Triple
T22366587
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Georg Elser Memorial, Berlin |
E552919
|
entity |
| Predicate | memorializedPersonOccupation |
P122548
|
FINISHED |
| Object | carpenter |
—
|
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: carpenter | Statement: [Georg Elser Memorial, Berlin, memorializedPersonOccupation, carpenter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: memorializedPersonOccupation Context triple: [Georg Elser Memorial, Berlin, memorializedPersonOccupation, carpenter]
-
A.
commemoratedPersonOccupation
chosen
Indicates the occupation or professional role held by the person who is being commemorated.
-
B.
commemoratedPerson
Indicates that the subject serves as a memorial or tribute to the referenced person.
-
C.
commemoratedPersonNationality
Indicates the nationality of the person who is being commemorated.
-
D.
memorialRole
Indicates that an entity holds a specific role, capacity, or function in relation to a memorial or commemorative context.
-
E.
memorialName
Indicates that a memorial is known by or designated with a particular name.
- 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_69e11e4affcc8190ba7c27d29062558d |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1580074dc819091305ac7017000d3 |
completed | April 29, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69e73011e6388190a05edf137f488441 |
completed | April 21, 2026, 8:06 a.m. |
Created at: April 16, 2026, 8:44 p.m.