Triple
T1491150
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Attack Surface |
E29581
|
entity |
| Predicate | protagonistEmployer |
P7
|
FINISHED |
| Object | private security contractor |
—
|
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: private security contractor | Statement: [Attack Surface, protagonistEmployer, private security contractor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: protagonistEmployer Context triple: [Attack Surface, protagonistEmployer, private security contractor]
-
A.
featuresProtagonistOccupation
Indicates that the work’s main character has a specified occupation or job role.
-
B.
employer
chosen
Indicates a relationship where one entity hires, pays, and oversees the work of another entity.
-
C.
formerEmployer
Indicates that one entity previously employed the other but no longer does so.
-
D.
antagonistOccupation
Indicates the role, job, or professional activity that the antagonist character performs.
-
E.
protagonistType
Indicates the role or category that the main character (protagonist) of a story or scenario belongs to.
- 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_69a498da82e08190ba833330d05f380f |
completed | March 1, 2026, 7:51 p.m. |
| NER | Named-entity recognition | batch_69a4c6c3ace4819081bc2b86ee2486b6 |
completed | March 1, 2026, 11:07 p.m. |
| PD | Predicate disambiguation | batch_69a4c48902808190a8028d359bcf123e |
completed | March 1, 2026, 10:58 p.m. |
Created at: March 1, 2026, 8:12 p.m.