Triple
T37261191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Σικελία |
E924261
|
entity |
| Predicate | διαχωρίζεται από την Ιταλική χερσόνησο με |
P18114
|
FINISHED |
| Object |
Στενό της Μεσσίνας
Το Στενό της Μεσσίνας είναι μια στενή θαλάσσια δίοδος στη νότια Ιταλία που χωρίζει τη Σικελία από την ηπειρωτική χώρα και συνδέει το Τυρρηνικό με το Ιόνιο Πέλαγος.
|
E2218636
|
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: Στενό της Μεσσίνας | Statement: [Σικελία, διαχωρίζεται από την Ιταλική χερσόνησο με, Στενό της Μεσσίνας]
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: Στενό της Μεσσίνας Triple: [Σικελία, διαχωρίζεται από την Ιταλική χερσόνησο με, Στενό της Μεσσίνας]
Generated description
Το Στενό της Μεσσίνας είναι μια στενή θαλάσσια δίοδος στη νότια Ιταλία που χωρίζει τη Σικελία από την ηπειρωτική χώρα και συνδέει το Τυρρηνικό με το Ιόνιο Πέλαγος.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: διαχωρίζεται από την Ιταλική χερσόνησο με Context triple: [Σικελία, διαχωρίζεται από την Ιταλική χερσόνησο με, Στενό της Μεσσίνας]
-
A.
separatedFromContinent
Indicates that an entity is geographically detached or isolated from a main continental landmass.
-
B.
distanceFromIschia
Indicates the spatial distance between a given entity and the location Ischia.
-
C.
separatedFromByLand
Indicates that two entities are divided or kept apart from each other by an intervening landmass.
-
D.
isSeparatedFromMainlandBy
chosen
Indicates that one land area is divided from the mainland by a specific intervening body or feature, such as water or terrain.
-
E.
seaSeparatedFrom
Indicates that one geographic region or landmass is separated from another by a sea lying between them.
- F. None of above.
Provenance (6 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_69f76eabd6c481909d414a80a1345c98 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb4134225081909fd60703b8cae397 |
completed | May 6, 2026, 1:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a4043d8d2e481908c363980e133e824 |
completed | June 27, 2026, 9:42 p.m. |
| NEDg | Description generation | batch_6a40448854a88190852646c14a8f9864 |
completed | June 27, 2026, 9:45 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a404505b4048190bfadd456a3214fe1 |
completed | June 27, 2026, 9:47 p.m. |
| PD | Predicate disambiguation | batch_69fb35bf767081908de8345358ca7f44 |
completed | May 6, 2026, 12:36 p.m. |
Created at: May 3, 2026, 4:15 p.m.