Triple
T36214912
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Pasternak Family |
E1047662
|
entity |
| Predicate | creatorFatherOfDepicted |
P79451
|
FINISHED |
| Object | Leonid Pasternak – father of Boris Pasternak |
—
|
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: Leonid Pasternak – father of Boris Pasternak | Statement: [The Pasternak Family, creatorFatherOfDepicted, Leonid Pasternak – father of Boris Pasternak]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: creatorFatherOfDepicted Context triple: [The Pasternak Family, creatorFatherOfDepicted, Leonid Pasternak – father of Boris Pasternak]
-
A.
creatorFather
Indicates that one entity is the male parent (father) who created, generated, or brought into existence the other entity.
-
B.
fatherWas
chosen
Indicates that one entity was the male parent (father) of another entity in the past.
-
C.
fatherFrom
Indicates a parental relationship where one entity is the biological or legal father of another entity.
-
D.
fatherAlsoKnownAs
Indicates that a person’s father is known or referred to by an alternative name or alias.
-
E.
forefatherOf
Indicates that one person is an ancestor, typically from an earlier generation, of another person.
- 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_69f76e4214748190a76c986d2a1838c2 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff956dc6548190979171d4b4068d47 |
completed | May 9, 2026, 8:13 p.m. |
| PD | Predicate disambiguation | batch_69ff93dc39c481908a97a12c3ef7dfe7 |
completed | May 9, 2026, 8:06 p.m. |
Created at: May 3, 2026, 4:09 p.m.