Triple
T2030361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sabines |
E44501
|
entity |
| Predicate | majorSettlement |
P316
|
FINISHED |
| Object | Cures Sabini |
E225365
|
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: Cures Sabini | Statement: [Sabines, majorSettlement, Cures Sabini]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cures Sabini Context triple: [Sabines, majorSettlement, Cures Sabini]
-
A.
Cures Sabini
chosen
Cures Sabini was an ancient city of the Sabine people in central Italy, historically significant as a regional center and later a Roman municipium.
-
B.
Cure
The Cure is a river in central France that flows through the Burgundy region before joining the Yonne.
-
C.
Panacea
Panacea is the Greek goddess of universal remedy and healing, associated with cures for all diseases.
-
D.
Quanta cura
Quanta cura is an 1864 papal encyclical by Pope Pius IX that condemns modern liberalism and religious indifferentism, issued together with the Syllabus of Errors.
-
E.
Antidote
"Antidote" is a breakout hit single by American rapper Travis Scott, known for its moody production, catchy hook, and major role in elevating his mainstream popularity.
- 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_69a889144f2481909932f0746a93023d |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb914a40081909a937689bea3dc85 |
completed | March 7, 2026, 5:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae1fed963c8190ac205b46f93ad650 |
completed | March 9, 2026, 1:18 a.m. |
Created at: March 4, 2026, 7:38 p.m.