Triple
T7083244
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Black Hole of Calcutta |
E165007
|
entity |
| Predicate | cellDimensions |
P67473
|
FINISHED |
| Object | about 14 feet by 18 feet |
—
|
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: about 14 feet by 18 feet | Statement: [Black Hole of Calcutta, cellDimensions, about 14 feet by 18 feet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cellDimensions Context triple: [Black Hole of Calcutta, cellDimensions, about 14 feet by 18 feet]
-
A.
cellSize
Indicates the physical dimensions or volume of a cell in a biological or computational context.
-
B.
characterCellResolution
Indicates a relationship where the visual or logical representation of characters is determined or adjusted at the level of individual cells (e.g., grid units or display slots).
-
C.
dimensionOfComponents
Indicates that a specified dimension value is associated with, or applies to, the components of an object or system.
-
D.
typicalDimension
chosen
Indicates that one entity represents a standard or characteristic measurement (such as size, length, or capacity) typically associated with another entity.
-
E.
cellType
Indicates the classification relationship that specifies what type of cell an entity is or is associated with.
- 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_69c6887d98408190912b9580666b0c1d |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e5102be08190bbde790bfa8fe9e2 |
completed | March 27, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69c6e1bfcb948190a5ada74fb8c054cb |
completed | March 27, 2026, 8 p.m. |
Created at: March 27, 2026, 2:40 p.m.