Triple
T37505053
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Curveball |
E932068
|
entity |
| Predicate | usedCodenameIn |
P61115
|
FINISHED |
| Object | German intelligence files |
—
|
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 intelligence files | Statement: [Curveball, usedCodenameIn, German intelligence files]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedCodenameIn Context triple: [Curveball, usedCodenameIn, German intelligence files]
-
A.
usesCodeName
chosen
Indicates that one entity refers to another entity by a code name or alias instead of its real or full designation.
-
B.
endUseAsCodename
Indicates that an entity stops being used as a codename for another entity or concept.
-
C.
relatedCodename
Indicates that one entity has an associated or connected codename that is contextually related to it.
-
D.
usesCodenameTheme
Indicates that an entity adopts a consistent codename pattern or motif (e.g., colors, planets, mythological figures) for naming related items or agents.
-
E.
codenameUser
Indicates that a user is assigned or associated with a particular codename.
- 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_69f76ec5268481909ea01c73aeeefd42 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fba5eec0448190a5e6f0c43fdcd0e3 |
completed | May 6, 2026, 8:34 p.m. |
| PD | Predicate disambiguation | batch_69fba34edd548190bfa980e6e16e0a88 |
completed | May 6, 2026, 8:23 p.m. |
Created at: May 3, 2026, 4:17 p.m.