Triple
T745158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lucie Maria Rommel |
E15324
|
entity |
| Predicate | roleAfterEvent |
P4073
|
FINISHED |
| Object | guardian of Erwin Rommel's public image |
—
|
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: guardian of Erwin Rommel's public image | Statement: [Lucie Maria Rommel, roleAfterEvent, guardian of Erwin Rommel's public image]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleAfterEvent Context triple: [Lucie Maria Rommel, roleAfterEvent, guardian of Erwin Rommel's public image]
-
A.
createdAfterEvent
Indicates that the creation of one entity occurred after a specified event in time.
-
B.
significantEventRole
Indicates that an entity plays an important or defining role in a particular significant event.
-
C.
eventRole
chosen
Indicates the specific function, capacity, or part an entity plays within an event or occurrence.
-
D.
assignsRoleTo
Indicates that one entity designates or grants a specific role or position to another entity.
-
E.
successorStateRole
Indicates that one role represents the state or position that directly follows and replaces another role in a sequence or process.
- 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_69a49358aa308190adbc9b5a0a2adcf9 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a61217b881908592096b1edacb8a |
completed | March 1, 2026, 8:48 p.m. |
| PD | Predicate disambiguation | batch_69a4a4ff10608190bfd60b4a1cb38f7d |
completed | March 1, 2026, 8:43 p.m. |
Created at: March 1, 2026, 7:37 p.m.