Triple
T29527579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Magnum ELINT satellite |
E749108
|
entity |
| Predicate | allegedCoverName |
P21109
|
FINISHED |
| Object | Magnum |
—
|
NE NERFINISHED |
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: Magnum | Statement: [Magnum ELINT satellite, allegedCoverName, Magnum]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: allegedCoverName Context triple: [Magnum ELINT satellite, allegedCoverName, Magnum]
-
A.
hasCoverName
chosen
Indicates that one entity uses or is known by an alternative, often secret or assumed, name in relation to another entity or context.
-
B.
brandCovered
Indicates that one entity provides coverage, representation, or inclusion for a particular brand within its scope (e.g., in a policy, service, catalog, or offering).
-
C.
isCover
Indicates that one entity functions as a protective or concealing layer over another entity.
-
D.
usedCover
Indicates that one entity employed another entity as a protective or concealing cover in a given context.
-
E.
coverSymbol
Indicates that one symbol or notation is used as a cover or representative marker for another entity in a given context.
- 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_69f0bd46d99c81908ba9d01cc1dbef7d |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f7117e55908190a67105e92bc4830f |
completed | May 3, 2026, 9:12 a.m. |
| PD | Predicate disambiguation | batch_69f70f380690819090cc34763ba460ed |
completed | May 3, 2026, 9:02 a.m. |
Created at: April 28, 2026, 4:48 p.m.