Triple
T23246248
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maternus |
E581588
|
entity |
| Predicate | contrastsWith |
P278
|
FINISHED |
| Object | Aper |
—
|
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: Aper | Statement: [Maternus, contrastsWith, Aper]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aper Context triple: [Maternus, contrastsWith, Aper]
-
A.
Aper
chosen
Aper is a character in Tacitus's "Dialogus de oratoribus," depicted as an advocate of contemporary oratory and a defender of modern rhetorical practices against traditionalist critics.
-
B.
Aapep
Aapep is an alternate name for Apep, the ancient Egyptian serpent deity embodying chaos and the eternal enemy of the sun god Ra.
-
C.
Aparan
Aparan is a small town in Armenia’s Aragatsotn Province, known for its proximity to Mount Aragats and its historic churches and monuments.
-
D.
Aparo
Aparo is an Italian surname most notably associated with comic book artist Jim Aparo, known for his work on DC Comics titles such as Batman.
-
E.
Addaperle
Addaperle is a comedic good witch character in "The Wiz" universe, known for her quirky, bumbling magic and warm-hearted guidance.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e24606b17c81908aba1a4911c8a8ba |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f193f0f5d88190a497f14601f9bf29 |
completed | April 29, 2026, 5:15 a.m. |
Created at: April 17, 2026, 4:10 p.m.