Triple
T11392007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Richthofen memorial at Vaux-sur-Somme |
E269864
|
entity |
| Predicate | memorializesDeathDate |
P865
|
FINISHED |
| Object | 21 April 1918 |
—
|
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: 21 April 1918 | Statement: [Richthofen memorial at Vaux-sur-Somme, memorializesDeathDate, 21 April 1918]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: memorializesDeathDate Context triple: [Richthofen memorial at Vaux-sur-Somme, memorializesDeathDate, 21 April 1918]
-
A.
commemorationDate
Indicates the date on which an event, person, or occasion is formally remembered or honored.
-
B.
commemoratedOn
chosen
Indicates that something is remembered, honored, or celebrated on a specific date or occasion.
-
C.
memorializesDeathsDuring
Indicates a relationship in which something serves as a memorial specifically for deaths that occurred during a particular event, period, or circumstance.
-
D.
commemoratesPersonDeathYear
Indicates that something marks, honors, or is associated with the year in which a specific person died.
-
E.
formerlyCommemoratedOn
Indicates that an entity was previously commemorated or observed on a particular date, but is no longer commemorated on that date.
- 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_69d6aacdbc6c8190af6dc3d5f5d22836 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d8001796f48190822526f52e3f0337 |
completed | April 9, 2026, 7:37 p.m. |
| PD | Predicate disambiguation | batch_69d7e70b228c8190b87f5101fd683788 |
completed | April 9, 2026, 5:51 p.m. |
Created at: April 8, 2026, 9:34 p.m.