Triple
T10883103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Red Cross visit of 1944 |
E256973
|
entity |
| Predicate | afterwards |
P1691
|
FINISHED |
| Object | continued deportations from Theresienstadt to Auschwitz |
—
|
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: continued deportations from Theresienstadt to Auschwitz | Statement: [Red Cross visit of 1944, afterwards, continued deportations from Theresienstadt to Auschwitz]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: afterwards Context triple: [Red Cross visit of 1944, afterwards, continued deportations from Theresienstadt to Auschwitz]
-
A.
after
chosen
Indicates that one event, state, or action occurs later in time than another, following it in temporal order.
-
B.
aftermathOf
Indicates that one event, state, or condition occurs as a consequence or result following another event.
-
C.
releasedAfterSuccessOf
Indicates that one entity was released following, and likely in response to, the successful performance or reception of another entity.
-
D.
aftermathDescription
Indicates the description or characterization of events, conditions, or consequences that occur following a particular incident or action.
-
E.
heldAfter
Indicates that one event or state occurs or is maintained at some point in time after another specified event or state.
- 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_69d6aa848804819081b2713ca0bedf06 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d751db24208190b3a7ed7eea118522 |
completed | April 9, 2026, 7:14 a.m. |
| PD | Predicate disambiguation | batch_69d70d360c388190a3d829fe8862434f |
completed | April 9, 2026, 2:21 a.m. |
Created at: April 8, 2026, 9:21 p.m.