Triple
T28716421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First Lady of Poland |
E729972
|
entity |
| Predicate | canAdvocateFor |
P33
|
FINISHED |
| Object | health-related causes |
—
|
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: health-related causes | Statement: [First Lady of Poland, canAdvocateFor, health-related causes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canAdvocateFor Context triple: [First Lady of Poland, canAdvocateFor, health-related causes]
-
A.
publicAdvocateStart
Indicates that a public advocate begins their term, role, or official activities.
-
B.
canOppose
Indicates that one entity has the ability or capacity to resist, counteract, or act in opposition to another entity or its actions.
-
C.
advocates
chosen
Indicates that one entity publicly supports, recommends, or argues in favor of another entity or its interests.
-
D.
advocatesIn
Indicates that an entity actively supports, promotes, or argues in favor of something within a particular context, domain, or setting.
-
E.
canBeAppealedTo
Indicates that a decision, action, or authority is subject to being challenged or reviewed by a higher or alternative authority through an appeal process.
- 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_69f043e7d5a4819094b18aca10b1e024 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f656db9bd88190b7e5da4c0da9a479 |
completed | May 2, 2026, 7:56 p.m. |
| PD | Predicate disambiguation | batch_69f651ac855481908e30c3b345d31356 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 5:51 a.m.