Triple
T38355297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | State Prize of Ukraine in Science and Technology |
E1046309
|
entity |
| Predicate | countryAwardedIn |
P204614
|
FINISHED |
| Object | Ukraine |
E14078
|
NE 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: Ukraine | Statement: [State Prize of Ukraine in Science and Technology, countryAwardedIn, Ukraine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryAwardedIn Context triple: [State Prize of Ukraine in Science and Technology, countryAwardedIn, Ukraine]
-
A.
musicAwardedTo
Indicates that a music-related award has been given to a particular recipient.
-
B.
albumAwardedTo
Indicates that a particular album has been granted or assigned to a specific recipient, such as an artist or group.
-
C.
topCountryArtistWinner
Indicates that the subject is the artist who won the top country artist award in the specified context or event.
-
D.
winnerArtist
Indicates that an artist is the winner of a particular contest, award, or competitive event.
-
E.
recordOfTheYearWinnerArtist
Indicates the artist who won the Record of the Year award for a given recording or year.
- F. None of above. chosen
Provenance (5 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_69f76e3a94fc81908edc175e8d259e80 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037cae084081909004d77514c5f286 |
completed | May 12, 2026, 7:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a41a7e16aac8190815325f6d200f8c9 |
completed | June 28, 2026, 11:01 p.m. |
| PD | Predicate disambiguation | batch_6a037a1c850c819088795a7ae59bdeb8 |
completed | May 12, 2026, 7:06 p.m. |
| PDg | Predicate description generation | batch_6a037c84ecbc81908232e5215355f43b |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 3, 2026, 4:31 p.m.