Triple
T32546341
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Χερσόνησος του Άθω |
E831857
|
entity |
| Predicate | έχειΕπίσημηΟνομασία |
P174577
|
FINISHED |
| Object |
Αθωνική Πολιτεία
Η Αθωνική Πολιτεία είναι μια αυτοδιοίκητη μοναστική πολιτεία της Ορθόδοξης Εκκλησίας στην Ελλάδα, γνωστή για τα πολυάριθμα ιστορικά μοναστήρια της και το αυστηρό καθεστώς πρόσβασης.
|
E2009491
|
NE FINISHED |
How this triple was built (3 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: Αθωνική Πολιτεία | Statement: [Χερσόνησος του Άθω, έχειΕπίσημηΟνομασία, Αθωνική Πολιτεία]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Αθωνική Πολιτεία Triple: [Χερσόνησος του Άθω, έχειΕπίσημηΟνομασία, Αθωνική Πολιτεία]
Generated description
Η Αθωνική Πολιτεία είναι μια αυτοδιοίκητη μοναστική πολιτεία της Ορθόδοξης Εκκλησίας στην Ελλάδα, γνωστή για τα πολυάριθμα ιστορικά μοναστήρια της και το αυστηρό καθεστώς πρόσβασης.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: έχειΕπίσημηΟνομασία Context triple: [Χερσόνησος του Άθω, έχειΕπίσημηΟνομασία, Αθωνική Πολιτεία]
-
A.
έχειΜεταγραφή
Indicates that an entity has been transferred or has undergone a transfer (e.g., between organizations, teams, or systems).
-
B.
έχειΚατηγοριοποιηθείΩς
Indicates that an entity has been classified or assigned to a specific category or type.
-
C.
έχειΘέα
Indicates that one entity offers or provides a view of, or overlooking, another entity.
-
D.
έχει_ανδριάντα
Indicates that an entity has or is associated with a statue (typically of a person).
-
E.
έχειΕτυμολογία
Indicates that an entity has a specific etymology or derives its origin from another linguistic source.
- F. None of above. chosen
Provenance (7 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_69f34925fd08819084cfe4ec566cb704 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c5bfe55881909a20ef79180d19c4 |
completed | May 3, 2026, 3:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a347080d3d88190a608c65ca95cc040 |
completed | June 18, 2026, 10:26 p.m. |
| NEDg | Description generation | batch_6a34710734988190a0a6880097a6a639 |
completed | June 18, 2026, 10:28 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a3471d84d708190bd56542c6f09ba30 |
completed | June 18, 2026, 10:31 p.m. |
| PD | Predicate disambiguation | batch_69f6bd2a14b081908162923dfbf0a6f4 |
completed | May 3, 2026, 3:12 a.m. |
| PDg | Predicate description generation | batch_69f6c1b666188190ac43c3011a7df048 |
completed | May 3, 2026, 3:32 a.m. |
Created at: May 1, 2026, 1:02 a.m.