Triple
T15709200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vigo the Carpathian |
E380790
|
entity |
| Predicate | mediumOfExistence |
P119873
|
FINISHED |
| Object | haunted painting |
—
|
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: haunted painting | Statement: [Vigo the Carpathian, mediumOfExistence, haunted painting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mediumOfExistence Context triple: [Vigo the Carpathian, mediumOfExistence, haunted painting]
-
A.
mediumOfFame
Indicates the medium, field, or domain through which an entity became famous or gained public recognition.
-
B.
visualMedium
Indicates that one entity serves as the visual medium or format through which another entity is presented, communicated, or experienced.
-
C.
mediatisedBy
Indicates that an entity’s communication or interaction is conveyed, shaped, or influenced through a particular medium or media channel rather than occurring directly.
-
D.
mediumSupport
Indicates that one entity provides a moderate or intermediate level of support or assistance to another entity.
-
E.
mediumOfOrigin
Indicates the original physical or digital medium from which an item, work, or data was derived or obtained.
- 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_69d86d9bf930819082b30cf6d169297c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f8d8b648190842c635f2ae7bfa4 |
completed | April 16, 2026, 2:55 a.m. |
| PD | Predicate disambiguation | batch_69e00526759c819088b80d85138b8974 |
completed | April 15, 2026, 9:37 p.m. |
| PDg | Predicate description generation | batch_69e0094af5b481908ad51d5d7ba0c726 |
completed | April 15, 2026, 9:55 p.m. |
Created at: April 10, 2026, 4:45 a.m.