Triple
T19385772
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Akademik Lomonosov |
E484929
|
entity |
| Predicate | draft_m |
P136253
|
FINISHED |
| Object | about 5.6 |
—
|
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: about 5.6 | Statement: [Akademik Lomonosov, draft_m, about 5.6]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: draft_m Context triple: [Akademik Lomonosov, draft_m, about 5.6]
-
A.
draft
Indicates that one entity prepares an initial or preliminary version of something, typically a document, plan, or design, which may be revised later.
-
B.
draftApprox
Indicates an approximate or provisional drafting relationship, where one entity serves as a non-final or estimated draft version of another.
-
C.
draftApproximate
Indicates that one entity creates or selects a preliminary, non-final version of another entity, capturing an approximate or rough form rather than a precise or completed one.
-
D.
draftFocus
Indicates that attention or priority is temporarily directed toward preparing or refining a draft version of something.
-
E.
draftSystem
Indicates a system or mechanism responsible for selecting, assigning, or organizing individuals for compulsory service, typically in a military or similar structured context.
- F. None of above. chosen
Provenance (4 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_69d8e8d460d88190abf0591c5c9d2b0c |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61b40d1148190b4fcd9ad56aa6910 |
completed | April 20, 2026, 12:25 p.m. |
| PD | Predicate disambiguation | batch_69e4fd602f008190aa9bc76ae17e4ce1 |
completed | April 19, 2026, 4:05 p.m. |
| PDg | Predicate description generation | batch_69e50213571881909cd7543a43b51986 |
completed | April 19, 2026, 4:25 p.m. |
Created at: April 10, 2026, 1:35 p.m.