Triple
T809434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Propylaea |
E17510
|
entity |
| Predicate | hasColumnArrangement |
P13119
|
FINISHED |
| Object | six Doric columns on the west front |
—
|
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: six Doric columns on the west front | Statement: [Propylaea, hasColumnArrangement, six Doric columns on the west front]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasColumnArrangement Context triple: [Propylaea, hasColumnArrangement, six Doric columns on the west front]
-
A.
hasColumnCountBack
Indicates that an entity (such as a table or layout) has a specified number of columns on its back side or rear-facing section.
-
B.
hasColumns
chosen
Indicates that one entity possesses or is characterized by a set of columns associated with it.
-
C.
hasArrangement
Indicates that one entity possesses, follows, or is organized according to a particular configuration, setup, or ordering defined by another entity.
-
D.
columnOrder
Indicates the relative sequencing or arrangement of columns within a structured layout or dataset.
-
E.
numberOfColumns
Indicates the total count of vertical divisions (columns) associated with or contained in a given structure or dataset.
- 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_69a4937ae8a08190b5084a03d532b30e |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4ac07fedc8190ab05595f25c1792f |
completed | March 1, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69a4aa7221c081908068e66fe720f26d |
completed | March 1, 2026, 9:06 p.m. |
Created at: March 1, 2026, 7:38 p.m.