Triple
T8923199
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stephanus pagination |
E212474
|
entity |
| Predicate | sectionLetters |
P11608
|
FINISHED |
| Object | subdivisions of each Stephanus page |
—
|
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: subdivisions of each Stephanus page | Statement: [Stephanus pagination, sectionLetters, subdivisions of each Stephanus page]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sectionLetters Context triple: [Stephanus pagination, sectionLetters, subdivisions of each Stephanus page]
-
A.
letterSequence
Indicates that one sequence of letters directly follows or is ordered in relation to another within a larger string or alphabetic arrangement.
-
B.
letterGroups
chosen
Indicates that entities are organized or associated into specific groups based on letters or letter-based criteria.
-
C.
rootLetters
Indicates that one element specifies the fundamental root letters from which another linguistic form is derived.
-
D.
sectionType
Indicates the specific kind or category of section that an entity belongs to or represents.
-
E.
routeLetter
Indicates the action or process of directing or sending a letter along a specific path or through designated channels to its intended destination.
- 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_69ca839481d48190b42b037e0d0f636c |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6652d63881908821c8735984322a |
completed | April 1, 2026, 12:26 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed0ef3c81908cc69eac852ee12a |
completed | March 31, 2026, 11:54 p.m. |
Created at: March 30, 2026, 6:56 p.m.