Triple
T4122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Central Intelligence Agency |
E78
|
entity |
| Predicate | primaryRole |
P88
|
FINISHED |
| Object | foreign intelligence collection |
—
|
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: foreign intelligence collection | Statement: [Central Intelligence Agency, primaryRole, foreign intelligence collection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryRole Context triple: [Central Intelligence Agency, primaryRole, foreign intelligence collection]
-
A.
role
Indicates the function, position, or responsibility that one entity holds in relation to another within a given context.
-
B.
keyPerson
Indicates that a person plays a primary, central, or critically important role in relation to an organization, project, or entity.
-
C.
purpose
Indicates that one entity exists, is done, or is used in order to achieve, support, or serve the goal, function, or intended outcome of another entity.
-
D.
hasPrimaryFunction
chosen
Indicates that one entity serves as the main or principal function or role of another entity.
-
E.
parent
Indicates a relationship where one entity is the direct mother or father of another entity, from whom that other entity is descended.
- 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_69a238d6b47881909e68288aed2fd858 |
completed | Feb. 28, 2026, 12:37 a.m. |
| NER | Named-entity recognition | batch_69a23bcc8eb48190b897cc331563980a |
completed | Feb. 28, 2026, 12:50 a.m. |
| PD | Predicate disambiguation | batch_69a23994309081909ff3e869deef2156 |
completed | Feb. 28, 2026, 12:40 a.m. |
Created at: Feb. 28, 2026, 12:40 a.m.