Triple
T9146968
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Serbo-Croatian |
E219480
|
entity |
| Predicate | hasISO639MacrolanguageCode |
P87026
|
FINISHED |
| Object | hbs |
—
|
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: hbs | Statement: [Serbo-Croatian, hasISO639MacrolanguageCode, hbs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasISO639MacrolanguageCode Context triple: [Serbo-Croatian, hasISO639MacrolanguageCode, hbs]
-
A.
isMacrolanguageCode
Indicates that a language code represents a macrolanguage encompassing multiple individual language varieties or codes.
-
B.
ISO639Macrolanguage
Indicates that a language variety is part of a broader ISO 639-defined macrolanguage grouping that encompasses multiple closely related individual languages.
-
C.
hasISO6393Code
Indicates that a language or linguistic entity is associated with a specific ISO 639-3 three-letter language code.
-
D.
hasISO639_5Code
Indicates that a language or language group is associated with a specific ISO 639-5 code that identifies it within the ISO 639-5 language classification standard.
-
E.
macrolanguageOf
Indicates that one language functions as a macrolanguage encompassing or grouping together one or more related individual languages.
- F. None of above. chosen
Provenance (4 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_69ca83e121dc81909912bd66953081c5 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca918a3c881909c34a6a682eb2625 |
completed | April 1, 2026, 5:11 a.m. |
| PD | Predicate disambiguation | batch_69cc6603ce8c8190bf6e8d6754bdec54 |
completed | April 1, 2026, 12:25 a.m. |
| PDg | Predicate description generation | batch_69cc6a3d230881909635b2ccea35cedb |
completed | April 1, 2026, 12:43 a.m. |
Created at: March 30, 2026, 7:20 p.m.