Triple
T4071305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coat of arms of the South African Republic |
E86652
|
entity |
| Predicate | captionLanguage |
P4196
|
FINISHED |
| Object | Dutch |
—
|
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: Dutch | Statement: [Coat of arms of the South African Republic, captionLanguage, Dutch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: captionLanguage Context triple: [Coat of arms of the South African Republic, captionLanguage, Dutch]
-
A.
languageSpokenOnScreen
Indicates that a particular language is used in spoken dialogue or audible communication within an on-screen work (such as a film, show, or video).
-
B.
languageOfSignage
chosen
Indicates the language used on signs or written displays associated with an entity.
-
C.
contentLanguage
Indicates the language in which the content is expressed or intended to be understood.
-
D.
screenplayLanguage
Indicates the language in which a screenplay is written or primarily expressed.
-
E.
titleLanguageForm
Indicates the specific linguistic form or variant in which a title is expressed (e.g., language, script, or transliteration form).
- F. None of above.
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_69aed93ebe448190a1f1686e28740ac9 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefc1f6d9c8190845d2fcd15fcdfd6 |
completed | March 9, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69aef9061d2481908307cafc9e9b32c0 |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:38 p.m.