Triple
T33923886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Italia annonaria |
E869694
|
entity |
| Predicate | establishedUnderEmperor |
P98269
|
FINISHED |
| Object | Diocletian |
—
|
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: Diocletian | Statement: [Italia annonaria, establishedUnderEmperor, Diocletian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: establishedUnderEmperor Context triple: [Italia annonaria, establishedUnderEmperor, Diocletian]
-
A.
formedUnderEmperor
chosen
Indicates that an entity (such as a group, institution, or administrative unit) was created or established during the reign or authority of a specific emperor.
-
B.
concludedUnderEmperor
Indicates that an event, agreement, or process was completed or formally concluded during the reign of a specific emperor.
-
C.
hasDateUnderEmperor
Indicates that an event or record occurred during the reign of a specified emperor.
-
D.
establishedUnderDynasty
Indicates that something (such as an institution, structure, or entity) was founded or created during the rule of a specific dynasty.
-
E.
hasEmperor
Indicates that an entity is ruled or governed by an emperor.
- 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_69f349992c508190aa4afa24a086cc8c |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fbbc49da8c8190902bbb05d2477cab |
completed | May 6, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69fbb13f34b08190bbbb220ac1e6e666 |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 1, 2026, 1:49 a.m.