Triple
T16232422
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pyrgi |
E394015
|
entity |
| Predicate | PyrgiTabletsFunction |
P122258
|
FINISHED |
| Object | votive dedication |
—
|
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: votive dedication | Statement: [Pyrgi, PyrgiTabletsFunction, votive dedication]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: PyrgiTabletsFunction Context triple: [Pyrgi, PyrgiTabletsFunction, votive dedication]
-
A.
pyramidTextInscriptions
Indicates that the subject has text inscriptions located on or within a pyramid.
-
B.
pyramidExcavator
Indicates a relationship where an entity performs excavation work on or within a pyramid.
-
C.
hasMemorialTabletsFor
Indicates that one entity contains or displays memorial tablets dedicated to another entity.
-
D.
nameInHieroglyphs
Indicates that an entity’s name is written or represented using hieroglyphic script.
-
E.
EgyptianVersionInscribedOn
Indicates that an Egyptian-language version of a text or inscription is carved or written onto a particular physical object or surface.
- 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_69d87f204df88190a8f88923decf9835 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e23d2b0cc48190853919135d5a172a |
completed | April 17, 2026, 2:01 p.m. |
| PD | Predicate disambiguation | batch_69e219ee6f6481909663b388dc99770a |
completed | April 17, 2026, 11:30 a.m. |
| PDg | Predicate description generation | batch_69e21e55a2388190b29a045a8c608ba4 |
completed | April 17, 2026, 11:49 a.m. |
Created at: April 10, 2026, 5:04 a.m.