Triple
T31916919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lucius Scribonius Libo (consul 16 AD) |
E814856
|
entity |
| Predicate | mentioned in |
P26173
|
FINISHED |
| Object | Annals by Tacitus |
—
|
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: Annals by Tacitus | Statement: [Lucius Scribonius Libo (consul 16 AD), mentioned in, Annals by Tacitus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mentioned in Context triple: [Lucius Scribonius Libo (consul 16 AD), mentioned in, Annals by Tacitus]
-
A.
mentionedAs
chosen
Indicates that one entity is referred to or cited by name or description in the context of another entity.
-
B.
mentionedWith
Indicates that two entities are mentioned together or in close association within the same context, such as a document, sentence, or conversation.
-
C.
mentions
Indicates that one entity refers to, cites, or brings up another entity in some form of communication or content.
-
D.
mentionedVia
Indicates that one entity is referenced or brought up through a particular medium, channel, or mechanism represented by another entity.
-
E.
mentionedInInscription
Indicates that an entity is referenced or named within a specific inscription or inscribed text.
- 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_69f6b21e7e088190832a3db585daea1c |
completed | May 3, 2026, 2:25 a.m. |
| PD | Predicate disambiguation | batch_69f6b14faf608190a25b977c0740729c |
completed | May 3, 2026, 2:22 a.m. |
Created at: May 1, 2026, 12:02 a.m.