Triple
T21588112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Umbundu language |
E532704
|
entity |
| Predicate | hasLanguageCodeStandard |
P22958
|
FINISHED |
| Object | ISO 639-3 |
—
|
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: ISO 639-3 | Statement: [Umbundu language, hasLanguageCodeStandard, ISO 639-3]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ISO 639-3 Context triple: [Umbundu language, hasLanguageCodeStandard, ISO 639-3]
-
A.
ISO 639-3
chosen
ISO 639-3 is an international standard that assigns three-letter codes to uniquely identify the world’s languages, including many lesser-known and endangered ones.
-
B.
ISO 639
ISO 639 is an international standard that defines codes for the representation of names of languages.
-
C.
ISO 639-3 Registration Authority
The ISO 639-3 Registration Authority is the organization responsible for maintaining and updating the ISO 639-3 standard, which assigns three-letter codes to the world’s languages.
-
D.
ISO 3166-3
ISO 3166-3 is the part of the ISO 3166 standard that defines codes for countries and territories that have been removed from the current ISO 3166-1 list, providing their former country codes and their replacements.
-
E.
ISO 15924
ISO 15924 is an international standard that assigns four-letter codes to the world’s writing systems and scripts for use in information processing and interchange.
- 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_69e0c46251648190876f0427cf2d321b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eeeb621ab88190a33a943424ffb306 |
completed | April 27, 2026, 4:51 a.m. |
Created at: April 16, 2026, 6:31 p.m.