Triple
T37774595
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gypsy family camp at Auschwitz-Birkenau |
E941649
|
entity |
| Predicate | firstTransportArrived |
P49364
|
FINISHED |
| Object | February 1943 |
—
|
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: February 1943 | Statement: [Gypsy family camp at Auschwitz-Birkenau, firstTransportArrived, February 1943]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstTransportArrived Context triple: [Gypsy family camp at Auschwitz-Birkenau, firstTransportArrived, February 1943]
-
A.
firstCompleteTransitBy
Indicates the agent (such as a person, vehicle, or mission) that first successfully completed a full transit or passage through a specified route, medium, or region.
-
B.
arrivalFrom
Indicates that an entity arrives at a location or state originating from a specified source location or state.
-
C.
arrivalAt
chosen
Indicates the event or state of an entity reaching and being present at a specific destination or location.
-
D.
transportedAfter
Indicates that one entity is transported only after the transportation of another entity has occurred in time.
-
E.
openedToTransit
Indicates that a route, passage, or connection has been made available or accessible for transit or movement between locations.
- 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_69f76ee4431881908f87e8892a9f39f3 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1772e48190ba738c6d11b321e2 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:19 p.m.