Triple
T10173484
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elsa Schneider |
E235790
|
entity |
| Predicate | covertRole |
P92521
|
FINISHED |
| Object | Nazi collaborator |
—
|
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: Nazi collaborator | Statement: [Elsa Schneider, covertRole, Nazi collaborator]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: covertRole Context triple: [Elsa Schneider, covertRole, Nazi collaborator]
-
A.
conversionRole
Indicates the specific role or function an entity plays within a conversion process or event.
-
B.
characterRoleSwap
Indicates a relationship where two characters exchange or assume each other’s narrative roles or functions within a story or scenario.
-
C.
deFactoRole
Indicates that an entity effectively functions in a role or capacity in practice, even if that role is not formally or officially assigned.
-
D.
playRoleIn
Indicates that an entity participates in or performs a specific function, character, or part within an event, context, or system.
-
E.
encodingRole
Indicates the role or function an entity has in the process of encoding information into a particular form or representation.
- 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_69ca84d1d5f88190ab878a1021ecff68 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdeca0dc508190916f2a1bbb288192 |
completed | April 2, 2026, 4:12 a.m. |
| PD | Predicate disambiguation | batch_69cd7c79f21c8190a7f31b2eab80b8ba |
completed | April 1, 2026, 8:13 p.m. |
| PDg | Predicate description generation | batch_69cd7edc6cf081909d95859d880a4059 |
completed | April 1, 2026, 8:23 p.m. |
Created at: March 30, 2026, 9:11 p.m.