Triple
T35320523
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Xiphilinus |
E1020025
|
entity |
| Predicate | sourceAuthorAbridged |
P33057
|
FINISHED |
| Object | Cassius Dio |
—
|
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: Cassius Dio | Statement: [John Xiphilinus, sourceAuthorAbridged, Cassius Dio]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sourceAuthorAbridged Context triple: [John Xiphilinus, sourceAuthorAbridged, Cassius Dio]
-
A.
authorOrigin
Indicates that an author has a specific place, region, or country as their origin or background.
-
B.
originAuthor
Indicates that an entity is the original creator or author of another entity (such as a work, document, or idea).
-
C.
originalAuthorOfSource
Indicates that an entity is the original creator or author of a given source or work.
-
D.
authorAsCredited
Indicates the relationship between a work and the person or entity credited as its author, regardless of actual authorship.
-
E.
authorAbbreviation
chosen
Indicates that one entity is the standardized abbreviated form of an author's name used in citations or references for 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_69f76de9d45c81908a2ed0956b448b65 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7a225a77c81908f8953ccfeb14336 |
completed | May 3, 2026, 7:29 p.m. |
| PD | Predicate disambiguation | batch_69f7a06d4f108190bae3ab9ae431d2c7 |
completed | May 3, 2026, 7:22 p.m. |
Created at: May 3, 2026, 4:03 p.m.