Triple
T11879717
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Temple of Poseidon at Sounion |
E282623
|
entity |
| Predicate | numberOfColumnsStanding |
P15257
|
FINISHED |
| Object | 16 approximately |
—
|
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: 16 approximately | Statement: [Temple of Poseidon at Sounion, numberOfColumnsStanding, 16 approximately]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfColumnsStanding Context triple: [Temple of Poseidon at Sounion, numberOfColumnsStanding, 16 approximately]
-
A.
currentStandingColumns
Indicates that certain columns are presently active, visible, or in use within a given context or layout.
-
B.
numberOfStandingPlaces
Indicates the total count of standing-only positions or spots available in a given context (e.g., a vehicle, venue, or area).
-
C.
numberOfColumns
chosen
Indicates the total count of vertical divisions (columns) associated with or contained in a given structure or dataset.
-
D.
numberOfColumnsOnFlanks
Indicates the count of columns located on the flanking sides of a structure or object.
-
E.
numberOfColumnsPerShortSide
Indicates the count of columns that appear along each of the shorter sides of a rectangular or similarly shaped structure or layout.
- 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_69d6ab2945d081908a5851c916cbcfb5 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8d39d2934819093b9f7006f45e5cb |
completed | April 10, 2026, 10:40 a.m. |
| PD | Predicate disambiguation | batch_69d8bb272f88819090c37c944c5a60ab |
completed | April 10, 2026, 8:56 a.m. |
Created at: April 8, 2026, 9:44 p.m.