Triple
T36385665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Helga Susanne Goebbels |
E896187
|
entity |
| Predicate | employerOfFather |
P171417
|
FINISHED |
| Object | Ministry of Public Enlightenment and Propaganda |
—
|
NE NERFINISHED |
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: Ministry of Public Enlightenment and Propaganda | Statement: [Helga Susanne Goebbels, employerOfFather, Ministry of Public Enlightenment and Propaganda]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: employerOfFather Context triple: [Helga Susanne Goebbels, employerOfFather, Ministry of Public Enlightenment and Propaganda]
-
A.
hasFatherEmployer
Indicates that the employer of a person’s father is related to or associated with that person.
-
B.
parentEmployer
Indicates that one organization is the direct or higher-level employer of another organization or entity.
-
C.
fatherOccupation
Indicates the type of job or profession held by a person's father.
-
D.
parentWorksAt
chosen
Indicates that the parent of a given person is employed at a specified organization or workplace.
-
E.
roleInFatherWork
Indicates that one entity has a specific role or involvement in the work or professional activities of another entity identified as the father.
- 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_69f76e51d358819092bbc5f119f49476 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fbc9d1dba881908c399b8e1dc13ce2 |
completed | May 6, 2026, 11:08 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ec03ac8190a757563f96fab283 |
completed | May 6, 2026, 11:04 p.m. |
Created at: May 3, 2026, 4:10 p.m.