Triple
T25068392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Five Suns |
E627843
|
entity |
| Predicate | recordsPreservedIn |
P2249
|
FINISHED |
| Object | Codex Vaticanus A |
—
|
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: Codex Vaticanus A | Statement: [Five Suns, recordsPreservedIn, Codex Vaticanus A]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recordsPreservedIn Context triple: [Five Suns, recordsPreservedIn, Codex Vaticanus A]
-
A.
preservedFor
Indicates that something has been kept intact or maintained in a particular state for the benefit, use, or reference of a specified entity or purpose.
-
B.
recordsWith
Indicates that one entity keeps or maintains documented information about another entity or event.
-
C.
preservedAsPartOf
Indicates that something has been kept, maintained, or conserved within a larger whole of which it forms a component or subset.
-
D.
preservedAt
chosen
Indicates that something is kept, maintained, or conserved in a particular place or context.
-
E.
preservedFrom
Indicates that something has been protected or kept safe from a particular source of damage, loss, or alteration.
- 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_69e2ff2d71dc8190b4758e57d643cbe4 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f497bc12b881908fe3386c66252bf6 |
completed | May 1, 2026, 12:08 p.m. |
| PD | Predicate disambiguation | batch_69f49366e8d08190adb4b71fe3a14683 |
completed | May 1, 2026, 11:49 a.m. |
Created at: April 18, 2026, 6:10 a.m.