Triple
T27271253
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anna Komorowska |
E688056
|
entity |
| Predicate | publicRoleDuring |
P181308
|
FINISHED |
| Object | Presidency of Bronisław Komorowski |
—
|
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: Presidency of Bronisław Komorowski | Statement: [Anna Komorowska, publicRoleDuring, Presidency of Bronisław Komorowski]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: publicRoleDuring Context triple: [Anna Komorowska, publicRoleDuring, Presidency of Bronisław Komorowski]
-
A.
representedRole
Indicates that one entity serves as a stand-in, proxy, or representative performing a role on behalf of another entity.
-
B.
roleDuringOccupation
Indicates the specific role or position an entity held during a particular occupation or period of control.
-
C.
appliedDuringRole
Indicates that an action, method, or process was carried out specifically while an entity was serving in a particular role or position.
-
D.
possibleRole
Indicates that an entity is capable of or eligible to serve in a particular role or function in a given context.
-
E.
exportRole
Indicates that an entity functions in a capacity or role specifically related to exporting goods, services, or data.
- F. None of above. chosen
Provenance (4 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_69ef3558cf8881909595ef89daf6e14a |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f7688dd3d08190ad13d0e780570a1c |
completed | May 3, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_69f767fcf2f881908bacc7bfc38e68a5 |
completed | May 3, 2026, 3:21 p.m. |
| PDg | Predicate description generation | batch_69f7688cea58819098bdfd7c80df7634 |
completed | May 3, 2026, 3:23 p.m. |
Created at: April 27, 2026, 10:59 a.m.