Triple
T22925363
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Μάχη του Κλεισούρας |
E569289
|
entity |
| Predicate | γλώσσα τοπωνυμίου |
P24399
|
FINISHED |
| Object | ελληνικά |
—
|
LITERAL 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: ελληνικά | Statement: [Μάχη του Κλεισούρας, γλώσσα τοπωνυμίου, ελληνικά]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: γλώσσα τοπωνυμίου Context triple: [Μάχη του Κλεισούρας, γλώσσα τοπωνυμίου, ελληνικά]
-
A.
onomasticType
Indicates the specific kind or category of a name (e.g., personal, place, or other name type) that characterizes the naming relationship.
-
B.
hasLanguageOfToponym
chosen
Indicates that a place name (toponym) is expressed in or associated with a particular language.
-
C.
hasToponymy
Indicates a relationship where one entity possesses or is associated with the system, study, or set of place names (toponyms) of another entity.
-
D.
eponymLanguage
Indicates that a language is named after (is the eponym of) a particular person, place, or entity.
-
E.
influenceOnToponymy
Indicates that one entity has affected or shaped the naming, form, or development of place names associated with another entity.
- F. None of above.
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_69e2458f7d008190901dccbaebeaba24 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f180d84fc08190b747c3f9052c657a |
completed | April 29, 2026, 3:54 a.m. |
| PD | Predicate disambiguation | batch_69ef3b7c5fc081909ac50c5c8569cc19 |
completed | April 27, 2026, 10:33 a.m. |
Created at: April 17, 2026, 3:43 p.m.