Triple
T9514281
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Task Group 22.3 |
E229482
|
entity |
| Predicate | capturedMaterial |
P14511
|
FINISHED |
| Object | German naval codebooks from U-505 |
—
|
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: German naval codebooks from U-505 | Statement: [Task Group 22.3, capturedMaterial, German naval codebooks from U-505]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capturedMaterial Context triple: [Task Group 22.3, capturedMaterial, German naval codebooks from U-505]
-
A.
capturedFor
Indicates that one entity has been taken into custody, control, or possession specifically for the benefit, use, or purpose of another entity.
-
B.
capturedEquipment
chosen
Indicates that one party has taken possession of another party’s equipment, typically as a result of conflict, competition, or enforcement.
-
C.
capturedBy
Indicates that one entity has been seized, taken into control, or otherwise apprehended by another entity.
-
D.
capturedOff
Indicates that one entity has taken another entity away or into custody, removing it from its original location or control.
-
E.
materialUsed
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
- 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_69ca84777560819084cddd999badc1aa |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd986bfcac8190aa97f8975cb17f6c |
completed | April 1, 2026, 10:13 p.m. |
| PD | Predicate disambiguation | batch_69cca567ca448190bf4bcce8ce7dd54f |
completed | April 1, 2026, 4:56 a.m. |
Created at: March 30, 2026, 7:58 p.m.