Triple
T36581401
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Святослав Шевчук |
E902404
|
entity |
| Predicate | місце народження |
P1
|
FINISHED |
| Object | м. Стрий, Львівська область, Україна |
—
|
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: м. Стрий, Львівська область, Україна | Statement: [Святослав Шевчук, місце народження, м. Стрий, Львівська область, Україна]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: місце народження Context triple: [Святослав Шевчук, місце народження, м. Стрий, Львівська область, Україна]
-
A.
placeOfBirth
chosen
Indicates the location where a person or other entity was born.
-
B.
birthPlaceAccordingTo
Indicates that an entity’s place of birth is given as a specific location according to a particular source or authority.
-
C.
creatorPlaceOfBirth
Indicates that the place specified is the location where the creator of an entity was born.
-
D.
namedAfterBirthPlace
Indicates that an entity is given a name derived from or based on the place where it was born.
-
E.
bodyPartFromWhichBorn
Indicates the specific body part of an entity from which another entity is born or emerges.
- 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.