Triple
T12913730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Citadel guardians |
E308923
|
entity |
| Predicate | threatLevelOfPrisoners |
P61645
|
FINISHED |
| Object | cosmic |
—
|
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: cosmic | Statement: [Citadel guardians, threatLevelOfPrisoners, cosmic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: threatLevelOfPrisoners Context triple: [Citadel guardians, threatLevelOfPrisoners, cosmic]
-
A.
inmates
Indicates that one entity is confined or held as a prisoner within an institution or facility associated with another entity.
-
B.
prisonerType
Indicates the classification or category assigned to a prisoner within a correctional or detention system.
-
C.
estimatedPrisonerCount
Indicates the estimated number of prisoners associated with a particular context, such as a location, time period, or event.
-
D.
hasPrisoners
Indicates that an entity holds or contains one or more individuals who are imprisoned or detained.
-
E.
threatLevelDescription
chosen
Indicates a textual description that characterizes the severity or nature of a threat level associated with an entity or situation.
- 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_69d7bdf92b588190acdf2a2291ac4590 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d971a0d6508190bca9668e9e06abfe |
completed | April 10, 2026, 9:54 p.m. |
| PD | Predicate disambiguation | batch_69d96fa9b7708190a9e9fa30f59ff580 |
completed | April 10, 2026, 9:46 p.m. |
Created at: April 9, 2026, 5:41 p.m.