy |
P224
|
FINISHED |
| Object | Marmarica |
—
|
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: Marmarica | Statement: [Crete and Cyrenaica, borderedBy, Marmarica]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marmarica Context triple: [Crete and Cyrenaica, borderedBy, Marmarica]
-
A.
Marmarica
chosen
Marmarica was an ancient coastal region in North Africa, situated between Cyrenaica (in modern eastern Libya) and Egypt, known from Greek and Roman geography.
-
B.
Mary Beard
Mary Beard is a prominent British classicist, author, and broadcaster known for her accessible and influential work on ancient Rome and public engagement with the humanities.
-
C.
J.P. Bowersock
J.P. Bowersock is an American guitarist and producer best known for his work with Ryan Adams and The Strokes.
-
D.
Ian Greer
Ian Greer is a British academic and medical researcher who serves as the President and Vice-Chancellor of Queen’s University Belfast.
-
E.
Geoffrey Lloyd
Geoffrey Lloyd was a British Conservative politician who served in several ministerial roles in the mid-20th century, particularly in areas related to energy and industry.
- 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_69e0c4618bec8190bcb0feb74568cbb1 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eee9d07ddc8190a4bba08223e56f46 |
completed | April 27, 2026, 4:45 a.m. |
Created at: April 16, 2026, 6:31 p.m.