Triple
T8137106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Constitution Day of Ukraine |
E189998
|
entity |
| Predicate | dayInYear |
P80885
|
FINISHED |
| Object | June 28 |
—
|
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: June 28 | Statement: [Constitution Day of Ukraine, dayInYear, June 28]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dayInYear Context triple: [Constitution Day of Ukraine, dayInYear, June 28]
-
A.
dayOfMonth
Indicates the specific calendar day number within a given month on which something occurs or is associated.
-
B.
dayRelativeToEaster
Indicates the temporal offset of a given day relative to the date of Easter in a specific year (e.g., days before or after Easter Sunday).
-
C.
dateDetermination
Indicates the process or criteria by which a specific date is identified, calculated, or assigned in relation to an event or condition.
-
D.
dayName
Indicates the specific name of the day of the week associated with a given date or time.
-
E.
dateInFrenchRepublicanCalendar
Indicates that a given date is expressed according to the French Republican (Revolutionary) calendar system rather than another calendar.
- 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_69ca82bd9900819099477cdc2eb4244f |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb440171d48190afa4a312ab19389c |
completed | March 31, 2026, 3:48 a.m. |
| PD | Predicate disambiguation | batch_69cb369c0d0481908762c488d7f77e74 |
completed | March 31, 2026, 2:51 a.m. |
| PDg | Predicate description generation | batch_69cb39d20e78819092ea9e04357be008 |
completed | March 31, 2026, 3:04 a.m. |
Created at: March 30, 2026, 5:35 p.m.