Triple
T23079473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CSS Arkansas |
E575426
|
entity |
| Predicate | armourPurpose |
P6071
|
FINISHED |
| Object | protection against Union naval gunfire |
—
|
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: protection against Union naval gunfire | Statement: [CSS Arkansas, armourPurpose, protection against Union naval gunfire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: armourPurpose Context triple: [CSS Arkansas, armourPurpose, protection against Union naval gunfire]
-
A.
armour
chosen
Indicates that an entity provides protective covering or defense for another entity.
-
B.
armorType
Indicates the specific category or classification of protective armor associated with an entity.
-
C.
armourBelt
Indicates a relationship where an armour belt is equipped on, attached to, or associated with an entity (such as a character, vehicle, or structure) as protective gear.
-
D.
armourCoverage
Indicates the extent or area of a subject’s body or structure that is protected or covered by armour.
-
E.
wearsArmorOf
Indicates that one entity is equipped with or dressed in the specific armor that belongs to or is associated with another entity.
- 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_69e245be28d48190ad1348d5a73db37d |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18c66a80481909ebc2ba69f1e4bd9 |
completed | April 29, 2026, 4:43 a.m. |
| PD | Predicate disambiguation | batch_69ef89e5ce748190b2c3ac3843484127 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:56 p.m.