Triple
T23246255
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maternus |
E581588
|
entity |
| Predicate | workAuthoredInNarrative |
P114742
|
FINISHED |
| Object | tragedies on Roman historical subjects |
—
|
LITERAL 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: tragedies on Roman historical subjects | Statement: [Maternus, workAuthoredInNarrative, tragedies on Roman historical subjects]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workAuthoredInNarrative Context triple: [Maternus, workAuthoredInNarrative, tragedies on Roman historical subjects]
-
A.
narrativeAuthor
chosen
Indicates that one entity is the author or creator of a given narrative associated with another entity.
-
B.
authorOfNarrativeWithinWork
Indicates that one entity is the creator or writer of a narrative that exists as a component or embedded story within a larger work.
-
C.
hasNarrativeToneOfWork
Indicates that a work exhibits or is characterized by a particular narrative tone.
-
D.
workAuthoredIn
Indicates that a work was created or written in a particular place or time context.
-
E.
worksOnStoryAbout
Indicates that one entity is actively engaged in creating, developing, or contributing to a story whose subject or focus is another entity.
- 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_69e24606b17c81908aba1a4911c8a8ba |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f193f0f5d88190a497f14601f9bf29 |
completed | April 29, 2026, 5:15 a.m. |
| PD | Predicate disambiguation | batch_69effce4d704819092826931d430e8c4 |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:10 p.m.