Triple
T35416068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Memoirs of Augustyn Kordecki |
E1023643
|
entity |
| Predicate | documentsOpposingSide |
P183289
|
FINISHED |
| Object | Swedish forces |
—
|
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: Swedish forces | Statement: [Memoirs of Augustyn Kordecki, documentsOpposingSide, Swedish forces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: documentsOpposingSide Context triple: [Memoirs of Augustyn Kordecki, documentsOpposingSide, Swedish forces]
-
A.
documentsPerspective
Indicates that one entity records, represents, or expresses the viewpoint or perspective of another entity.
-
B.
documentsDecisionsOn
Indicates that one entity records, details, or formally captures the decisions made about another entity.
-
C.
documentsNow
Indicates that an entity is currently documenting, recording, or writing about another entity at the present time.
-
D.
documentList
Indicates a relationship where one entity serves as a list or collection of documents associated with another entity.
-
E.
documentAtIssue
Indicates that a particular document is the specific item under consideration or dispute in a given context or proceeding.
- 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_69f76df54bac8190bd0d3b0eb35cda5f |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f79da9f80c8190b0afd8509f28747b |
completed | May 3, 2026, 7:10 p.m. |
| PD | Predicate disambiguation | batch_69f79617d40481909ba372f94209c08b |
completed | May 3, 2026, 6:38 p.m. |
| PDg | Predicate description generation | batch_69f79da8d8848190ab5ab1bdad95d58c |
completed | May 3, 2026, 7:10 p.m. |
Created at: May 3, 2026, 4:03 p.m.