Triple
T34498959
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | court of Honorius |
E885694
|
entity |
| Predicate | influentialGeneral |
P192730
|
FINISHED |
| Object | Stilicho |
—
|
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: Stilicho | Statement: [court of Honorius, influentialGeneral, Stilicho]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: influentialGeneral Context triple: [court of Honorius, influentialGeneral, Stilicho]
-
A.
influentialAs
Indicates that one entity has at least as much influence or impact as another entity.
-
B.
influentialFrom
Indicates that one entity has exerted influence on another, contributing to or shaping the latter’s ideas, behavior, or development.
-
C.
influenceOf
Indicates that one entity affects, shapes, or alters the state, behavior, or properties of another entity.
-
D.
typeOfInfluence
Indicates the specific nature or category of influence that one entity exerts on another.
-
E.
influentialUnder
Indicates that one entity is significantly shaped, guided, or affected by the influence or authority of another entity.
- F. None of above. chosen
Provenance (4 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_69f349cafcec8190997b45b3fdc16c27 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69fd2839880c819099a7a89783f2270e |
completed | May 8, 2026, 12:03 a.m. |
| PD | Predicate disambiguation | batch_69fd23dc5da48190ae8ba08947d34956 |
completed | May 7, 2026, 11:44 p.m. |
| PDg | Predicate description generation | batch_69fd28379d2c8190903ba228ee1cc756 |
completed | May 8, 2026, 12:03 a.m. |
Created at: May 1, 2026, 2:01 a.m.