Triple
T727089
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1st Ukrainian Front |
E14749
|
entity |
| Predicate | frontNumbering |
P19365
|
FINISHED |
| Object | first Ukrainian front-level formation of the Red Army |
—
|
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: first Ukrainian front-level formation of the Red Army | Statement: [1st Ukrainian Front, frontNumbering, first Ukrainian front-level formation of the Red Army]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frontNumbering Context triple: [1st Ukrainian Front, frontNumbering, first Ukrainian front-level formation of the Red Army]
-
A.
frontType
Indicates the type or category of a front (e.g., boundary or leading side) that one entity presents or forms relative to another.
-
B.
numberingType
Indicates the scheme or style used to assign sequential numbers or labels within an ordered set.
-
C.
frontAssignment
Indicates that one entity is assigned or positioned at the front relative to another entity or context.
-
D.
titleNumber
Indicates the numerical designation or sequence number assigned to a title within an ordered set of titles.
-
E.
serialNumber
Indicates a unique identifying code assigned to an individual item or instance within a series or batch.
- 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_69a4934c753c81909b309027e48b9b3a |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a64adf2c81908e48090be35dd9d9 |
completed | March 1, 2026, 8:49 p.m. |
| PD | Predicate disambiguation | batch_69a4a4f839608190878a60eb7a044ed9 |
completed | March 1, 2026, 8:43 p.m. |
| PDg | Predicate description generation | batch_69a4a64957ec81909fe2e2dbffd80ed3 |
completed | March 1, 2026, 8:49 p.m. |
Created at: March 1, 2026, 7:37 p.m.