Triple
T28381532
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | bombing of Dresden |
E718901
|
entity |
| Predicate | authorWhoDepicted |
P73801
|
FINISHED |
| Object | Kurt Vonnegut |
—
|
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: Kurt Vonnegut | Statement: [bombing of Dresden, authorWhoDepicted, Kurt Vonnegut]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: authorWhoDepicted Context triple: [bombing of Dresden, authorWhoDepicted, Kurt Vonnegut]
-
A.
authorOfDepiction
chosen
Indicates that one entity is the creator or author responsible for producing a particular depiction of another entity.
-
B.
composerOfDepictingWork
Indicates that an entity is the composer of a musical work that is itself a depiction or representation of another entity or subject.
-
C.
depictsAuthorOf
Indicates that one entity visually represents or portrays the person who is the author of another entity.
-
D.
depictedInAuthor
Indicates that an author is visually represented or portrayed within a particular work or depiction.
-
E.
authorOfWorkAbout
Indicates that one entity is the author or creator of a work whose subject or content is about 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_69eff6ee5afc8190bd7375a29f0cc6c6 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f74c70fd248190a9d5543afcb08211 |
completed | May 3, 2026, 1:24 p.m. |
| PD | Predicate disambiguation | batch_69f7478e3b548190a51d5d436e2bb036 |
completed | May 3, 2026, 1:03 p.m. |
Created at: April 28, 2026, 1:06 a.m.