Triple
T17691343
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Normandie dry dock |
E441033
|
entity |
| Predicate | purposeOfAttack |
P38945
|
FINISHED |
| Object | to deny the dock to German capital ships |
—
|
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: to deny the dock to German capital ships | Statement: [Normandie dry dock, purposeOfAttack, to deny the dock to German capital ships]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: purposeOfAttack Context triple: [Normandie dry dock, purposeOfAttack, to deny the dock to German capital ships]
-
A.
objectiveOfAttackers
Indicates the target or goal that attackers aim to reach or affect through their attack.
-
B.
aimOfAttacker
chosen
Indicates that a particular goal, target, or objective is what the attacker intends to achieve or affect.
-
C.
reasonForAttack
Indicates that one entity’s attack on another is motivated or caused by the specified reason.
-
D.
tacticalPurpose
Indicates the specific tactical objective or intended operational role that an action, asset, or decision is meant to achieve within a broader plan or mission.
-
E.
attackType
Indicates the specific method, style, or category of attack used in an aggressive or hostile action between entities.
- 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_69d8b9e940b081908b862bb0e6e89b0d |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e47152306c819086d483d87348db5d |
completed | April 19, 2026, 6:08 a.m. |
| PD | Predicate disambiguation | batch_69e3cde3673c8190a889e14ba1f07dc1 |
completed | April 18, 2026, 6:30 p.m. |
Created at: April 10, 2026, 10:03 a.m.