Triple
T14034786
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sezze |
E337682
|
entity |
| Predicate | sharesBorderWith |
P224
|
FINISHED |
| Object | Sabaudia |
E337680
|
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: Sabaudia | Statement: [Sezze, sharesBorderWith, Sabaudia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sabaudia Context triple: [Sezze, sharesBorderWith, Sabaudia]
-
A.
Sabaudia
chosen
Sabaudia is a coastal town in the Lazio region of central Italy, known for its rationalist architecture and long sandy beaches along the Tyrrhenian Sea.
-
B.
Capet
Capet is the dynastic surname of the medieval French royal house that began with Hugh Capet and ruled France for centuries.
-
C.
Vergniaud
Vergniaud is a French surname most notably borne by Pierre Victurnien Vergniaud, a prominent orator and leading figure of the Girondin faction during the French Revolution.
-
D.
Boulon
Boulon is a small commune in the Calvados department of northwestern France, situated within the arrondissement of Caen.
-
E.
Dioise
Dioise is the French demonym referring to inhabitants of the town of Die in the Drôme department of southeastern France.
- 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_69d81c664e48819088cbd8f433aeffe5 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2fac71188190a586049405f1071e |
completed | April 14, 2026, 12:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb65a21088190a14808d09b2b9f42 |
completed | May 7, 2026, 3:57 p.m. |
Created at: April 9, 2026, 10:20 p.m.