Triple
T1044145
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moscow Exchange |
E22536
|
entity |
| Predicate | offersTradingHours |
P2917
|
FINISHED |
| Object | regular trading sessions |
—
|
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: regular trading sessions | Statement: [Moscow Exchange, offersTradingHours, regular trading sessions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offersTradingHours Context triple: [Moscow Exchange, offersTradingHours, regular trading sessions]
-
A.
hasTradingHours
chosen
Indicates that an entity operates or is available for trading during specified time periods.
-
B.
tradingHoursType
Indicates the classification of an entity’s trading hours, such as whether they are regular, extended, holiday-specific, or of another defined type.
-
C.
hoursOfOperation
Indicates the time periods during which a place or service is open and available for use.
-
D.
openingHoursCharacteristic
Indicates a relationship that specifies particular attributes or features of an entity’s opening hours, such as patterns, exceptions, or special conditions.
-
E.
hasPreMarketSession
Indicates that a financial instrument or market has a designated trading session that occurs before the regular market hours.
- 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_69a493d91478819094cc01fb65564bc1 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b8475ab48190848388eea6448cb6 |
completed | March 1, 2026, 10:05 p.m. |
| PD | Predicate disambiguation | batch_69a4b72ba60881908b017ef3b2b9645e |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:42 p.m.