Triple
T3641316
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bifrost |
E77192
|
entity |
| Predicate | guardFunction |
P38819
|
FINISHED |
| Object | controls access to Asgard |
—
|
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: controls access to Asgard | Statement: [Bifrost, guardFunction, controls access to Asgard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: guardFunction Context triple: [Bifrost, guardFunction, controls access to Asgard]
-
A.
guardType
Indicates the specific kind or category of guarding role or protection associated with an entity.
-
B.
safetyFunction
Indicates that one entity serves as a safety-related function or mechanism that protects, safeguards, or reduces risk for another entity or process.
-
C.
guardMounting
Indicates the action of assigning or taking up a position for guard duty, typically as part of a scheduled security or watch rotation.
-
D.
guardedSectionOf
Indicates a relationship where one entity serves as a protective or security boundary for a specific section or portion of another entity.
-
E.
hasSecurityFunction
chosen
Indicates that an entity performs, provides, or is responsible for a security-related role, protection mechanism, or safeguarding function for another entity or system.
- 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_69ad85de1b988190a45f8dbfebc806fc |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc357c3308190bd8801d68244a53e |
completed | March 8, 2026, 6:43 p.m. |
| PD | Predicate disambiguation | batch_69adb8445b2c8190ab07f6ad4e010d0e |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:24 p.m.