Triple
T13258842
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SD-6 |
E315734
|
entity |
| Predicate | coverRole |
P109187
|
FINISHED |
| Object | black-ops division of the CIA |
—
|
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: black-ops division of the CIA | Statement: [SD-6, coverRole, black-ops division of the CIA]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coverRole Context triple: [SD-6, coverRole, black-ops division of the CIA]
-
A.
coversPerson
Indicates that one entity provides protection, insurance, or inclusion for a person under its scope or terms.
-
B.
coverSymbol
Indicates that one symbol or notation is used as a cover or representative marker for another entity in a given context.
-
C.
cover
Indicates that one entity extends over, conceals, protects, or provides a surface or layer for another entity.
-
D.
coverText
Indicates that one text serves as the cover or front-facing textual representation for another work or resource.
-
E.
formerCover
Indicates that one entity previously served as the cover (e.g., protective or outer layer) for another entity but no longer does so.
- F. None of above. chosen
Provenance (4 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_69d806b1d9ac8190852c5571d5bd5f0f |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99cfdc9388190af1fdd3cd4717bd8 |
completed | April 11, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69d98f60911081909fa346a054f76c9f |
completed | April 11, 2026, 12:01 a.m. |
| PDg | Predicate description generation | batch_69d99cf7f9c48190a6a4f452b4a2aefa |
completed | April 11, 2026, 12:59 a.m. |
Created at: April 9, 2026, 9:25 p.m.