Triple
T18953947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cai Guo-Qiang: The Unmanned Nature |
E463723
|
entity |
| Predicate | focusesOnMedium |
P99187
|
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: The Unmanned Nature, focusesOnMedium, gunpowder]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: focusesOnMedium Context triple: [Cai Guo-Qiang: The Unmanned Nature, focusesOnMedium, gunpowder]
-
A.
focusesOn
Indicates that one entity directs its attention, effort, or primary activity toward another entity or specific subject.
-
B.
mediaFocus
Indicates that the primary attention, coverage, or emphasis of a media source is directed toward a particular entity or topic.
-
C.
featuredMedium
chosen
Indicates that one medium (such as an image, video, or other media item) is highlighted or designated as the primary or representative media for another entity.
-
D.
favoriteMedium
Indicates that one entity is the preferred or most liked medium (e.g., communication or artistic medium) of another entity.
-
E.
targetMedium
Indicates the medium or channel through which an action, message, or effect is directed or intended to be delivered.
- 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