Triple
T9054424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Byzacena |
E216961
|
entity |
| Predicate | borderedBy |
P224
|
FINISHED |
| Object | Zeugitana |
E216962
|
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: Zeugitana | Statement: [Byzacena, borderedBy, Zeugitana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zeugitana Context triple: [Byzacena, borderedBy, Zeugitana]
-
A.
Zeugitana
chosen
Zeugitana was an ancient region in northern Tunisia centered around Carthage, known as a key coastal and urbanized area of Roman North Africa.
-
B.
Zogoiby
Zogoiby is the surname of Aurora Zogoiby, a character from Salman Rushdie’s novel "The Moor’s Last Sigh."
-
C.
Galissas
Galissas is a coastal village and popular beach resort on the Greek island of Syros in the Cyclades.
-
D.
Dardanella
Dardanella is a popular early 20th-century jazz and dance band standard, best known through Ben Selvin’s hugely successful recording.
-
E.
Adigeni
Adigeni is a small town in southern Georgia, serving as a local administrative and cultural center within the Samtskhe-Javakheti region.
- 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_69ca83d362e88190ae44b4e4dc194209 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc7a72e2dc8190a16deff8abe701b1 |
completed | April 1, 2026, 1:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfebdb01a8819084365c9b73506a28 |
completed | April 3, 2026, 4:33 p.m. |
Created at: March 30, 2026, 7:10 p.m.