Triple
T36581414
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Святослав Шевчук |
E902404
|
entity |
| Predicate | попередник на посаді Глави УГКЦ |
P107970
|
FINISHED |
| Object | Любомир Гузар |
—
|
NE NERFINISHED |
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: Любомир Гузар | Statement: [Святослав Шевчук, попередник на посаді Глави УГКЦ, Любомир Гузар]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: попередник на посаді Глави УГКЦ Context triple: [Святослав Шевчук, попередник на посаді Глави УГКЦ, Любомир Гузар]
-
A.
predecessorAsMajorArchbishop
chosen
Indicates that one individual previously held the position of Major Archbishop immediately before the current holder.
-
B.
predecessorChairpersonModel
Indicates that one entity served as the chairperson immediately before another entity in a sequence of chairperson roles.
-
C.
roleOfLeonidKravchuk
Indicates the official position, capacity, or function held by Leonid Kravchuk in a given context.
-
D.
predecessorHeadOfStateRepresentative
Indicates that one entity previously served as the head-of-state representative immediately before the other entity in a given office or role.
-
E.
predecessorAsChiefStrategist
Indicates that one entity previously held the role of chief strategist before another entity in a sequence of officeholders.
- 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_69f76e64d8908190868473959a250b94 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c371931c8190afb1d4dd5157f92c |
completed | May 3, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69f7c1baf25c8190a78dd54a400d2c50 |
completed | May 3, 2026, 9:44 p.m. |
Created at: May 3, 2026, 4:11 p.m.