Triple
T8205897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adeimantus |
E191685
|
entity |
| Predicate | appearsInBookOfRepublic |
P75974
|
FINISHED |
| Object | Book II |
—
|
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: Book II | Statement: [Adeimantus, appearsInBookOfRepublic, Book II]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appearsInBookOfRepublic Context triple: [Adeimantus, appearsInBookOfRepublic, Book II]
-
A.
introducedInRepublic
Indicates that something (such as a concept, character, or idea) first appears or is presented in Plato's dialogue "Republic."
-
B.
appearsIn
Indicates that an entity is present, featured, or occurs within a particular context, work, or medium.
-
C.
includedInBook
chosen
Indicates that something (such as a section, chapter, or content item) is contained within or forms part of a specific book.
-
D.
characterizesRepublicAs
Indicates that one entity defines, describes, or portrays a particular republic as having certain qualities, attributes, or a specific nature.
-
E.
appearsInPublication
Indicates that an entity is featured, mentioned, or discussed within a specific publication.
- 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_69ca82c7f3e08190857bf1fc63b2a10c |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb726a301c8190a4b2d3d184b7e448 |
completed | March 31, 2026, 7:06 a.m. |
| PD | Predicate disambiguation | batch_69cb36ad01ac81909609b15f6a6c8581 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:43 p.m.