Triple
T26034372
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Panagia Platytera |
E647512
|
entity |
| Predicate | inscriptionOftenIncludes |
P27535
|
FINISHED |
| Object | Platytera ton Ouranon |
—
|
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: Platytera ton Ouranon | Statement: [Panagia Platytera, inscriptionOftenIncludes, Platytera ton Ouranon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inscriptionOftenIncludes Context triple: [Panagia Platytera, inscriptionOftenIncludes, Platytera ton Ouranon]
-
A.
inscriptionBy
Indicates that an inscription was created, written, or carved by a particular agent or entity.
-
B.
inscription
Indicates that text has been written, carved, or engraved onto a surface or object.
-
C.
inscriptionSupport
Indicates that one entity serves as the physical surface or material on which another entity (an inscription) is written, carved, or otherwise recorded.
-
D.
inscriptionMentions
chosen
Indicates that the content of an inscription refers to, names, or otherwise mentions a particular entity.
-
E.
inscriptionStatus
Indicates the current state or condition of an inscription, such as whether it has been created, verified, updated, or removed.
- 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_69e77e8b60e88190a3b26c4f0032a2c2 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f6061bfb248190af47ba49de93abfc |
completed | May 2, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69f5aff889988190ad10bcf1a280f717 |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 22, 2026, 9:06 a.m.