Triple
T29472683
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Семнадцать мгновений весны |
E747553
|
entity |
| Predicate | композиторПесен |
P150140
|
FINISHED |
| Object | Микаэл Таривердиев |
—
|
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: Микаэл Таривердиев | Statement: [Семнадцать мгновений весны, композиторПесен, Микаэл Таривердиев]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: композиторПесен Context triple: [Семнадцать мгновений весны, композиторПесен, Микаэл Таривердиев]
-
A.
stateSongComposer
Indicates that a person is the composer of the official song of a particular state.
-
B.
titleSongComposer
Indicates that one entity is the composer of the title song associated with another entity (such as a film, show, or album).
-
C.
hasMusicalComposer
Indicates that one entity serves as the musical composer responsible for creating the music associated with another entity.
-
D.
composerOfSongsInWork
chosen
Indicates that one entity is the composer of the songs contained within a particular work (such as a film, play, or album).
-
E.
composerOfOriginalSongs
Indicates that one entity is the composer who created the original songs associated with another entity.
- 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_69f0bd42cf308190bb01b20bc5b7c2d0 |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f66bd2451c8190ad14604068f308d8 |
completed | May 2, 2026, 9:25 p.m. |
| PD | Predicate disambiguation | batch_69f66339175c819080bd70f0ff7057b1 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 3:58 p.m.