Triple
T7232709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gaj's Latin alphabet |
E154939
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | Croatian Latin alphabet |
E415242
|
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: Croatian Latin alphabet | Statement: [Gaj's Latin alphabet, alsoKnownAs, Croatian Latin alphabet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Croatian Latin alphabet Context triple: [Gaj's Latin alphabet, alsoKnownAs, Croatian Latin alphabet]
-
A.
Croatian Latin alphabet
chosen
The Croatian Latin alphabet is the standardized Latin-based writing system used for the Croatian language, employing a set of letters with specific diacritics to represent its phonemic inventory.
-
B.
Serbian Latin alphabet
The Serbian Latin alphabet is the standardized Latin-script writing system used for the Serbian language alongside the Serbian Cyrillic alphabet.
-
C.
Montenegrin Latin alphabet
The Montenegrin Latin alphabet is the standardized Latin-based writing system used for the Montenegrin language, distinguished by a few additional letters that reflect its specific phonetic features.
-
D.
Serbian Cyrillic alphabet
The Serbian Cyrillic alphabet is the standardized Cyrillic script used for writing the Serbian language, consisting of 30 letters in a one-to-one correspondence with Serbian phonemes.
-
E.
Bosnian Cyrillic
Bosnian Cyrillic is a medieval variant of the Cyrillic script historically used in parts of Bosnia and neighboring regions for religious and administrative texts.
- 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_69c68811dd1c8190ac460bb39e64e1f0 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea106cc881909348be576ced4beb |
completed | March 27, 2026, 8:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7cc2786f88190b0008891f801ca95 |
completed | March 28, 2026, 12:40 p.m. |
Created at: March 27, 2026, 2:54 p.m.