Triple
T38164840
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edgeworth box |
E953115
|
entity |
| Predicate | visualDimension |
P50437
|
FINISHED |
| Object | two-dimensional diagram |
—
|
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: two-dimensional diagram | Statement: [Edgeworth box, visualDimension, two-dimensional diagram]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: visualDimension Context triple: [Edgeworth box, visualDimension, two-dimensional diagram]
-
A.
dimensionVariant
Indicates a relationship where one entity is a variant or alternative version of another with respect to certain dimensions or configurable attributes.
-
B.
dimensionAvailability
Indicates that a particular dimension or measurement is currently accessible, usable, or provided within a given context or system.
-
C.
dimensionCharacteristic
chosen
Indicates that one entity specifies or describes a dimensional property or measurement characteristic of another entity.
-
D.
dimensionType
Indicates the specific kind or category of dimension that characterizes how something is measured or structured.
-
E.
dimensionStatus
Indicates the current state or condition of a given dimension (such as whether it is active, valid, complete, or in a particular lifecycle phase).
- 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_69f76f0b93c48190a117319ab3a9f282 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fcb089a8f881909aa9e722babd43f7 |
completed | May 7, 2026, 3:32 p.m. |
| PD | Predicate disambiguation | batch_69fc45666c5c8190913bd632ac0e5b84 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:21 p.m.