Triple
T11020722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Statesman |
E260479
|
entity |
| Predicate | hasSecurityClearanceLevel |
P20877
|
FINISHED |
| Object | top secret |
—
|
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: top secret | Statement: [Statesman, hasSecurityClearanceLevel, top secret]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSecurityClearanceLevel Context triple: [Statesman, hasSecurityClearanceLevel, top secret]
-
A.
hasClearance
chosen
Indicates that one entity possesses the required authorization level or permission to access or perform actions on another entity or resource.
-
B.
hasClearanceBelow
Indicates that one entity’s clearance level is lower than another entity’s clearance level.
-
C.
canBeDeclassifiedBy
Indicates that an item currently classified or restricted may be lawfully downgraded or released by a specified authority or entity.
-
D.
hasTypeOfSecrecy
Indicates that something is associated with a particular kind or level of secrecy.
-
E.
hasSecurityScreening
Indicates that an entity is subject to, or has undergone, a security screening process.
- 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_69d6aa9687448190b28d353b1b6a610e |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d797baad408190a53fd6941a750f68 |
completed | April 9, 2026, 12:12 p.m. |
| PD | Predicate disambiguation | batch_69d72e995e008190bbffb314129ed0cd |
completed | April 9, 2026, 4:44 a.m. |
Created at: April 8, 2026, 9:25 p.m.