Triple
T2837959
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Kolberg (1945) |
E62394
|
entity |
| Predicate | defensiveStatus |
P8412
|
FINISHED |
| Object | fortress city |
—
|
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: fortress city | Statement: [Battle of Kolberg (1945), defensiveStatus, fortress city]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defensiveStatus Context triple: [Battle of Kolberg (1945), defensiveStatus, fortress city]
-
A.
defensiveRole
Indicates that an entity serves a protective or guarding function in relation to another entity or context.
-
B.
canBeDefendedIn
Indicates that something (such as a claim, action, or position) is capable of being justified or supported within a specified context, forum, or framework.
-
C.
defensiveStructure
chosen
Indicates a relationship where one entity functions as a structure built or used to protect, defend, or fortify another entity or area.
-
D.
defensivePlan
Indicates a relationship where an entity formulates or adopts a strategy specifically intended to protect against threats, attacks, or other adverse actions.
-
E.
defensiveTask
Indicates a task in which an entity protects, guards, or defends another entity or resource from potential threats or harm.
- 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_69ab4c3d16bc81908b3a1c98fbd287fe |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdef015bc81909f6a2ff17b22862f |
completed | March 7, 2026, 8:16 a.m. |
| PD | Predicate disambiguation | batch_69abdd0ce8b08190ba28c192988f38ce |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 10:01 p.m.