Triple
T30636090
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St Michael and the Devil |
E779846
|
entity |
| Predicate | portraysRoleOfMichael |
P100368
|
FINISHED |
| Object | warrior angel |
—
|
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: warrior angel | Statement: [St Michael and the Devil, portraysRoleOfMichael, warrior angel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portraysRoleOfMichael Context triple: [St Michael and the Devil, portraysRoleOfMichael, warrior angel]
-
A.
portraysRoleTrait
Indicates that one entity depicts or represents a particular role or character trait of another entity.
-
B.
portraysPersonAs
chosen
Indicates that one entity represents, depicts, or characterizes another person in a particular way or role.
-
C.
portraysActorAs
Indicates that one entity depicts or represents an actor in a particular role, character, or manner.
-
D.
portraysDoubleRole
Indicates that a single performer or entity depicts or assumes two distinct roles within the same context or work.
-
E.
hasPortrayedPersonRole
Indicates that an entity has performed or held a specific role in portraying a particular person (e.g., in a film, play, or other representation).
- 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_69f224a50ebc81909b961a94c7f66b12 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fd974d75e08190af46b1d608769f3b |
completed | May 8, 2026, 7:57 a.m. |
| PD | Predicate disambiguation | batch_69fd94ff792c8190bedf4a639d3da809 |
completed | May 8, 2026, 7:47 a.m. |
Created at: April 29, 2026, 8:28 p.m.