Triple
T1810461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berytus |
E40318
|
entity |
| Predicate | grantedBy |
P2246
|
FINISHED |
| Object | Emperor Augustus |
E5360
|
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: Emperor Augustus | Statement: [Berytus, grantedBy, Emperor Augustus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Emperor Augustus Context triple: [Berytus, grantedBy, Emperor Augustus]
-
A.
Augustus
chosen
Augustus was the first Roman emperor, who established the Roman Empire and led a period of relative peace and prosperity known as the Pax Romana.
-
B.
Gaius Octavius
Gaius Octavius was a Roman senator and provincial governor best known as the biological father of Augustus, the first Roman emperor.
-
C.
Auguste
Auguste is a masculine French given name historically borne by notable figures such as philosophers, artists, and scientists.
-
D.
Claudi
Claudi is a given name, typically a variant or shortened form of names like Claudiu or Claudia used in various European languages.
-
E.
Julius
Julius is the main character of Cory Doctorow's science fiction novel "Down and Out in the Magic Kingdom," navigating a post-scarcity future society centered around a radically transformed Disney World.
- 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_69a88643a3388190a612f2ebe1fb29e7 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69aa65c461e881908070cb80d9092981 |
completed | March 6, 2026, 5:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afb65e6d588190ad1a33a92785fd91 |
completed | March 10, 2026, 6:12 a.m. |
Created at: March 4, 2026, 7:32 p.m.