Triple
T18066965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Central Croatia |
E432318
|
entity |
| Predicate | borders |
P224
|
FINISHED |
| Object | Lika |
—
|
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: Lika | Statement: [Central Croatia, borders, Lika]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lika Context triple: [Central Croatia, borders, Lika]
-
A.
Lika
chosen
Lika is a mountainous, sparsely populated historical region in central Croatia known for its karst landscapes, forests, and national parks such as Plitvice Lakes.
-
B.
Salka
Salka was an Austrian-American screenwriter, actress, and influential Hollywood salon hostess known for championing European émigré artists in the 1930s and 1940s.
-
C.
Tinka
Tinka is a literary work by German writer Volker Braun, known for its engagement with socialist themes and critical reflection on East German society.
-
D.
Tinka
Tinka is a fictional character portrayed by Danish actress Gerda Lie Kaas, likely in a Scandinavian film or television production.
-
E.
Liku
Liku is a village on the island of Wallis (ʻUvea) in the French overseas collectivity of Wallis and Futuna in the South Pacific.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9070cac81909fa9473fb1c3f1c7 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4cce97ce08190a2f8762ce545e091 |
completed | April 19, 2026, 12:39 p.m. |
Created at: April 10, 2026, 10:26 a.m.