Triple
T32203600
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ilie Verdeț |
E822610
|
entity |
| Predicate | wasSubordinateOf |
P258
|
FINISHED |
| Object | Nicolae Ceaușescu |
—
|
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: Nicolae Ceaușescu | Statement: [Ilie Verdeț, wasSubordinateOf, Nicolae Ceaușescu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasSubordinateOf Context triple: [Ilie Verdeț, wasSubordinateOf, Nicolae Ceaușescu]
-
A.
subordinateTo
chosen
Indicates that one entity holds a lower rank, status, or authority and is subject to the control, direction, or oversight of another entity.
-
B.
notSubordinateTo
Indicates that one entity is not in a lower-ranking, subordinate, or reporting position to another entity within a hierarchy or organizational structure.
-
C.
hasSubrole
Indicates that one role functions as a more specific, subordinate, or specialized version of another broader role.
-
D.
isChildOf
Indicates that one entity is the offspring or direct descendant of another entity.
-
E.
isFlankerOf
Indicates that one entity occupies or performs the role of a flanker in relation to another entity, typically providing support or coverage from the side.
- 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_69f349093174819086e633c190a51aa8 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6bb3dc9c881908fa012bef3704384 |
completed | May 3, 2026, 3:04 a.m. |
| PD | Predicate disambiguation | batch_69f6b3aa892481908d29283a074e6722 |
completed | May 3, 2026, 2:32 a.m. |
Created at: May 1, 2026, 12:36 a.m.