Triple
T7297667
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ad astra per aspera |
E164564
|
entity |
| Predicate | grammaticalCaseOfAstra |
P13618
|
FINISHED |
| Object | accusative |
—
|
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: accusative | Statement: [Ad astra per aspera, grammaticalCaseOfAstra, accusative]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: grammaticalCaseOfAstra Context triple: [Ad astra per aspera, grammaticalCaseOfAstra, accusative]
-
A.
numberOfGrammaticalCases
Indicates the relationship that specifies how many distinct grammatical cases a language or linguistic system possesses.
-
B.
positionInAsterism
Indicates the specific location or role that an object occupies within a defined asterism pattern.
-
C.
isAsterismOf
Indicates that one or more stars collectively form or belong to a specific asterism.
-
D.
hasCaseForms
chosen
Indicates that an entity possesses multiple grammatical case variants or inflected forms associated with it.
-
E.
astronomicalBasis
Indicates that one entity serves as the astronomical foundation, reference, or underlying celestial cause for another entity or phenomenon.
- 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_69c6887a499881909dd23341399c59d8 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6eb8f83c881909e8eae85410f9659 |
completed | March 27, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69c6e76e67d88190bd3ca6864f45845a |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 3 p.m.