Triple
T37307824
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yao’s garbled circuits |
E926124
|
entity |
| Predicate | typicalAdversaryModel |
P127290
|
FINISHED |
| Object | semi-honest adversary |
—
|
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: semi-honest adversary | Statement: [Yao’s garbled circuits, typicalAdversaryModel, semi-honest adversary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalAdversaryModel Context triple: [Yao’s garbled circuits, typicalAdversaryModel, semi-honest adversary]
-
A.
modelsAdversary
chosen
Indicates that one entity represents, simulates, or formally characterizes another entity as an adversary within a given context or system.
-
B.
commonAdversary
Indicates that two or more entities share the same opponent, rival, or threat.
-
C.
adversaryView
Indicates that one entity observes, analyzes, or interprets another entity from the perspective of an opponent or potential attacker.
-
D.
primaryAdversaryPlanning
Indicates that an entity is the main opposing force actively formulating or directing plans against another entity.
-
E.
mainAdversaryDescribedAs
Indicates that the primary opponent or enemy in a conflict is characterized or labeled in a particular way.
- 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_69f76eb1bc508190924e9fa5d8acdeb3 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a11efc08190bb7cacc1325b4dc6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:16 p.m.