Triple
T27926688
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MS10-042 |
E707854
|
entity |
| Predicate | informationDomain |
P112931
|
FINISHED |
| Object | computer security |
—
|
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: computer security | Statement: [MS10-042, informationDomain, computer security]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: informationDomain Context triple: [MS10-042, informationDomain, computer security]
-
A.
typeOfInformation
Indicates that one entity specifies the category or kind of information that characterizes or describes another entity.
-
B.
informationStructure
Indicates how information within a communication is organized or structured, such as what is presented as given, new, focused, or backgrounded.
-
C.
knowledgeScope
Indicates the extent or range of information, topics, or understanding that an entity possesses or is concerned with.
-
D.
involvedDomain
chosen
Indicates that an entity participates in or is associated with a particular domain, field, or area of activity.
-
E.
usesInformationFor
Indicates that one entity applies or exploits information obtained from another entity for a particular purpose or activity.
- 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_69ef96bbf2c48190a9d0e0291457aab6 |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f6562fd3488190be1acd8c526a28d2 |
completed | May 2, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69f651a931748190a637e631a52bbfaa |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 27, 2026, 7 p.m.