Triple
T19169002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cai Guo-Qiang: Yuz Museum Retrospective |
E469263
|
entity |
| Predicate | mediumCovered |
P85587
|
FINISHED |
| Object | gunpowder |
—
|
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 | Statement: [Cai Guo-Qiang: Yuz Museum Retrospective, mediumCovered, gunpowder]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mediumCovered Context triple: [Cai Guo-Qiang: Yuz Museum Retrospective, mediumCovered, gunpowder]
-
A.
mediumAppearance
Indicates that an entity appears in or is featured within a particular medium (such as a work, format, or communication channel).
-
B.
mediumIncludes
chosen
Indicates that a given medium contains, encompasses, or incorporates another item, component, or element within it.
-
C.
mediumDisplayed
Indicates that a particular medium (such as an image, video, or document) is being shown or rendered in a given context or interface.
-
D.
mediumAdaptedTo
Indicates that a medium (such as a format, channel, or platform) has been specifically adjusted or tailored to suit a particular use, context, or target.
-
E.
medium
Indicates that an entity serves as the means, channel, or intermediary through which an action, communication, or effect is carried out between other entities.
- 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_69d8dd09d5a081909ae43c286651ae5a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f162ac648190a5f60c6a77b68304 |
completed | April 20, 2026, 9:26 a.m. |
| PD | Predicate disambiguation | batch_69e4b9b83d6881908e6271c620f74100 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:06 p.m.