Triple
T24240989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Self-Portrait in a Convex Mirror |
E603220
|
entity |
| Predicate | hasCentralPoem |
P21160
|
FINISHED |
| Object | Self-Portrait in a Convex Mirror (poem) |
—
|
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: Self-Portrait in a Convex Mirror (poem) | Statement: [Self-Portrait in a Convex Mirror, hasCentralPoem, Self-Portrait in a Convex Mirror (poem)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCentralPoem Context triple: [Self-Portrait in a Convex Mirror, hasCentralPoem, Self-Portrait in a Convex Mirror (poem)]
-
A.
hasCanonicalPoem
Indicates that an entity is associated with a poem recognized as its standard or authoritative version.
-
B.
hasPoemSetIn
Indicates that a poem is set in or takes place within a particular location or setting.
-
C.
containsPoem
chosen
Indicates that one entity includes or holds a poem as part of its contents.
-
D.
containsPoemsFrom
Indicates that one entity includes or features poems that originate from or are authored in association with another entity.
-
E.
containsPoemsBy
Indicates that one entity (such as a collection or publication) includes poems authored by 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_69e2953f631c819097cbb421046bd417 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f28a9f812c81909dba8fbb54d8985c |
completed | April 29, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69f1c448abec8190b87cbf9ed419a309 |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 18, 2026, 12:03 a.m.