Triple
T10164666
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Attila the Hun |
E235175
|
entity |
| Predicate | source |
P409
|
FINISHED |
| Object | Jordanes |
E224013
|
NE 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: Jordanes | Statement: [Attila the Hun, source, Jordanes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jordanes Context triple: [Attila the Hun, source, Jordanes]
-
A.
Jordanes
chosen
Jordanes was a 6th-century Roman bureaucrat and historian best known for his work "Getica," a key source on the history of the Goths and other barbarian peoples.
-
B.
Nabataean kingdom
The Nabataean kingdom was an ancient Arab state centered on the city of Petra that flourished as a major trading hub in the Near East from around the 4th century BCE until its annexation by the Roman Empire.
-
C.
Jordan
Jordan is a municipality in the Philippines that serves as the capital of the island province of Guimaras in the Western Visayas region.
-
D.
Jordan
Jordan was a Formula One racing team and constructor known for launching the careers of several top drivers and competing in the sport during the 1990s and early 2000s.
-
E.
Jordan
Jordan is a scientist known for formally describing the bacterial genus Bradyrhizobium.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca84ceafd0819085828600e11bed6b |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdec6b96dc8190ae37d0d28e4c393b |
completed | April 2, 2026, 4:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d300d672fc8190ad5b937d02a737fd |
completed | April 6, 2026, 12:39 a.m. |
Created at: March 30, 2026, 9:10 p.m.