Triple
T29694361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cornelius Leyden |
E751301
|
entity |
| Predicate | isDrawnInto |
P150335
|
FINISHED |
| Object | investigation of the life and death of Dimitrios |
—
|
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: investigation of the life and death of Dimitrios | Statement: [Cornelius Leyden, isDrawnInto, investigation of the life and death of Dimitrios]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isDrawnInto Context triple: [Cornelius Leyden, isDrawnInto, investigation of the life and death of Dimitrios]
-
A.
ifDraw
Indicates that one entity draws, sketches, or creates a visual representation of another entity.
-
B.
hasDrawType
Indicates that an entity is associated with a specific manner, style, or category of drawing or graphical rendering.
-
C.
drawnTo
chosen
Indicates that one entity is attracted or pulled toward another entity, whether physically, emotionally, or conceptually.
-
D.
drawnUnder
Indicates that one entity is depicted or represented as being beneath another entity in a drawing or visual representation.
-
E.
isPainted
Indicates that one entity has applied paint to cover or decorate the surface of 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_69f0d625b09481909b0b69aea1e846c8 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f672af46e48190b76e9298e7d23eef |
completed | May 2, 2026, 9:54 p.m. |
| PD | Predicate disambiguation | batch_69f6659f246081909821c5f452d14e8f |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 7:19 p.m.