Triple
T20620407
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crowley |
E506683
|
entity |
| Predicate | relationshipTypeWithAziraphale |
P140807
|
FINISHED |
| Object | unlikely friendship |
—
|
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: unlikely friendship | Statement: [Crowley, relationshipTypeWithAziraphale, unlikely friendship]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWithAziraphale Context triple: [Crowley, relationshipTypeWithAziraphale, unlikely friendship]
-
A.
angelicHierarchy
Indicates a hierarchical relationship in which one angelic being holds a higher or lower rank or order relative to another within a structured celestial order.
-
B.
relationshipWithAngelEyes
Indicates a personal or significant connection that an entity has with the individual referred to as AngelEyes.
-
C.
associatedWithArchangelName
Indicates that something has a connection or linkage to a specific archangel’s name.
-
D.
spiritualConsortOf
Indicates a relationship in which one entity is regarded as the spiritual or sacred partner, counterpart, or consort of another.
-
E.
associatedReligionRole
Indicates that one entity holds a specific religious role, office, or function in relation to another entity.
- F. None of above. chosen
Provenance (4 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_69e0b4bc90988190ac360aaf645efc1d |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6abe19ca481908c896bec49a025cd |
completed | April 20, 2026, 10:42 p.m. |
| PD | Predicate disambiguation | batch_69e5a00c43308190b7ea58d559257e07 |
completed | April 20, 2026, 3:39 a.m. |
| PDg | Predicate description generation | batch_69e5a6a9f3f88190b961db9aca36f7da |
completed | April 20, 2026, 4:08 a.m. |
Created at: April 16, 2026, 11:42 a.m.