Triple
T34622618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gracie Watson |
E889045
|
entity |
| Predicate | memorialStyle |
P180191
|
FINISHED |
| Object | Victorian-era funerary art |
—
|
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: Victorian-era funerary art | Statement: [Gracie Watson, memorialStyle, Victorian-era funerary art]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: memorialStyle Context triple: [Gracie Watson, memorialStyle, Victorian-era funerary art]
-
A.
memorialType
Indicates the specific kind or category of memorial associated with an entity (e.g., plaque, statue, monument).
-
B.
memorialTheme
Indicates that something (such as a work, event, or object) is dedicated to remembering, honoring, or commemorating a person, group, or event.
-
C.
memorialWork
Indicates that one entity is a commemorative work (such as a monument, plaque, or artwork) created to honor or remember another entity.
-
D.
memorialization
Indicates the act of preserving the memory or honoring the legacy of someone or something, often through a dedicated object, event, or practice.
-
E.
hasMemorial
Indicates that a memorial exists in honor of, or dedicated to, a particular entity.
- 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_69f349d64a388190a013cfa9bd33fad7 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f73397e5488190a9cdce98a0ac0383 |
completed | May 3, 2026, 11:38 a.m. |
| PD | Predicate disambiguation | batch_69f732f3ad248190b4bcbf589d000f0d |
completed | May 3, 2026, 11:35 a.m. |
| PDg | Predicate description generation | batch_69f733970ab48190888f282712a77d4c |
completed | May 3, 2026, 11:37 a.m. |
Created at: May 1, 2026, 2:04 a.m.