Triple
T28950279
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tatiana Navka / Roman Kostomarov |
E730992
|
entity |
| Predicate | partnershipEnded |
P99605
|
FINISHED |
| Object | mid-2000s |
—
|
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: mid-2000s | Statement: [Tatiana Navka / Roman Kostomarov, partnershipEnded, mid-2000s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partnershipEnded Context triple: [Tatiana Navka / Roman Kostomarov, partnershipEnded, mid-2000s]
-
A.
endedPartnershipWith
chosen
Indicates that a previously existing partnership or collaborative relationship between two entities has been terminated.
-
B.
sponsorshipEndedWith
Indicates that a previously existing sponsorship relationship between entities has come to an end.
-
C.
sponsorshipEnded
Indicates that a previously existing sponsorship relationship between entities has been terminated or has come to an end.
-
D.
affiliationEndedWith
Indicates that a previously existing affiliation or association between entities has come to an end at a specific point in time or under certain conditions.
-
E.
partnerInEndingWith
Indicates that an entity participates as a partner in an event, process, or relationship that concludes with a specified outcome or terminal state.
- 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_69f043eb9bcc819091ac7b07aecb6475 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f6978fe97081908fe568091ad9b159 |
completed | May 3, 2026, 12:32 a.m. |
| PD | Predicate disambiguation | batch_69f69661e6ec8190948251c7516a32ad |
completed | May 3, 2026, 12:27 a.m. |
Created at: April 28, 2026, 8:43 a.m.