Triple
T1884760
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ionic order |
E39937
|
entity |
| Predicate | typicalProportion |
P16308
|
FINISHED |
| Object | column height about nine times column diameter |
—
|
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: column height about nine times column diameter | Statement: [Ionic order, typicalProportion, column height about nine times column diameter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalProportion Context triple: [Ionic order, typicalProportion, column height about nine times column diameter]
-
A.
officialProportion
Indicates the proportion or percentage of something as formally defined or reported by an official source or authority.
-
B.
hasProportion
chosen
Indicates that one entity stands in a specified ratio, fraction, or relative share to another entity or whole.
-
C.
typicalIn
Indicates that something commonly occurs, appears, or is found within a given context, category, or environment.
-
D.
isProportionalTo
Indicates that one quantity varies in constant ratio to another, so when one changes, the other changes by a fixed multiplicative factor.
-
E.
proportionalTo
Indicates that one quantity varies in constant ratio to another, so changes in one are directly reflected by proportional changes in the other.
- 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_69a88633e4fc8190b7eb40463e048ec5 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb4f53f408190ae30e1a12721e7d7 |
completed | March 7, 2026, 5:17 a.m. |
| PD | Predicate disambiguation | batch_69abafe497a88190a1da6af2888b71b4 |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:34 p.m.