Triple
T11762674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Collection of Greek and Roman Antiquities |
E279695
|
entity |
| Predicate | includesObjectType |
P58911
|
FINISHED |
| Object | classical sculpture |
—
|
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: classical sculpture | Statement: [Collection of Greek and Roman Antiquities, includesObjectType, classical sculpture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesObjectType Context triple: [Collection of Greek and Roman Antiquities, includesObjectType, classical sculpture]
-
A.
includesTypeOfObject
chosen
Indicates that one entity contains or encompasses another entity that is a specific type or category of object.
-
B.
hasObjectTypes
Indicates that something is associated with one or more specific categories or types of objects.
-
C.
typicalObjectType
Indicates that something is a common or characteristic type of object typically associated with or involved in another entity or situation.
-
D.
includedEntityType
Indicates that one entity type is contained within, or forms a component part of, another entity type.
-
E.
hasObjectiveTypes
Indicates that an entity is associated with one or more specific types or categories of objectives it aims to achieve.
- 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_69d6ab01d2688190ad8ed6bda487eaa5 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a5248e0881909ed1b4df7be422f7 |
completed | April 10, 2026, 7:22 a.m. |
| PD | Predicate disambiguation | batch_69d88a829fe481909cc5431de7d6058e |
completed | April 10, 2026, 5:28 a.m. |
Created at: April 8, 2026, 9:41 p.m.