Triple
T29015836
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Αδαμάντιος Κοραής |
E737303
|
entity |
| Predicate | έδρασε κυρίως σε |
P130710
|
FINISHED |
| Object | Παρίσι |
—
|
NE NERFINISHED |
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: Παρίσι | Statement: [Αδαμάντιος Κοραής, έδρασε κυρίως σε, Παρίσι]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: έδρασε κυρίως σε Context triple: [Αδαμάντιος Κοραής, έδρασε κυρίως σε, Παρίσι]
-
A.
έδρασεΚυρίωςΣε
chosen
Indicates that an entity carried out its main or most significant activity in a particular place or context.
-
B.
ήταν_ηγετική_δύναμη_στην
Indicates that an entity served as the leading or dominant force in, or had primary leadership over, another entity or organization.
-
C.
δραστηριοποιείταιΣε
Indicates that an entity is active, operates, or conducts its activities within a specified area, field, or context.
-
D.
έδραΠρωθυπουργίας
Indicates the location or seat where the office and functions of the Prime Minister are based or carried out.
-
E.
δραστηριοποιείταιΚατά
Indicates that an entity actively operates against, opposes, or takes action targeting another entity or issue.
- 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_69f077ee19f881909af48f9cab00a2e5 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f65fe0772881909b1fbc2e28a1206a |
completed | May 2, 2026, 8:34 p.m. |
| PD | Predicate disambiguation | batch_69f659d297cc8190b2b962ba30a1edb3 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 9:45 a.m.