Triple
T38083161
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Auschwitz trials in Frankfurt |
E950907
|
entity |
| Predicate | numberOfIndictedPersons |
P866
|
FINISHED |
| Object | 22 |
—
|
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: 22 | Statement: [Auschwitz trials in Frankfurt, numberOfIndictedPersons, 22]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfIndictedPersons Context triple: [Auschwitz trials in Frankfurt, numberOfIndictedPersons, 22]
-
A.
numberOfIndictedPersonsApproximate
Indicates an approximate count of persons who have been formally indicted in a given context or case.
-
B.
numberOfPeopleAccused
chosen
Indicates the count of individuals who are formally alleged to have committed a particular act or offense.
-
C.
numberOfPerpetrators
Indicates the count of distinct individuals who carried out or participated in a particular act, event, or offense.
-
D.
numberOfInmatesInvolved
Indicates the count of inmates who participated in or were involved in a specified incident or event.
-
E.
dateFirstIndictmentsIssued
Indicates the date on which the first formal indictments in a particular case or investigation were officially issued.
- 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_69f76f03a3608190a73fd6df87c792a8 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a037df1223c8190a5d61e4f8e6fd613 |
completed | May 12, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_6a037a1ad6c48190bfe35d350c1b4751 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:21 p.m.