Triple
T14078028
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sky |
E338790
|
entity |
| Predicate | settingOfStory |
P1957
|
FINISHED |
| Object | Kalokairi |
E1073317
|
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: Kalokairi | Statement: [Sky, settingOfStory, Kalokairi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kalokairi Context triple: [Sky, settingOfStory, Kalokairi]
-
A.
Kalokairi
chosen
Kalokairi is a fictional Greek island best known as the main setting of the musical and film "Mamma Mia!".
-
B.
Pefkochori
Pefkochori is a popular seaside village in northern Greece known for its beaches, pine trees, and tourist resorts on the Kassandra peninsula.
-
C.
Asakyiri
Asakyiri is one of the traditional matrilineal clans of the Akan people of Ghana, associated with shared ancestry, symbols, and social responsibilities.
-
D.
Kouklia
Kouklia is a village in the Paphos District of Cyprus known for its rich archaeological heritage, including the ancient sanctuary of Aphrodite at Palaepaphos.
-
E.
Katafidi
Katafidi is a prominent mountain peak in the Tzoumerka range of the Pindus Mountains in northwestern Greece.
- 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_69d81c687b0c819087fd9ed4198403f8 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5c5e027881908f610f5bab7598d4 |
completed | April 14, 2026, 3:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb670f51c819088e8d0137f8d3bb1 |
completed | May 7, 2026, 3:57 p.m. |
Created at: April 9, 2026, 10:21 p.m.