Triple
T15223224
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soviet Pavilion (1937 Paris Exposition) |
E363812
|
entity |
| Predicate | materialOfMainSculpture |
P1272
|
FINISHED |
| Object | stainless steel |
—
|
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: stainless steel | Statement: [Soviet Pavilion (1937 Paris Exposition), materialOfMainSculpture, stainless steel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: materialOfMainSculpture Context triple: [Soviet Pavilion (1937 Paris Exposition), materialOfMainSculpture, stainless steel]
-
A.
statueMaterialDetail
Indicates that a statue is made of, or incorporates, a specific material with detailed characterization (e.g., type, composition, or quality).
-
B.
materialUsed
chosen
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
-
C.
artStyleOfEnclosingSculpture
Indicates that one entity specifies the artistic style or aesthetic category of a surrounding or enclosing sculpture associated with another entity.
-
D.
featuresSculptureOf
Indicates that one entity includes or displays a sculpture that depicts or represents another entity.
-
E.
materialDepicted
Indicates that a work or representation visually portrays or includes a particular material as part of its subject.
- 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_69d85a0ce24c81909c4d3b6475548c95 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0078a9318819081db3b7bcc28e04f |
completed | April 15, 2026, 9:47 p.m. |
| PD | Predicate disambiguation | batch_69deca8479188190b2e5d3bc708d7d07 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:12 a.m.