Triple
T25957680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Union of the Great Islands |
E645448
|
entity |
| Predicate | hasTranslationDirection |
P20095
|
FINISHED |
| Object | from Comorian to English |
—
|
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: from Comorian to English | Statement: [The Union of the Great Islands, hasTranslationDirection, from Comorian to English]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTranslationDirection Context triple: [The Union of the Great Islands, hasTranslationDirection, from Comorian to English]
-
A.
hasTranslation
Indicates that one entity is a translation or translated version of another entity in a different language.
-
B.
translationDirection
chosen
Indicates the source and target languages involved in a translation, specifying the direction from the original language to the translated language.
-
C.
canTranslateBetween
Indicates that an entity has the ability to translate or convert information accurately between two specified languages, formats, or representation systems.
-
D.
hasTranslationBase
Indicates that one entity serves as the original source or base text from which the other entity is translated.
-
E.
hasTranslated
Indicates that one entity has rendered the content of another entity from one language into a different language.
- 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_69e77e85efc08190997da7fcf98bd300 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f6c49627908190b3553474c7c3072b |
completed | May 3, 2026, 3:44 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f23ae081909a52801266063a3c |
completed | May 3, 2026, 3:41 a.m. |
Created at: April 22, 2026, 8:46 a.m.