Triple
T27107734
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chandeliers |
E686624
|
entity |
| Predicate | dimensionConstraint |
P73084
|
FINISHED |
| Object | hung to allow head clearance |
—
|
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: hung to allow head clearance | Statement: [Chandeliers, dimensionConstraint, hung to allow head clearance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dimensionConstraint Context triple: [Chandeliers, dimensionConstraint, hung to allow head clearance]
-
A.
dimensionRestriction
chosen
Indicates a constraint or limit imposed on the size, extent, or number of dimensions associated with an entity or relationship.
-
B.
dimensionBoundType
Indicates the type or nature of the constraint that bounds a given dimension in a relationship.
-
C.
dimensionEquals
Indicates that two entities have exactly the same dimensional properties or measurements.
-
D.
dimensionType
Indicates the specific kind or category of dimension that characterizes how something is measured or structured.
-
E.
dimension
Indicates that one entity specifies a measurable extent or size attribute (such as length, width, height, or similar quantitative property) of another entity.
- 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_69ef148accd48190b6ed6e13a15f2a4f |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f623fef610819086a38b74d8c934b3 |
completed | May 2, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69f620e0b37481909a280574decbd443 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 8:51 a.m.