Triple
T21783844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | On Divisions of Figures |
E537784
|
entity |
| Predicate | studiesFigureType |
P143446
|
FINISHED |
| Object | triangles |
—
|
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: triangles | Statement: [On Divisions of Figures, studiesFigureType, triangles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: studiesFigureType Context triple: [On Divisions of Figures, studiesFigureType, triangles]
-
A.
studyType
Indicates the kind or category of study or research methodology associated with an entity or activity.
-
B.
includesFigureType
Indicates that one entity contains or encompasses a specific type or category of figure within it.
-
C.
studiesFeature
chosen
Indicates that an entity conducts research or examination on a particular feature or characteristic of something.
-
D.
figureType
Indicates that one entity is classified as a specific type or category of figure in relation to another entity.
-
E.
discussesFigure
Indicates that one entity engages in discussion or analysis specifically about a particular figure (such as a person, character, or notable individual).
- 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_69e0c47198f881908cb0d237266c10e9 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f046303d54819096b3fab4ab5678e6 |
completed | April 28, 2026, 5:31 a.m. |
| PD | Predicate disambiguation | batch_69e6be6299988190a34c98fa76d94700 |
completed | April 21, 2026, 12:01 a.m. |
Created at: April 16, 2026, 6:52 p.m.