Triple
T31470927
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Department of Sculpture |
E802856
|
entity |
| Predicate | hasStudyArea |
P934
|
FINISHED |
| Object | figurative 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: figurative sculpture | Statement: [Department of Sculpture, hasStudyArea, figurative sculpture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStudyArea Context triple: [Department of Sculpture, hasStudyArea, figurative sculpture]
-
A.
hasStudyAreaType
Indicates that an entity’s study area is classified as a specific type or category (e.g., lab, field site, classroom).
-
B.
hasResearchArea
chosen
Indicates that an entity (such as a person, project, or organization) is associated with or focused on a particular field or area of research.
-
C.
studiedWithin
Indicates that one entity pursued studies or academic work within the scope, context, or boundaries defined by another entity (such as an institution, program, or field).
-
D.
jurisdictionOfStudy
Indicates the legal or geographic jurisdiction within which a given study is conducted or governed.
-
E.
hasStudied
Indicates that an entity has engaged in learning or academic work related to another entity (such as a subject, field, or course).
- 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_69f348c84c1c81908739f100ecf7394e |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69feb5e66224819083b87c3707a5a5e0 |
completed | May 9, 2026, 4:19 a.m. |
| PD | Predicate disambiguation | batch_69feb3bd700c8190991ed200cd3c04db |
completed | May 9, 2026, 4:10 a.m. |
Created at: April 30, 2026, 9:26 p.m.