Triple
T13534828
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treaty of Wuchale |
E323233
|
entity |
| Predicate | AmharicVersionStated |
P54502
|
FINISHED |
| Object | Ethiopia may use Italian government for foreign relations |
—
|
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: Ethiopia may use Italian government for foreign relations | Statement: [Treaty of Wuchale, AmharicVersionStated, Ethiopia may use Italian government for foreign relations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: AmharicVersionStated Context triple: [Treaty of Wuchale, AmharicVersionStated, Ethiopia may use Italian government for foreign relations]
-
A.
languageOfOfficialAnnouncements
Indicates the language used for formal or official public announcements issued by an authority.
-
B.
hasChineseVersion
chosen
Indicates that an entity has a corresponding version or representation available in Chinese.
-
C.
languageOfUSVersion
Indicates that one entity is the language used in the U.S. version of another entity (such as a work, product, or edition).
-
D.
languageOfOfficialEditions
Indicates the language in which the official editions or versions of a work, document, or publication are produced or authorized.
-
E.
translatedIn
Indicates that a work, text, or content has been rendered from its original language into another specified language or linguistic 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_69d8076776248190bdf0d4fa1f85a5fc |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbafbcad2881909fb7490311807f75 |
completed | April 12, 2026, 2:44 p.m. |
| PD | Predicate disambiguation | batch_69dbae1046c48190b4ee98c6c9cb9d85 |
completed | April 12, 2026, 2:37 p.m. |
Created at: April 9, 2026, 9:44 p.m.