Triple
T9101572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | «На дне» |
E218169
|
entity |
| Predicate | основная тема |
P12980
|
FINISHED |
| Object | жизнь обитателей ночлежки |
—
|
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: жизнь обитателей ночлежки | Statement: [«На дне», основная тема, жизнь обитателей ночлежки]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: основная тема Context triple: [«На дне», основная тема, жизнь обитателей ночлежки]
-
A.
primaryTopicOf
chosen
Indicates that a given subject is the main or central topic described by another resource (such as a document, page, or record).
-
B.
theme
Indicates the entity that is the primary participant or content affected or characterized by an action, event, or state.
-
C.
thematicConcept
Indicates that one entity embodies, expresses, or is centrally concerned with a particular underlying theme or conceptual idea represented by the other entity.
-
D.
primaryConcept
Indicates that one concept is the main or central idea in relation to another concept or context.
-
E.
primaryIssue
Indicates that the related item is the main or most important issue among a set of issues.
- 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_69ca83d9844081908e561e367fda6d45 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc971435d08190b5007ed44ac0a364 |
completed | April 1, 2026, 3:55 a.m. |
| PD | Predicate disambiguation | batch_69cc65fc7f408190a5846e29ab3b97e5 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:15 p.m.