Triple
T31916909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lucius Scribonius Libo (consul 16 AD) |
E814856
|
entity |
| Predicate | co-consul |
P32433
|
FINISHED |
| Object | Gaius Caelius Rufus |
—
|
NE NERFINISHED |
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: Gaius Caelius Rufus | Statement: [Lucius Scribonius Libo (consul 16 AD), co-consul, Gaius Caelius Rufus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: co-consul Context triple: [Lucius Scribonius Libo (consul 16 AD), co-consul, Gaius Caelius Rufus]
-
A.
coConsulWith
chosen
Indicates that two individuals simultaneously held the office of consul together during the same term or period.
-
B.
thirdConsul
Indicates that an entity holds the position or role of the third consul in a specified governing body or context.
-
C.
consulshipWith
Indicates a relationship where two or more entities jointly hold, share, or are associated with the same consulship or consular office.
-
D.
consulship
Indicates the relationship in which an individual holds or exercises the office and powers of a consul.
-
E.
secondConsul
Indicates that an individual holds the position of the second consul in a consular pair or sequence.
- 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_69f348f109d88190b5005372c53d2fcd |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b1ef9a84819092952e451b98987b |
completed | May 3, 2026, 2:24 a.m. |
| PD | Predicate disambiguation | batch_69f6aca59d4881908d14ed47962703bd |
completed | May 3, 2026, 2:02 a.m. |
Created at: May 1, 2026, 12:02 a.m.