Triple
T20535767
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cai Guo-Qiang: Writing with Gunpowder |
E504193
|
entity |
| Predicate | subjectSpecialization |
P140458
|
FINISHED |
| Object | gunpowder 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: gunpowder art | Statement: [Cai Guo-Qiang: Writing with Gunpowder, subjectSpecialization, gunpowder art]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subjectSpecialization Context triple: [Cai Guo-Qiang: Writing with Gunpowder, subjectSpecialization, gunpowder art]
-
A.
laterSpecializedIn
Indicates that an entity initially engaged in a broader or different field and subsequently focused its work or expertise in a more specific or specialized area.
-
B.
labelSpecialization
Indicates that one label is a more specific or specialized version of another label within a labeling or classification system.
-
C.
subDisciplineOf
Indicates that one discipline is a more specialized or narrower field within another, broader discipline.
-
D.
subjectGroup
Indicates that an entity functions as a group or collection that the subject belongs to or is categorized under.
-
E.
positionSpecialization
Indicates that one position is a more specialized or focused variant of another, broader position.
- 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_69e0b4b476648190bc6019622ae54d3c |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a06ed3088190bd01a95672b01ad6 |
completed | April 20, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69e59fe5592c8190bb6122b784496d02 |
completed | April 20, 2026, 3:39 a.m. |
| PDg | Predicate description generation | batch_69e5a6a824748190bbe6192d73f3c613 |
completed | April 20, 2026, 4:08 a.m. |
Created at: April 16, 2026, 11:37 a.m.