Triple
T18954044
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cai Guo-Qiang: Works 1985–2010 |
E463725
|
entity |
| Predicate | documentsTechnique |
P63260
|
FINISHED |
| Object | use of gunpowder in 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: use of gunpowder in art | Statement: [Cai Guo-Qiang: Works 1985–2010, documentsTechnique, use of gunpowder in art]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: documentsTechnique Context triple: [Cai Guo-Qiang: Works 1985–2010, documentsTechnique, use of gunpowder in art]
-
A.
featuresTechnique
Indicates that something incorporates or makes use of a particular technique as part of its content or execution.
-
B.
hasTechnique
Indicates that an entity employs, utilizes, or is associated with a particular method, procedure, or technique.
-
C.
allowedTechnique
Indicates that a particular technique or method is permitted or acceptable to use in a given context or under specified rules.
-
D.
documentsMethod
chosen
Indicates that one entity provides documentation or descriptive information about the method represented by the other entity.
-
E.
coversTechnique
Indicates that one entity includes, addresses, or explains a particular technique within its scope or content.
- 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_69d8dcffc278819086792a4ebfddfafa |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d545f47881909110e6a92e86b384 |
completed | April 20, 2026, 7:27 a.m. |
| PD | Predicate disambiguation | batch_69e4a2efec5c8190840704016bf547a1 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, noon