Triple
T29641453
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman Kiosk at Naqa |
E755870
|
entity |
| Predicate | hasColumnOrderContext |
P24192
|
FINISHED |
| Object | mixed classical and local forms |
—
|
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: mixed classical and local forms | Statement: [Roman Kiosk at Naqa, hasColumnOrderContext, mixed classical and local forms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasColumnOrderContext Context triple: [Roman Kiosk at Naqa, hasColumnOrderContext, mixed classical and local forms]
-
A.
hasColumnOrder
chosen
Indicates that one column in a sequence is positioned before or after another column, specifying their relative ordering.
-
B.
columnOrderUsed
Indicates that a specific ordering of columns is applied or relied upon in a given context or operation.
-
C.
hasElementOrder
Indicates that one entity is ordered or ranked relative to another within a sequence or hierarchy.
-
D.
hasCanonicalOrdering
Indicates that there is a standard, agreed-upon sequence in which the related elements should be arranged or considered.
-
E.
hasOrderStructure
Indicates that there is a defined ordering relation imposed on the elements of a set or collection, specifying how they are arranged or compared in terms of order.
- 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_69f0ef89d2c88190a6d0d5116ccd7cc9 |
completed | April 28, 2026, 5:34 p.m. |
| NER | Named-entity recognition | batch_6a00868083b081909afc3d8d4ad56b43 |
completed | May 10, 2026, 1:22 p.m. |
| PD | Predicate disambiguation | batch_6a0084f5f72c8190b08afa82690e322a |
completed | May 10, 2026, 1:15 p.m. |
Created at: April 28, 2026, 6:47 p.m.