Triple
T35309415
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Concrete Masterpiece |
E1019725
|
entity |
| Predicate | hasFictionalArtwork |
P93730
|
FINISHED |
| Object | prison-wall frescoes |
—
|
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: prison-wall frescoes | Statement: [The Concrete Masterpiece, hasFictionalArtwork, prison-wall frescoes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFictionalArtwork Context triple: [The Concrete Masterpiece, hasFictionalArtwork, prison-wall frescoes]
-
A.
hasFictionalWork
Indicates that one entity is the creator, owner, or source of a fictional work associated with another entity.
-
B.
hasFictionalCollector
Indicates that an entity is associated with a fictional character who collects or curates it.
-
C.
hasFictionalAuthor
Indicates that one entity is the fictional or in-universe author of a work attributed to them.
-
D.
hasFictionalContent
chosen
Indicates that something contains or includes material that is imaginary, invented, or not intended to represent real events or facts.
-
E.
hasFictionalDocument
Indicates that one entity possesses, is associated with, or includes a document that is fictional or exists only within an imagined or narrative context.
- 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_69f76de8b4c48190ae504b86185c474c |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ffc704e1e88190884928a6a5c55a87 |
completed | May 9, 2026, 11:45 p.m. |
| PD | Predicate disambiguation | batch_69ffc6b483d881908ad872e25fa6abc5 |
completed | May 9, 2026, 11:43 p.m. |
Created at: May 3, 2026, 4:03 p.m.