Triple
T7370296
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Kock |
E169981
|
entity |
| Predicate | PolishObjective |
P76618
|
FINISHED |
| Object | delay German advance and maintain organized resistance |
—
|
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: delay German advance and maintain organized resistance | Statement: [Battle of Kock, PolishObjective, delay German advance and maintain organized resistance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: PolishObjective Context triple: [Battle of Kock, PolishObjective, delay German advance and maintain organized resistance]
-
A.
polishObjective
Indicates that an entity’s goal or target is to improve, refine, or perfect another entity.
-
B.
polishUnit
Indicates that one entity performs the action of polishing or refining another entity, typically improving its surface, appearance, or quality.
-
C.
officialNamePolish
Indicates the official or legally recognized name of an entity as expressed in the Polish language.
-
D.
PolishCommander
Indicates that an entity serves as a military commander associated with Poland.
-
E.
hasNameInPolish
Indicates that an entity is associated with a specific name or label expressed in the Polish language.
- 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_69c68a5bfaac81909ce7f001dfb70c76 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f182df5c81908964fbaa3f8ec790 |
completed | March 27, 2026, 9:07 p.m. |
| PD | Predicate disambiguation | batch_69c6f02ee3e08190a7a00c981129b22c |
completed | March 27, 2026, 9:01 p.m. |
| PDg | Predicate description generation | batch_69c6f0ebf9c88190af5a4d87d3fd338a |
completed | March 27, 2026, 9:04 p.m. |
Created at: March 27, 2026, 3:07 p.m.