Triple
T30208678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tuscan column |
E768006
|
entity |
| Predicate | foundInTreatise |
P193307
|
FINISHED |
| Object | The Ten Books on Architecture |
—
|
NE NERFINISHED |
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: The Ten Books on Architecture | Statement: [Tuscan column, foundInTreatise, The Ten Books on Architecture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foundInTreatise Context triple: [Tuscan column, foundInTreatise, The Ten Books on Architecture]
-
A.
foundInRite
Indicates that something (such as an element, object, or action) occurs within, is used in, or is otherwise present as part of a specific rite or ritual.
-
B.
foundInCodexWith
Indicates that one entity is documented together with another entity within the same codex or manuscript.
-
C.
foundInChapter
Indicates that something (such as a concept, section, or element) is contained within or occurs in a specific chapter.
-
D.
foundInParva
Indicates that one entity is contained or located within a smaller subdivision or section (a "parva") of another entity.
-
E.
foundInMushaf
Indicates that something (such as a verse, phrase, or reading) is present and recorded in the written text of the Mushaf (the compiled Qur’anic codex).
- F. None of above. chosen
Provenance (4 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_69f2247eb0848190b4032f302d39c0d9 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fd4129a8848190a5002150278ac689 |
completed | May 8, 2026, 1:49 a.m. |
| PD | Predicate disambiguation | batch_69fd3e0515ec8190937c7af71ebc3875 |
completed | May 8, 2026, 1:36 a.m. |
| PDg | Predicate description generation | batch_69fd4128ed908190837ec9936774a1cf |
completed | May 8, 2026, 1:49 a.m. |
Created at: April 29, 2026, 7:32 p.m.